Changelog: Bug fixes & improvements

Scholarly is always improving. Here you can find every bug fix, major feature, and other improvements we've made.

August 12th, 2026

More AI models for Premium

Grok 4.6 from xAI replaces Grok 4.5 across chat and create tools. It stays a recommended Frontier model, thinking is always on, and previous Grok 4.5 and Grok 4.3 selections continue automatically.
Premium now includes recommended access to Grok 4.6, Claude Sonnet 5, Gemini 3.1 Pro Preview, and GPT 5.6 Terra. The full supported catalog is also back under More Models, while flashcards keep GPT 5.6 Luna as their focused recommendation.

A clearer pricing page

Rebuilt the pricing page from scratch. Plans and prices now sit at the top of the page instead of below the fold, each plan says who it is for in one line, and the plan comparison table fits on screen instead of scrolling sideways and cutting off the Laureate column.
Teams is back on the pricing page, under a new Personal / Teams switch.
The pricing page no longer has a monthly/yearly toggle. Premium is yearly-only and shows the monthly price instead of the yearly total.
Laureate now leads with what it actually unlocks: the full Frontier model catalogue — Claude Opus 5, Gemini 3.1 Pro and Grok 4.6 — which no other individual plan includes, on 20 creations and 20 chats each week.
Laureate creation Frontier Boosts doubled from 10 to 20 each week. Its 75 total weekly AI creations and 20 Chat Frontier Boosts are unchanged.
Standard video lectures now let you pick a color look — or apply a saved custom design — without leaving Standard. Companion slide decks are included automatically.
Auto (Laureate) now uses Claude Opus 5 at low reasoning for Frontier work. After weekly Frontier uses are gone, Auto continues on GPT 5.6 Luna.

More reliable YouTube transcripts

A YouTube video that needs transcribing is now processed once and picked up wherever your request lands, instead of occasionally failing or being transcribed again when several requests arrive together.

Longer free podcasts

Free podcasts now run up to about 15 minutes — a commute-length listen. Upgrade still unlocks a longer target length.
Podcast now sits with Flashcards and Video Lecture on Home, after you upload, in the New menu, on source AI actions, and as a first-run welcome choice.

Longer free video lectures

Free AI Video Lectures now use Auto length — sized to your sources, typically a few minutes — instead of a 2-minute preview. Paid plans can still pick a specific length up to 15 minutes.

August 11th, 2026

Chat with your Research

Research is now a focused workspace with Report, Sources, and Create tabs, plus a dedicated chat. Ask for a grounded summary, compare findings, challenge a conclusion, or inspect the evidence without leaving the report.
The chat is now the single place to request follow-up research. It can start another background report inside the same Research session, where report history sits beside the chat and progress updates automatically.

Deep Research: source-to-artifact workspace

Starting Deep Research from Home or an old Research link now opens the same guided source-to-result workspace. Add files, folders, saved Scholarly content, Google Drive files, URLs, or a prompt; then set the research objective, depth, evidence priorities, and model, and choose at least one additional deliverable such as a study guide, comparison table, CSV, timeline, or one-page brief.
Research now keeps Report, Sources, Files, and AI Creations in separate tabs above the workspace, gives an active research plan clearer visual separation while it runs, and starts new setup forms at Medium depth.

Simpler AI model controls

Chat, Research, and AI creation now share one consistent model selector with Auto, Auto (Premium), and Auto (Laureate) visible on every plan. The bottom Frontier Boost toggle switches Auto (Laureate) between Claude Sonnet 5 and GPT 5.6 Luna.
Laureate's 75 AI creations, 10 creation Frontier Boosts, and 20 Chat Frontier Boosts now reset every week instead of every month.
Creation setup panels now use consistent, larger section titles and descriptions across designs, expert styles, settings, custom instructions, and Study Packs.

Clearer Premium plan details

The upgrade screen now lists Export & download and Priority support alongside the existing Premium benefits.

Flashcards: new AI & Sources tab

The Sources tab on every flashcard deck is now AI & Sources. Create a podcast, video lecture, study guide, and more straight from the deck's original source material, and see everything else already created from it — all without leaving your deck.
"Created from this" lists across the app now update the moment a generation finishes — no page reload needed.

Regional Pricing

Premium is now ₹1,299 per month or ₹6,199 per year in India. The yearly option keeps the same Premium access while saving about 60% compared with paying month to month.

Bug Fixes

YouTube videos with captions are no longer rejected as "no captions available" when our transcript provider is temporarily rate-limited. Uploads now retry automatically, and if the provider is still busy you'll see an honest "try again shortly" message instead.
Anki flashcard import now supports decks exported by Anki 2.1.50 and newer (the compressed .apkg format). Corrupt deck files also get a clear explanation instead of a raw database error.
Uploading a video that has no audio track no longer fails with a technical error — the video now imports normally, with transcript-based features simply unavailable.
When a chat reply reaches the four-image generation cap, the assistant now finishes its answer with the images it already created instead of the whole reply failing.
Cmd+K and Ctrl+K now open workspace search immediately with the search field ready for typing.
Workspace search now shows content and chats together without extra filters, and the window stays the same height while you type so results no longer shift the layout.
Flashcard decks now show how many Questions are ready directly in the tab, without waiting for you to open Questions first.
Long YouTube videos without captions now finish transcript processing reliably instead of sometimes appearing to have no transcript while processing.
Signing out or switching accounts in the same tab now clears the previous account's library completely. Files from the earlier session no longer appear on Home, in the sidebar, or under All content, and the new account's own content loads right away instead of leaving the workspace empty.
Help chat history, active study sessions, questions marked as hard, and podcast progress checks now reset on sign-out too, so nothing from the previous session carries into the next account.
After sign-up, the onboarding handoff now keeps a clear loading indicator on screen and warms the next workspace view, instead of flashing a blank page before the welcome flow appears.

August 10th, 2026

Explore: dedicated podcast, video, and flashcard pages

Explore now has purpose-built public pages for podcasts, videos, and flashcards. Podcasts get a featured player and a ranked episode chart, videos a cinematic billboard and thumbnail wall, and flashcards an interactive sample card you can flip — every item is real community content, in English and Japanese.
Podcast and video items across Explore now include episode duration and chapter counts.

Bug Fixes

Chats can now reference earlier chats. Type @ to find a previous conversation and bring its user and assistant messages into the current discussion.
Typing @ in Chat now searches your complete library, so older pages, files, recordings, podcasts, Research sessions, and folders remain easy to find even when they have not been loaded yet.
Upgrade and download dialogs now close cleanly when you sign out or switch accounts, so the next account never inherits the previous session's content or action.
AI Meeting Notes mentions in Chat now use their red recording accent instead of appearing as a generic grey upload.
AI Video Lectures now preserve signed values from their sources, keep internal production instructions out of narration, and reliably include a requested companion slide deck.
Returning to a Chat now restores a completed answer, document paging reaches the final page and has accessible controls, and AI creator instruction counters and upload limits explain exactly what is blocking the next step.
Free Exam screens now explain the one-attempt daily allowance and when it resets.
PDFs chosen from a folder's Import screen now continue through the normal uploader and save back into that folder, and uploaded images remain visible there too. File pickers also match the formats the uploader supports, and cloud-synced files show a clear retry message if access is lost.

August 9th, 2026

Bug Fixes

Fixed Illustrated and Short video lectures failing with "Failed to render the video" or drifting out of sync with their narration — the finishing step now preserves the silent beats between scenes instead of collapsing them.
Large Word and PowerPoint documents now convert reliably for reading in chat and Google Drive imports, up to your plan's file-size limit — previously anything over 32MB failed with a raw server error.
Opening Home directly now loads recent chats and existing workspace state correctly, instead of sometimes showing the new-user empty screen until you visited Chat.
Video lecture pages are cleaner: companion decks now open in a Slides tab, and the redundant AI Generated badge is gone.
Companion slide decks are now included for Free members too and are enabled by default for every Standard AI Video Lecture. Everyone can review and present the deck in the Slides tab; downloads remain a Premium feature.

August 8th, 2026

Video Lectures: color variety and Dark Mode

Standard video lectures now draw from a pool of hand-tuned color palettes — soft pastels, brights, and editorial wildcards alongside the classic cream-and-blue — so each new lecture gets its own look while keeping the same clean design. Charts, cards, and embedded diagrams all follow the drawn palette.
A new Dark Mode toggle in the video creation panel renders every slide on a clean dark theme, drawn from five dark palettes with matched accents and chart colors.

Stronger reasoning in paid Auto

Paid Auto now uses high reasoning effort in Chat and agent-powered AI creators, including Research, slides, documents, video lectures, infographics, and podcasts. Flashcards keep their balanced medium setting, and Free Auto remains unchanged.

Video lectures can include a slide deck

Every Standard AI Video Lecture can include a companion PDF deck, with the option enabled by default on every plan. Each page captures the completed teaching scene, and the finished deck opens in its own Slides tab without using another AI creation; Premium members can also download it beside the MP4.

Bug Fixes

Fixed chat turns that could spend the entire turn running web searches and end with a “used all of its research steps” error — the assistant now wraps up and answers from the results it already gathered.
Stopping a new Chat answer now works reliably even when the stream is still starting, instead of sometimes leaving the answer running.
Switching away from the Library tab in an AI creator now preserves the folder and loaded page you were browsing. AVIF images imported from a URL are also recognized correctly.
The docked podcast player keeps its chapter label aligned after a chapter seek, and study progress is cleared and isolated when accounts change.
Older study-guide paragraphs render again instead of disappearing, and pill-style selectors now keep their intended fully rounded shape at every size.
Shared flashcard study guides now verify that the deck belongs to the page being viewed, keeping another deck's highlights private.
Settings, sharing, and other dialogs now open above the entire page, including an expanded podcast chat, so every control remains visible and usable.
Downloads now consistently require Premium across Chat podcasts, file and Office preview fallbacks, and AI Playground images. Free members see the share-or-upgrade choice instead of downloading directly.

Clearer content tabs

AI Creations and source lineage now share one AI & Sources tab across podcasts, video lectures, PDFs, files, and Research, keeping the same create, related-output, and source details together.
Podcast Producer Notes and Related Resources are gathered into one Deep dive tab, and the bottom player stays pinned while signed-out listeners browse a shared episode.
Podcasts with chapter slides now gain a synchronized Video mode and a share-ready MP4. Video rendering happens separately so the finished audio stays available; MP4 downloads are included on paid plans.

Calmer podcast and video pages

The episode header no longer repeats the cover art, title, and duration the player already shows. It is one details line with the summary folded to two lines, so the slide, the tabs, and your chapters all fit on screen without scrolling.
Chapters are now a numbered list you can scan and jump from, on both podcasts and video lectures. The sideways-scrolling cards are gone, along with the shrunken copy of the slide that was already playing above them.
Fewer, clearer tabs. Producer Notes and Related Resources become Deep dive on podcasts, and video Questions moves into the tab row instead of sitting permanently open between the player and everything else.

August 7th, 2026

Premium plan updates

Premium includes 10 AI creations each week, shared across flashcards, podcasts, video lectures, slides, documents, Deep Research, and the other AI creators. The allowance resets every Monday at 00:00 UTC.
Settings → Billing now shows your live weekly usage. A failed creation returns its slot automatically, and reaching the limit leaves all existing work available while showing the next reset clearly.

Expert styles in every AI creator

Every AI creation panel now offers format-specific expert styles beside the other creative choices — including quizzes, essays, reports, case studies, rubrics, cheat sheets, and general documents. Quiz styles and custom instructions now also steer the generated questions.

The podcast player now docks at the bottom

The episode player sits in a bar pinned to the bottom of the page — play, skip, speed, and your position in the episode stay in reach while you browse chapters, the transcript, and questions.

Podcasts now come with a research layer

New podcasts include timestamped Producer Notes that add researched context at the moments where it matters. Jump back to the exact point, follow the cited links, or send a note straight into the podcast chat to explore it further.
A Related Resources section curates trustworthy websites, papers, archives, courses, and exhibits for continuing beyond the episode. The same enrichment pass also creates the listening check-in questions, so every extra is planned together while the audio records.

Home opens with your next session

Home now leads with a continue card that names your single next step — cards due for review with a time estimate, the deck you were mid-way through, or your latest material — so returning never starts from a blank page.
The welcome-back popup is retired. After a few days away, Home itself greets you with what's waiting instead of interrupting with a modal.

A calmer Home

Create with AI now leads with the tools people actually reach for, and moves the rest one click away under More — so the row is scannable instead of a wall of chips.
"Jump back in" is gone: it repeated the same items already listed under Content, and the continue card at the top of Home now covers picking up where you left off. Folders move below your work and appear once you have one.
Creation tiles and chips across Home and the upload flow share one flat, consistent button style in both light and dark mode.

Folders are just your folder now

A folder page is now its name, a search box, New, and your content — the wall of creation tiles is gone. Everything you could make from a folder is still one click away under New, and new content still saves into the folder you're in.
Search filters the current folder as you type, across both its items and its subfolders.

Consistent sections on content pages

Chapters, Summary, Transcript, Tasks, AI Creations, and Sources now share one clear card layout — a titled card with its own icon and actions — across video lectures, podcasts, AI Meeting Notes, PDFs, files, pages, and flashcard decks.

Uploads

AVIF images can now be uploaded anywhere images are accepted — they're converted automatically, so flashcards, chat, and page uploads all work with them.

Production QA follow-up

Free Study consistently stops after five questions, including when Next is pressed quickly, and its Questions count now shows the real daily allowance. Flashcard controls also stay single and readable before and after a card is flipped.
Pages now open directly as one editor without an extra AI Creations tab. Pasting from Google Docs, Word, and other rich editors preserves headings, bold, italics, underline, links, lists, quotes, and tables while still recognizing Markdown-style headings and quotes.
Two-host podcast requests now stay at exactly two voices, delivery directions no longer leak into transcripts or speech, and finished podcast and video audio is mastered to a consistent listening level.
Long account emails truncate cleanly in Settings, narrow flashcard tabs remain usable, and signed-out Library visits no longer report a false content-loading error.

Reliability

Library search inside every AI creator now uses the same live search as Cmd+K, so newly added sources appear, results stay current, and longer result lists can load beyond the first page.
Video Lectures now preserve narration at its natural recorded pace across Freestyle, Illustrated, Math, Kids, and Short modes, instead of speeding up the voice to force a longer script into a shorter target.
Importing a file by URL now works for websites with a misconfigured security certificate: Scholarly completes the site's certificate chain the same way browsers do, and explains clearly when a certificate genuinely can't be trusted.
Video lectures that hit their AI time limit near the end of generation are now reported accurately and retried when possible, instead of failing as an unexpected error.
PowerPoint previews now show a clean, scrollable deck with no editing, sharing, comments, or notes controls. Every slide fits the preview panel in both light and dark mode.

August 6th, 2026

Reliability

Study guides and other AI documents now retry automatically when their secure processing environment has a temporary startup problem, instead of ending the creation immediately.
Flashcard read-aloud now starts reliably in Safari instead of downloading the audio into a silent player.
Changing a page heading into a paragraph now updates the block immediately and remains correct after reloading; selected text and selected blocks can also be deleted normally.
Word and PowerPoint study guides now consistently name the original document, while native spreadsheet files no longer lead to a PDF-only summary page that cannot open them.

Cleaner profile menu

The profile menu no longer repeats team setup or deleted-item shortcuts. Deleted content remains available under Library → Deleted, and profile pictures stay circular when the sidebar narrows.

August 5th, 2026

Reliability

Video Lectures now repair or reject narration that stops mid-sentence before recording begins, so completed videos finish every explanation cleanly.
Short videos restore their original Scholarly art direction and word-for-word paper-strip captions across four distinct, completely still illustrations.
Daily Chat allowances now reset consistently in both Chat and Billing, so an expired limit cannot block a new day's messages while Billing shows unused credits.
Shared flashcard decks now clearly show that autoplay requires sign-in instead of offering a control that cannot play while signed out.

Chat replies that stay perfectly in place

Typed, retried, voice, and Help chat replies now update in place from the first word to the finished answer, so formatting no longer shifts when streaming ends.
Chat replies keep generating when you visit another page and are still live when you return, without requiring a refresh or restart.

August 4th, 2026

Faster creator steps

Customization is now prepared across creation modals when they open, so Next and Back switch steps immediately without a blank pause.

Stop one answer and send the next

Queued chat messages now have Stop & send. It interrupts an outdated response, safely settles any partial answer, and sends your next message without another click.

Deepseek Flash in every model picker

Deepseek Flash is now available for Chat, Research, Slides and documents, Video Lectures, Infographics and Mind Maps, Flashcards, and Podcasts.
It is an efficient, low-cost reasoning option. Because it is text-only, visual source workflows use the text extracted from your material.

Simpler model pickers

Only Auto (Premium) and Auto (Free) stay up front. Manual choices now live under Premium Models and Free Models, without lock or speed icons cluttering the list.

Reliability

Refining an existing flashcard deck works again. The structured response now uses a provider-compatible format instead of failing before the AI request could be sent.
Chat streaming, read-aloud, and flashcard autoplay now recover from an expired short-lived session token without interrupting your work.
Math formulas no longer create nested scroll areas while you move through Chat and other generated content.

More faithful creation and first-run copy

Podcasts now recognize natural instructions such as “two clearly labeled speakers” as a hard two-voice format, so a producer cannot slip into the finished audio.
Creation preflight now says Word document, PowerPoint, spreadsheet, or PDF to match the source you selected instead of calling every page-based source a PDF.
Welcome and pricing copy now speaks to learners, researchers, professionals, and teams instead of assuming every new user is walking to class.
Teams pricing consistently leads with the canonical $45/seat/month price and names $324/seat/year as the separate discounted annual option.

August 3rd, 2026

A voice picker you can actually hear

Choosing a voice now opens a full picker instead of a cramped dropdown: browse all 26 voices, search, and play a short demo of any voice before you commit.
The same picker is used everywhere a voice is chosen — chat settings, voice mode, read-aloud, podcast guest voices, and video narration — so it always looks and works the same.

Chat and AI Creations settings

The Scholarly AI settings tab was split in two. Chat now holds suggestions, auto-play audio, your voice, language, custom instructions, and memories; AI Creations holds custom designs, check-in questions, and autocomplete.
Video and podcast check-in questions can now be turned on or off from settings, not only from the player.

Long podcasts now actually run long

Requesting a 45 or 60-minute podcast now delivers an episode that genuinely fills that time. Long episodes are planned chapter by chapter and written in sections, instead of trailing off around the half-hour mark no matter what you asked for.
Short targets are respected too: an episode that came out far over your requested length is now tightened before the audio is recorded.

A calmer AI Creations tab and podcast page

The AI Creations tab on every source now matches the folder studio: quiet create buttons with color reserved for each creation type's icon, and simpler one-line empty states. The Sources tab got the same treatment.
The podcast page was tidied up: one title instead of two, a cleaner details line, shorter tab names, and calmer chapter visuals.

Reliability

Fixed: the chapter visuals' next and previous arrows could flip to the neighbouring chapter and immediately snap back. Chapter navigation now lands on the chapter you picked — on podcasts and video lectures.
AI Slides now treats explicit source absences as hard constraints across titles and decorative copy, so a deck cannot invent a date, weekday, event, or causal claim that the source says is not provided.
Chat now searches the normalized PowerPoint content on the first source question, including extracted speaker notes, instead of claiming the original deck is unavailable and waiting for you to rephrase.
Podcast transcripts now repeat the speaker name at every chapter opening, even when the same person also closed the previous chapter.
When an AI creation limit blocks the next step, Next is now visibly and accessibly disabled while the upgrade action remains available.

August 2nd, 2026

A calmer, simpler sidebar

The sidebar now focuses on navigation: New, Home, Chat, and a new Library link, with one Recent list that mixes your latest content and chats.
Recently Deleted, Changelog, Share Feedback, and Join Discord moved into your profile menu — same features, less clutter.

Simpler creation menus

Timeline, SOP, flowchart, lesson plan, and outline now live inside AI PDF Creator. Pick the document type after adding your sources instead of choosing between separate creators up front.
Spreadsheet and the former AI File Creator are now one Document & File Creator. AI Essay Writer remains a separate creator.

Expert styles, where you actually decide

The expert style cards in every AI creation panel now sit with the other creative choices near the top, instead of below the instruction box at the very bottom. Same styles, same effect — they were just easy to miss down there.
"Number of flashcards" moved out of the preset box into Settings, next to language and model, where the rest of the dials live.

Clearer free media previews

Free Video Lectures now run up to 2 minutes and free Podcasts up to 5 minutes. The customize step shows these limits up front, with a direct Upgrade link for longer creations.

Reliability

A PowerPoint or Word upload is now called by its own name and type everywhere, not just in chat. Its viewer, the planning chat behind Plan with chat, the Sources list on an AI creation, and generated podcasts and video lectures all refer to your .pptx or .docx instead of the PDF we convert it to for viewing.
Fixed: podcasts, video plans and the help bot could tell you a PowerPoint's speaker notes were unavailable. They are extracted from your .pptx and kept with the matching slide, and every surface now says so.
The "How was this…?" feedback card now only appears on the page for the thing it is asking about. It no longer follows you onto an unrelated video lecture or slide deck after a background creation finishes.
Timeline plan-limit errors now include a direct upgrade action, and opening the plan options from the pre-flight limit check clears any older error banner.
A temporary failure while syncing autocomplete usage no longer reduces your remaining allowance until you reload the page.
People viewing a publicly shared page can now export or preview it. Private pages remain blocked from public download links.
The Premium offer shown after leaving checkout is clearer and easier to use again. It keeps the benefit summary, student proof, and monthly or yearly choice together, while the subscribe and dismiss actions stay visible on phones without covering the content.
When a podcast can't be created because its sources couldn't be read — for example a saved web page instead of the real document — the error now names the actual problem with each source and what to do about it, instead of a generic "no usable content" message.
If your Google Drive access has expired or been revoked, chat tools and AI creations now tell you directly to reconnect Google Workspace in Settings instead of failing with a technical error.
Excel workbooks with native charts now open in Scholarly instead of showing a preview error. Unsupported chart artwork is skipped while every populated worksheet remains available, and the original workbook still downloads unchanged.
AI-created spreadsheets now reject cramped wrapped labels and noisy chart labels that repeat the series, category, and value, so dashboard sheets arrive easier to read.
Podcasts now enforce an explicitly requested two-speaker format before audio is synthesized, so a producer voice can no longer slip into a two-person conversation.
New students now see the tools and choose what to study before any pricing prompt. Upgrade suggestions remain available after they have received value or reach a relevant limit.
Upgrade actions consistently say Premium, voice limits clearly distinguish Free from Premium, and converted PowerPoint or Word viewers label the original file type instead of the internal PDF copy.
Free Study now shows its 10-card question allowance without interrupting the first question, then explains the remaining deck and upgrade path at the relevant study limit.
Workspace pages once again keep the Scholarly logo and breadcrumb separator visible on desktop, making the current page easier to place and Home one click away.

August 1st, 2026

Plan any AI creation with chat

Every AI creator now has a Plan with chat button beside its standard next step. Open the planning composer in place to discuss your sources and shape the result before creating flashcards, quizzes, slides, videos, podcasts, documents, study materials, and more.

Reliability

Fixed: duplicating a page containing a flashcard deck could silently drop cards. If a card's image failed to copy, the whole card went missing from the copy — question and answer text included. Every card now comes through, and a card whose image can't be copied keeps its text.
Fixed: duplicated flashcard decks came back reordered, with every card that had an image moved to the end. Copies now keep the original card order.
Duplicated flashcards now also keep their AI hint and difficulty label instead of losing them in the copy, and their source citation follows the copy — it opens the duplicated PDF or video in your new page rather than pointing back at the original.
When you let a flashcard deck or quiz finish in the background, Home now keeps the finished item on screen with a link straight into it, and your new deck shows up under Jump back in right away — no page refresh needed.
A creator can no longer sit on "Creating your…" forever if we lose track of a generation. It now tells you what happened and hands the page back, instead of leaving a spinner and a stale browser tab title until you reload.
Fixed: the flashcard feedback prompt no longer sits over Next after card five, so longer decks keep advancing normally.
Finished short Video Lectures no longer open a sharing dialog over their tabs, so Summary, Transcript, AI Creations, and Sources remain usable.
Fixed: after you hit the free upload limit, pressing Next in Add content did nothing at all. It now opens your plan options so the limit is actually actionable.
Chat now knows a PowerPoint or Word upload is still your PowerPoint or Word file, not a PDF — including where to find a presentation's speaker notes.
AI creations now recover automatically when a model provider returns a malformed response, retrying or switching to a backup model instead of failing with "An unexpected error occurred."
Connecting Google Drive no longer fails when you spend more than ten minutes on Google's account and permission screens.
Shared chat links with a malformed address now show a clear not-found page instead of a generic error.

July 31st, 2026

One AI PDF creator for any document

The separate SOP, flowchart, lesson plan, and outline creators are now a single AI PDF creator. Add your sources once, then pick the document type in the customize step.
Need something the presets don't cover? Pick "Anything" and describe the document in your own instructions — a briefing, a checklist, meeting minutes — and it gets built to that shape.
Four new document types: cheat sheet, report, case study, and rubric — each source-grounded and written to the same typeset PDF quality as the existing kinds.

New: AI File Creator

A new creator that turns your sources into a downloadable file. Describe what you want and it picks the format to match — an Excel workbook, a CSV table, a JSON export, a Markdown document, or a calendar file — or start from one of those tiles directly. The existing AI Spreadsheet creator is unchanged and is also available as a tile inside the new creator.

Preview Office files directly

Word documents, Excel workbooks, and PowerPoint decks now open in the shared file preview from chat, research, and saved files. New Word and PowerPoint uploads keep their original file for preview and download while Scholarly continues using the processed PDF for AI understanding.
Office files over 25 MB show a clear preview-limit message and a direct download action instead of attempting to load indefinitely.
Fixed: spreadsheets containing an Excel table — including every workbook the AI File Creator produces — reported that the file could not be previewed. They now open normally.
Office previews now match the rest of the app: PowerPoint decks follow light and dark mode, Word pages sit on the app's own surfaces, spreadsheet rows grow to fit wrapped text, and trackpad scrolling no longer runs away or triggers browser back-navigation. Opening a preview also no longer affects text sizing elsewhere in the app.

Clearer yearly pricing on upgrade

The upgrade modal now leads with the monthly equivalent for yearly plans (for example $12/mo), keeps the annual total visible immediately below it, labels the checkout button as yearly with the same monthly equivalent, and consistently calls the individual paid plan Premium.

More faithful, complete study creations

Free practice exams now use at most one question from each prepared flashcard, and every exam entry point shows that honest prepared-pool maximum instead of repeated variants of the same cards.
When you explicitly ask to preserve every source question, every source section must finish successfully before the deck is delivered. Everyday requests to cover a topic broadly keep the normal faster generation path.
Long video-lecture scenes now introduce their teaching points throughout the narration instead of becoming a static slide in the opening seconds.
Short Video Lectures now keep source markers and machine-style identifiers out of narration, preserving the central explanation as natural speech instead of reading document scaffolding aloud.
Research grounded in a linked PDF now draws labeled excerpts from across the document instead of relying only on its opening section.
Source-grounded chat tables now cite every factual cell directly, so each number, date, or quote can be checked in one click.
PowerPoint speaker notes are now extracted before PDF conversion and kept with their matching slide for chat and AI creations.
Infographics now honor explicit landscape and portrait requests, recognize historical year ranges as timelines, and stop genuinely oversized exhaustive requests before generation with guidance to narrow or split the content.
Podcast expansion now catches near-duplicate chapter content while preserving distinct chapters that happen to share a generic title.

Reliability fixes

Fixed uploads that could fail with a raw "Retry limit exceeded" message. Brief file storage hiccups are now retried automatically instead of ending the upload, and if storage really is busy you get a clear message and the upload retries itself.
Fixed chat turns that could spend every research step and then save a generic error as the answer. Chat now says plainly when a web search comes back empty, and a turn that cannot reach an answer no longer saves a placeholder reply or spends a chat credit.
Chat reasoning and tool actions now stay in their true order while an answer is streaming, including longer Auto conversations that use several rounds of tools.
Charts created in chat are now attached before the assistant says they are visible. If the model only inspects the image, chat automatically finishes the delivery step instead of leaving the chart hidden.
Selecting text in a chat now keeps the Ask, Copy, and Speak menu beside the selected words, including after scrolling through a long conversation.
Fixed a page editor crash that could begin after using undo or redo, where further typing appeared on screen but was never saved.
Fixed switching from monthly to yearly billing so a billing update arriving at the same moment can no longer roll your renewal date back.
Fixed rare connection errors where a page load or request could fail once with a server error and then work on retry.
Flashcard creation now honors the selected difficulty all the way through generation instead of silently falling back to the default.
Creation flows now wait for image uploads to finish, and AI Creations treats temporary source-loading failures as retryable instead of incorrectly marking the source as unsupported.
The flashcard creation footer now wraps cleanly when a plan-limit message appears, keeping Build a blank deck readable and usable.
Abandoned-checkout recovery now describes what happened accurately and keeps yearly Premium as the primary option instead of switching a yearly shopper to monthly.
Laureate members now see the correct weekly flagship-credit reset guidance and can receive subscriber feedback prompts, while Free users continue to see the right upgrade gates for premium models.
Research preparation and podcasts now handle missing optional content safely, and the welcome-back dialog has a properly announced title for screen readers.

A more reliable page editor

Undoing or redoing text on a page is now saved. Previously the change was applied on screen but never written back, so reloading the page brought the undone text back.
Read-only and shared pages now stay read-only. Previously they could become editable again after interacting with them, and text typed while blocks were selected could be silently discarded.
Signup and other pages no longer load the rich-text editor they never use, cutting a large amount of JavaScript from the first page load.

Mobile

Interactive podcast questions now scroll into view when they appear, and stay open while you tap around the page.
Fixed the flashcard study card on smaller phones — the card controls no longer fall off the bottom of the screen, and long questions are no longer hidden behind the card buttons.
Opening a creation's customization step now shows a loading state instead of a blank sheet, and Google Drive picks scroll properly when you select several files.
"Other Models" now expands inside the model picker on phones instead of opening a panel on top of it, so every model is reachable.
Plan details that used to appear only on hover — like Laureate's weekly credit allowance — are now readable on touch.
Tapping an image to enlarge it now fills the screen instead of opening at half width.
Bigger, easier tap targets across study, exams, saved instructions, sharing and the plan billing toggle.
Blog posts, the file page tabs, search filters and marketing stats now lay out properly on a phone.

July 30th, 2026

Smarter Auto across Scholarly

Auto now uses GPT-5.6 Luna for chat on every plan, with high reasoning effort on Premium and higher for stronger answers. Free chat stays on Luna with its efficient reasoning setting, while AI creators keep their existing automatic models.

Everything made from a source, in one place

Pages, PDFs, videos, AI Meeting Notes, podcasts, research reports, and saved files now have an AI Creations tab with the creation tools that work for that source.
New flashcards, quizzes, podcasts, video lectures, slides, study guides, worksheets, visual documents, essays, and more stay durably connected to the source they came from, including the PDF pages used.
Search and filter a source's creations by study tools, media, or documents, then open any result directly.
Creation shortcuts now live in AI Creations instead of the assistant's empty conversation, keeping chat focused on questions and explanations.
PDFs, videos, and AI Meeting Notes now keep flashcard creation and linked decks inside AI Creations, replacing their redundant standalone Flashcards tabs.
New flashcard decks, generated documents and files, video lectures, and podcasts have a Sources tab that shows the original material used to create them, including PDF page ranges, with a direct path back to each source.

July 29th, 2026

A faster, smarter voice assistant

Scholarly's voice assistant now uses xAI's Grok Voice Think Fast 2. Conversations respond faster, follow complex study requests more reliably, and handle interruptions and tool use more naturally.

Faster navigation between your work and Home

Returning to Home from PDFs, videos, flashcards, podcasts, recordings, research, and shared chats now feels immediate while keeping your sidebar and workspace ready.

July 28th, 2026

The right Auto model when chat creates for you

When AI Chat starts a video lecture, podcast, slides, flashcards, a visual document, or research, it now uses Auto (Free) on Free and Auto (Premium) on paid plans — the same model choice as the creation dialog.

A cleaner model picker

Named AI models now use compact, single-line rows in every picker. Auto (Premium) and Auto (Free) keep their explanations so their behavior stays clear.

Better recovery from brief connection problems

An account left open in an older browser tab no longer crashes while loading after Scholarly's AI model list changes.
PDF processing now retries an interrupted page-image upload before restarting through the slower fallback processor.
Video and audio downloads now retry interrupted proxy transfers instead of failing after a brief connection drop.

Choose the AI that writes your podcast

Podcast creation now includes an AI model picker. Free uses Gemini 2.5 Flash; paid plans default to Gemini 3 Flash Preview and can choose either. The selection writes and reviews the transcript only — voices and audio generation stay unchanged.

Podcast names and voices stay in sync

Every podcast speaker now uses the exact name of the Grok voice you hear — for example, Cosmo, Ursa, or Sirius. This applies to the automatic host, guest, and producer as well as a guest voice you choose.

Podcast navigation stays within reach

Interactive questions now have their own counted tab alongside Chapters and Transcript, and longer podcast pages scroll all the way to every panel.

Follow podcasts with chapter slides

Every new podcast now includes a visual companion by default for everyone. Scholarly generates one clean Editorial slide per chapter alongside the audio, then follows the current chapter automatically as you listen. You can turn it off for an audio-only episode.
Previous and Next now switch podcast chapter slides immediately in Safari, even while the audio is paused.

Clearer, interruption-free study tools

Feedback cards no longer cover quiz or exam answers. They stay out of focused study routes and can always be dismissed.
Flashcard quantity options now describe AI-generated counts as targets rather than guarantees, so short sources no longer appear to promise hundreds of useful cards.
AI Slides now reviews pages at a readable size and checks card spacing and complete equations before finishing, reducing overlapping text and missing formulas.
Text fields no longer grab keyboard focus automatically when pages, searches, or study steps open.

A clearer welcome and faster path to studying

The welcome tour now separates its introduction, plan comparison, study tools, and start choices into four focused screens.
Completed flashcard tasks now offer Start studying directly from the completion message and Home task tray.

July 27th, 2026

Fewer generations lost to a single hiccup

Google Drive files that can't be downloaded are now caught when you pick them, instead of failing partway through a generation.
PDFs now open reliably in the in-app reader instead of failing while the browser loads the PDF worker.

Clearer, more honest error messages

When a document has no lesson content, we no longer suggest saving it as a PDF again — we point you to the pages or link that do have the material.
A Drive file whose owner turned off downloading now explains that and how to fix it, instead of asking you to reconnect an account that was working.

A cleaner, context-aware upgrade screen

Opening plan options from an Upgrade Plan button no longer shows a limit warning just because the account has used free credits. Limit warnings now stay attached to the action that actually reached the limit.
The upgrade dialog no longer shows a bright outline around the entire window when keyboard focus moves into it. Buttons and fields keep their normal visible focus indicators.

Safer defaults and more faithful creations

Every AI creation now starts in your saved language, using your browser locale with an English fallback the first time. Changing Language in any creator updates that account preference everywhere.
AI Slides now preserve source values and units exactly. When a table is too dense, it leaves out a column instead of inventing summaries, ranges, or units.
The welcome tour can now be skipped from its first screen and dismissed with the Escape key.

Honest, broader practice-exam coverage

Exam mode now shows how many of your deck's cards actually have practice questions — "N of M cards prepared" — instead of promising questions that were never generated.
On paid plans, creating an exam now fills only the missing practice variants needed for that exam's size, so paid exams are no longer restricted to a stale 10-card pool.
Free decks show the 10-card preparation limit right where you pick an exam, with the upgrade path next to it.

Video lectures grounded in your source again

Prepared video lectures can once again inspect up to two PDF pages the plan specifically flagged for figures, tables, or equations, while general source rereading stays off.
The planner can now supply concise on-screen card copy instead of repeating narration; scenes without it retain the existing narration-based fallback.

Bug fixes

The cancel-flow pause offer now matches the 3-month pause you can set yourself in billing settings — it was previously capped at 2.
If you cancelled because you did not want auto-renewal, the follow-up email no longer offers a discounted subscription; it offers a plain restart instead.
Win-back discount codes could expire before paid access ended. Their expiry is now anchored to remain valid for 21 days after access ends.

July 26th, 2026

One consistent Premium plan name

Same plan, same price, same features — Scholarly's paid plan is now called Premium everywhere in the product. Nothing changes about your subscription or billing.

Flagship AI credits for Scholarly Laureate

Laureate includes 2,000 weekly credits for flagship-model work. Standard and advanced models stay unlimited on both Premium and Laureate, so Premium access is unchanged.
Laureate members can see their weekly flagship-credit balance, usage details, and reset time in Settings → Usage.
Laureate members can top up flagship credits in a heavy week without changing plans.

Your work stays where you left it

A PDF or video now shows the flashcard deck made from it, instead of an empty tab offering to create one you already have.
"Jump back in" on the home page now includes your flashcard decks, not just the file you made them from.
The free-limits banner no longer appears while your first creation is still generating — it waits until your work is ready.
The chat limit now tells you when it resets, so a daily limit no longer reads as a permanent one.
Finishing a creation no longer flashes the create form back up with a "Retry" button while it opens your new content.

More faithful study materials

PDF and video summaries now follow the language of your source by default instead of forcing English.
LaTeX formulas in flashcards and study questions no longer lose commands such as fractions, Greek letters, or text labels during generation.
When an AI creation asks to read more PDF pages than one pass allows, it is now told exactly which pages were skipped so it can continue reading them instead of silently missing part of the source.
Flashcards now stop when only a link or reference to missing material arrives, rather than inventing a confident-looking deck from general knowledge.
AI podcasts now keep a direct, appropriate tone for sensitive human topics instead of forcing cosmic metaphors into every subject.
Infographics no longer risk printing internal layout labels such as “TITLE” or “SECTION” onto the finished poster.

Scholarly for Teams, easier to find and start

Teams is now a full plan on the pricing page, alongside Free and Premium, with per-seat pricing that follows the monthly/yearly toggle.
Team setup is now reachable from the profile menu, billing settings, and plan options — and those entry points open team setup directly instead of sending you to a marketing page.
If you sign up or use Scholarly with a work or school email, signup and your home page now mention Teams — one plan and one bill for everyone — instead of the generic pitch.
"Talk to sales" on the Teams page is now a form on the page itself, so enquiries reach us without needing a mail client.
The Teams page now leads with turning your organization's existing handbooks, recordings, and decks into onboarding and training content.

Fewer generations lost to avoidable failures

You can now make a video lecture from a short topic — paste “Krebs cycle” and it generates, instead of being turned away for being too short.
If an AI provider declines to read a document on content-safety grounds, we now try a different provider automatically. Legitimate medical, anatomy, and clinical material no longer dead-ends.
A PDF with nothing readable in it now says so straight away, instead of showing “still processing” for ten minutes and then failing.
Picking a Google Drive file that is over your plan's size limit is now flagged the moment you choose it, with the upgrade path shown — rather than failing after you press Create.
A video lecture whose picture ran out before the narration finished is now caught and re-stitched while it is still being made, instead of failing at the very end after several minutes of work.
If an AI provider declines to read your source while preparing a podcast, we now try a different provider before giving up — the same recovery study guides already had.

Bug fixes

Switching an existing monthly subscription to yearly billing failed every time with a generic "please try again" message. It now goes through.
Some new accounts were dropped onto the home page instead of onboarding right after signing up, and could end up marked as onboarded without ever seeing it.
If our servers hiccuped in the moment right after you signed in, you could be sent straight back to the login form even though your sign-in had worked.
An empty response from the server could sign you out mid-session even though your session was still valid.
A failed page navigation could reload the app and silently discard an edit that was still being saved. Reloads are now limited to the stale-app-version case they were meant for.
Opening scholarly.so/content directly showed a "Page not found" error instead of your library.
Reloading a podcast part-way through no longer re-asks the questions you had already answered while listening.
Videos whose file was structurally damaged could still be delivered and then refuse to play in the browser. They are now caught during generation and rebuilt.
Video generation could stall for around 20 minutes before recovering, when the generator waited on a step that had already finished.
Explore search quietly fell back to non-semantic results when the embedding provider was briefly busy. It now retries first.
Requests in flight during a deploy could be cut off instead of being allowed to finish.
Opening a dialog now moves keyboard focus into it, and closing one returns focus to whatever opened it. Focus used to stay on the page behind, which left keyboard and screen-reader users outside the dialog that had just taken over the screen.
Pressing Enter in the email field on signup now moves to the password field. It previously did nothing at all.
Video lecture title and closing cards no longer print an internal authoring note as on-screen text, and on-screen lines are no longer cut off mid-sentence when the card still had room for them.
The “NEW” badge on the home page was too light to read comfortably in light mode.
Compact library rows painted the same colour as the page behind them; they now read as distinct cards.
Help and marketing pages listed slide themes that are no longer offered.
The screen where you choose what to make announced “Your content is ready!” before your file had been uploaded. It now names the step instead of claiming your source is already saved.
The monthly and yearly options in the upgrade dialog can now be moved between with the arrow keys, the way a set of radio buttons is expected to work.
Podcast instructions that name which hosts should appear are now followed, instead of the standard three-host cast being used regardless.
Video generation could throw away a nearly-finished lecture and start over after a step briefly misbehaved, even though it had already corrected itself — adding several minutes for no benefit.
Audio and video that would not play blamed an expired link and told you to refresh. Nothing expires, and refreshing never helped; the message now says what actually happened.
Help lists and navigation no longer perform an unnecessary wait that could contribute to stale or unexpectedly reloaded views.

July 25th, 2026

Smarter defaults and clearer dialogs

AI Chat and creation dialogs now offer Auto (Premium) and Auto (Free), so you can let Scholarly use the recommended model for the quality tier you choose.
Voice-picker search now uses one clean, consistent surface in both light and dark mode.
Plan options now show a yellow limit explanation only when the action that opened them actually reached that limit.
Locked Full HD and custom-length video options now explain exactly what Premium unlocks before showing plan choices.
Welcome tours now introduce what Scholarly can do before showing the option to skip the rest.

Video lectures show your numbers, not placeholders

Chart, equation and statistic scenes in an AI Video Lecture now use the real figures from your source. Previously these could fall back to placeholder scaffolding — a generic two-bar chart or the scene's own title typeset as an equation — even while the narration read your actual values.
When a scene genuinely has no figure worth showing, it now renders as a clean text callout instead of an empty or invented visual.

Podcasts

New podcasts now come with interactive questions. While you listen, a quick check-for-understanding question appears right after the idea it tests finishes — and never pauses the audio.
Answer to get an explanation grounded in the episode, revisit any question from the episode's question list, and track your score across attempts. You can switch questions off from the player at any time.

Exams and quiz limits

The Exam tab now prepares its own study questions instead of waiting on the Questions tab, so exams open on a deck you have not quizzed yet. If questions cannot be prepared, you get a clear message and a Try again button rather than an endless spinner.
Returning to a deck after using your daily practice questions now shows the full limit screen — questions remaining, when it resets, and a way back to your flashcards — instead of a bare notice.

Interface fixes

The upgrade dialog now scrolls your selected plan into view on short screens, so the highlighted term always matches the price on the button.
On phones, the chat box on Home no longer overlaps its own buttons, so tapping anywhere in the field starts typing.
The “How was this?” card after a generation no longer sits on top of the chat send button.
Copying a share link from a private item now says up front that it will make the item viewable, instead of only telling you afterwards.
Home creation shortcuts are back to the roomier three-card layout, with full AI tool names and the original quick-access order.
If Google's permission screen closes without the Google Drive box ticked, Scholarly now tells you which box to tick and offers Try again on the spot — instead of a message that disappeared and left no way to retry.

July 24th, 2026

Teams for training, onboarding, and sales

New Teams marketing pages for employee training, employee onboarding, sales enablement, and businesses — plus help docs for getting started, billing, sharing with Your team, and switching from an individual plan.
Expanded Teams help covers seats ($45/seat/month or $324/seat/year), weekly credits, and the shared library workflow for L&D and research groups.
New ChatGPT Business (formerly Team) comparison and guides for buyers evaluating AI employee training tools and sales enablement from company docs.

Clearer study-tool guides and comparisons

Updated PDF Summarizer, flashcard, homework-helper, Quizlet, and Chegg pages with clearer comparisons, examples, and more accessible imagery.

Chat attachments stay with the right message

Images and other attachments sent with your first chat message now stay on that message instead of jumping onto the next one.
Attaching multiple images in chat now shows a compact equal-height grid (up to four) instead of stacking large previews in a tall list.
Fresh web searches in AI Chat now return current sources again instead of failing when the search provider rejects an outdated crawl option.
Chat replies no longer fail permanently when one AI model rejects a long conversation — the message now moves to another model instead of leaving the conversation stuck.
The chat model picker now highlights four recommended choices, making it faster to choose a capable model without scanning a long shortlist.

Video lectures and research recover instead of failing

Video lectures and research runs interrupted mid-generation by a server restart now retry automatically instead of failing and refunding.
A video whose final render fails a quality check now regenerates once automatically, and a video ending moments before its narration is repaired in place instead of rejected.
Long video lectures no longer stop early against an internal step limit that was smaller than the work they were approved to do.
PDF study guides no longer fail, or get cut short partway through, on longer documents.
Flashcard sets from dense sources now switch to a working model in minutes instead of retrying until the time limit, so decks arrive far sooner.
Video lectures now catch a corrupted or silent render while the video can still be rebuilt, instead of failing at the very end.
A video lecture that got stuck retrying the same failed step now gets a clear correction and, if it still cannot move on, is retried automatically instead of quietly using up the whole generation.
Videos, podcasts, flashcards, and other AI-created study materials no longer fail just because the model produced slightly more text than requested.

You stay signed in through brief outages

A temporary connection or server error while loading your account no longer signs you out and sends you back to the login screen.

More reliable creation from your sources

Recording and transcription no longer use an AI creation, leaving your included creation available for the flashcards or quiz you make from the recording.
When one source fails while creating Flashcards or a Quiz, successfully uploaded sources stay ready and the failed source can be removed without starting over.
Creation dialogs now keep clear limit guidance and an Upgrade action visible when a server-side plan limit is reached.
Post-purchase tools and cancellation guidance now keep the record of features you have tried after your account refreshes.
Signing up from a tool page now carries that tool into onboarding and opens the matching creation flow, so you can continue without starting over.
The welcome tour now introduces upgrading earlier, restoring the step order that helped more new users reach the plan explanation.
Slide creation no longer gets stuck repairing harmless text overlap, and Very High flashcard sets once again target at least 200 useful cards when the source supports it.
If Essay Writer generation is interrupted after claiming a refund, the system now reconciles it so the AI creation credit is returned.
Google Drive searches for large or shared study materials now read every result page and use the file details those filters need.

Clearer billing choices

After a successful payment or plan change, your active plan now appears immediately instead of briefly showing the old plan or asking you to retry checkout.
The plan chooser can now start with monthly billing selected, making the lower-commitment option easier to continue with while yearly savings stay visible.
Monthly members see the yearly-switch reminder near renewal, at most once per billing cycle.
If you leave a yearly checkout, the recovery screen now leads with monthly billing instead of immediately repeating the yearly offer.

Smoother dialogs

Dialogs no longer pre-select Close, Skip, or another button as soon as they open, removing the unexpected blue outline around those controls.
Creation settings now sit in their own labelled section, separate from the design choice, with each option on its own row so the setup is easier to scan.

A much better phone experience

Fixed screens where the main button could end up off-screen on a phone: the post-upload "what to create" chooser, the post-purchase welcome steps, the checkout offer, and the practice exam setup now keep their primary action reachable.
Long flashcard answers, quiz questions, and the end-of-session summary no longer get cut off with no way to scroll to them, and long multiple-choice options are shown in full instead of being truncated.
Plan and competitor comparison tables now stack into readable cards on phones instead of squeezing three columns into a sideways-scrolling strip — and the explanations that were previously hover-only are shown inline.
Video, recording, and PDF pages now show the item's name on phones, including when you open a shared link.
Hitting your AI creation limit now shows the upgrade options instead of the create buttons silently doing nothing, and the "finish yearly checkout" reminder no longer covers the chat box or recording controls.

July 23rd, 2026

Reliability fixes

Long, tool-heavy AI Chat conversations now keep your latest message intact instead of occasionally failing before the answer starts.
Large PDF summaries now stay within safe output bounds instead of occasionally failing near the end.
Healthy long video lectures are no longer rejected when export creates a harmless sub-second difference between audio and video timestamps.
Team workspaces avoid repeated membership lookups during startup, reducing intermittent account-loading failures under heavy load.

A clearer refund policy

The refund policy now explains that most requests made within 30 days are approved, while unusually extensive use, fraud, or abuse may require a case-by-case review.

July 22nd, 2026

More room to shape your AI

Custom instructions now allow up to 5,000 characters across Chat, Skills, Custom Designs, and every supported create flow.
Plus and Premium members can now choose Claude Sonnet 5 for AI Video Lectures.

Short-form video, made more reliable

Kids & Story is now the landscape twin of Short: a 30-second, full-width illustrated story with crisp cuts, paper-strip captions, and the same logo controls.
Autonomous video modes now verify that narration and visuals describe the same chapters before an export can finish.
Large and scanned sources are processed in small, resumable batches, so a worker restart does not throw away completed video preprocessing.

Creating and upgrading

AI Study Guide is easier to find on Home and after uploads, while Worksheet now lives under More in a balanced action grid.
Generated and edited page titles no longer revert to Untitled when you leave the editor.
Plan dialogs now show the true reason they opened and support complete Tab and Shift+Tab keyboard navigation.
Large textbooks and PDFs now finish processing much faster, so you can start studying sooner.
Large PDFs now open incrementally and stay responsive while you scroll or zoom, without downloading and rendering the entire document up front.

July 21st, 2026

New Gemini models

Gemini 3.6 Flash and Gemini 3.5 Flash Lite are now available across Chat, Research, Slides, Video Lectures, Infographics, Mind Maps, and Flashcards.
If a retired model was selected, Scholarly now chooses the current default for that feature instead of silently pretending it is a different named model.

Clearer plans and recovery

Yearly and monthly checkout options once again show the exact charge up front — including $144 today or $30/month — with a direct monthly choice.
Returning from checkout now shows the file, action, or limit that led you there and lets you pick up where you left off.
Upload and AI limits stay visible on Home, Chat, and page upload surfaces with accurate reset or lifetime wording and a persistent upgrade action.

Your source survives the whole create flow

Files are saved before customization or checkout can navigate away, so returning to the library no longer loses an upload that was ready to create from.
Practice Exams in Auto language now follow the main language of the source instead of being overridden by a small translated glossary.

July 20th, 2026

Scholarly for Teams now starts at one seat

You can create a full Teams workspace for one person and add teammates later; the 29-seat self-serve maximum is unchanged.

A refreshed Help Center

A new Memory guide explains how the AI Assistant saves useful facts, how to add memories yourself, and how to mark them outdated or restore them.
Every Help Center article was checked against the current product, with outdated model, plan, workflow, and feature details corrected.

Fixes and reliability

Chat keeps generating when a phone locks or a connection drops, then reconnects quietly; Stop is now an explicit action instead of an accidental disconnect.
Emoji in Word, PowerPoint, and other Office files now render visibly in converted PDFs instead of disappearing.
Clearing the email field on login no longer silently clears or desynchronizes the password field.
Podcasts, recordings, and Deep Research now show clear Processing or Failed states across Home, libraries, and search.

July 19th, 2026

Mind Maps with real, readable text

Mind Maps now render as vector PDFs with exact labels and a native text layer, so their text stays crisp, searchable, selectable, and accessible.

More resilient AI generation

Podcasts now save completed chapter audio and retry through temporary voice-provider outages instead of discarding the whole episode.
Video Lecture narration is synthesized as one continuous performance whenever possible, removing the repeated speed and tone reset at every chapter.
Flashcards can now read browser-printed PDFs from their page images when the selectable text contains only headers, dates, and URLs.

Fixes

Email signup or login now offers a real Continue with Google button when the address already belongs to a Google-linked Scholarly account.
Branded Short videos now include a crisp Scholarly mark, while paid no-logo exports stay watermark-free.

July 18th, 2026

Smoother AI Chat

New answer text fades in smoothly, citations appear as source badges while the answer is still streaming, and the finished response no longer snaps into a different layout.

Flashcard exports you can actually reach

Export and Daily Goal now open with a click or tap, making PDF, Print, and Anki export available on both desktop and touch screens.

Podcast reliability

Podcasts recover from temporary transcript and voice-generation failures with bounded retries instead of failing the whole episode on the first provider hiccup.
Older podcast setups with a missing guest name now safely use “Guest” instead of crashing during transcript creation.

A clearer yearly option

Monthly subscribers who cancel because of price can switch to yearly billing inside the cancellation flow, with the full charge shown before confirmation.

July 17th, 2026

Illustrated video lectures

Video Lectures have a new Illustrated design: a full-length, hand-drawn explainer where one quirky character sketches every idea on a clean white board.
Each scene turns one idea into a simple visual metaphor — a coin ramp, a growing jar, a balance scale — with its handwritten labels drawn right into the art.
Both Illustrated and Short now hold each scene as a clean still with crisp cuts, instead of a slow zoom.

Short videos

Video Lectures have a new Short design: a ~30-second vertical (9:16) video that distills your source into one tight, illustrated story.
The narration appears on screen word-for-word as paper-strip subtitles, synced to the voice — Shorts work with the sound off.
Every Short is art-directed in one of four Scholarly styles — cobalt dither, oil painting, papercraft diorama, or sketchbook journal.
The video player now shapes itself to vertical videos instead of adding black bars.

July 16th, 2026

Fixes & improvements

Video lectures now automatically retry on a different AI model when a provider has a temporary problem, instead of failing your generation.
Video lectures that run past their generation time limit now automatically retry once on a different AI model instead of failing and refunding your credit.
Flashcard study questions no longer disappear when the AI skips a card — the deck keeps every question it generated and fills in the rest the next time you open study mode.
PDF summary errors now show a clear, friendly message instead of technical error text.

July 14th, 2026

New — choose your voice across Scholarly

Scholarly now includes 26 official multilingual Grok voices: 21 new voices plus Ara, Eve, Leo, Rex, and Sal, available for AI Video Lectures, AI Podcasts, read-aloud, and live Voice Mode.
Choose the exact voice for live Voice Mode and read-aloud in Scholarly AI settings, choose a podcast guest voice, or choose the narrator for a video. Each option explains its tone.
Luna — a gentle, patient voice — is the new default for live Voice Mode and read-aloud. For podcasts and videos, leave voice selection on Auto and Scholarly will choose voices that fit your material.
Voice Mode now handles reconnects and interruptions more reliably, without overlapping old audio or losing a turn that still needs to be saved.

Bug Fixes

Fixed a crash that could close the page while an AI answer was streaming. Answers that mixed a plain “*” with a math formula — like “5 * 3” next to \times — could take down chat, PDF, and flashcard pages mid-response. They now render correctly.

July 12th, 2026

Bug Fixes

Fixed a rare error that could stop the Home page from loading for some workspace members.
Keyboard shortcuts (including ⌘/Ctrl + K search) no longer occasionally error on Safari when a password manager or browser autofill fills in a field.

July 11th, 2026

Bug Fixes

Copying a share link now works reliably on Safari and iPhone/iPad — tapping “Copy share link” no longer fails with “Couldn't copy the link.”
Flashcard generation no longer dead-ends with “try different files” when the AI returns a response our checker can't read — we now automatically retry on a second model instead of failing the whole deck.

July 9th, 2026

Improvements

Sidebar layout refreshed: Home, Chat, and Recently Deleted sit at the top; a primary New button and search sit below; Content / Chats tabs filter Recent, Folders, and chats. Recent and Pinned now use the same type-colored rows as Home, and dark-mode sidebar text is easier to read.

July 8th, 2026

Bug Fixes

AI Video Lectures that stall while planning now show a clearer message and retry on a stronger model instead of failing as a vague “technical issue.”
Flashcard creation no longer dead-ends after a brief AI hiccup with “try different files” — we now retry automatically when the model returns an incomplete or unreadable response.
Fixed sign-up occasionally crashing when finishing the last registration step after Google sign-in.

Improvements

Grok 4.5 from xAI is now available (replacing Grok 4.3) across chat and create tools. On paid plans it is the default model for AI Video Lectures, AI Slides, Infographics, Flashcards, and Research (free stays on DeepSeek). Generation runs at medium reasoning depth. Previous Grok 4.3 selections continue to work via automatic upgrade.
Refined the yearly Premium savings banner on Home so the discount and switch-to-yearly offer are easier to scan.
Tightened spacing on the Create-with-AI option grid so longer titles like “AI Video Lecture” fit without being cut off.
Removed the rotating study tips from creation loading screens — just the status and progress now.
Fixed design/style option cards in create modals flashing a light white hover in dark mode.
Simplified the create-modal “close while generating” button to a clear Close action (no more “continue studying” wording).
The “More credits” model badge (e.g. on Claude Sonnet 5) now only appears for team/enterprise accounts that use weekly credits — not on individual plans.
Grok 4.5 in AI Chat always uses thinking (no Instant / off mode) — matching what the model supports, so chats no longer fail when thinking was turned off.
Fixed a chat bug where your message could disappear after a failed reply even though it was saved — the original text stays visible for retry.

July 7th, 2026

Bug Fixes

AI video lectures now work from photos and scanned documents. Previously, creating a video from an image or an image-only PDF could fail with an unhelpful message telling you to pick a different model — now we automatically read your images and build the video.
Fixed AI Flowcharts where the steps could render as solid black boxes that hid their labels — every step now shows as a clean, readable box with its text clearly visible.

Improvements

Cleaned up the sidebar. A prominent New button and search sit at the top, with Content and Chats sections for browsing your library, folders, and recent chats.

July 6th, 2026

Bug Fixes

Flashcards no longer fail on a brief AI hiccup — if the model returns an empty response, we now retry automatically (and fall back to a backup model) instead of failing your deck and using up a creation.
Fixed a rare issue where creating flashcards could fail with an error or get stuck partway — even when your cards had already been generated. Flashcard creation now reliably saves your finished deck.
Clearer message when an AI video lecture source has too little text — instead of wrongly suggesting your file is scanned or telling you to “run OCR,” we now simply say the source is too short and to add more detail.

Improvements

Tidied mobile sign-up/login forms and fixed a rare Google sign-up crash.

July 5th, 2026

A cleaner AI Meeting Notes page

A slimmer, more elegant player — the bulky playback panel is now a single, compact bar, so your transcript, summary, and tasks get more room and the whole page feels calmer.
Easier to read — refreshed the layout with more breathing room around your transcript, summary, and action items.

Improvements

Chat now quietly rides out brief hiccups from the AI provider — if a response can’t start because the model is momentarily overloaded, we retry automatically instead of showing an error.
Signup starts you in the free workspace — the final “How will you use Scholarly?” step now always pre-selects the free “Just me” option, so tapping Continue takes individuals straight into their personal study space. The paid Teams option stays one tap away, just never pre-picked.
Share entire folders — folders can now be shared just like any other item. Recipients get a read-only view of everything inside, and folders shared with “Your team” show up in your team’s shared library automatically.

Bug Fixes

Clearer messages when flashcards can’t be created — if you paste a short topic or upload a photo with no lesson content, we now explain what to do for that kind of input instead of showing PDF-only advice about “pages” and “Print to PDF.”

July 4th, 2026

Introducing Scholarly for Teams

One workspace for your whole group — put a class, department, research lab, school, or company on a single plan. Every paid feature turns on automatically for every member, and everyone works from your shared material.
The most capable AI models — teams unlock our top tier of models across every AI feature, with admin controls to choose which model tiers the team can use.
Weekly AI credits per member — each person gets their own weekly credits, never a shared pool, so one teammate’s heavy week never eats into anyone else’s.
Admin controls in one place — invite by email or link, Member and Admin roles, shared source libraries, and one central bill. See Scholarly for Teams to start a team.

AI Image Playground upgrades

High-quality mode — a new Quality selector lets paid plans generate sharper 2K images on models that support it, and shows exactly which models will use it.
See which model is generating — while images render (and if one fails), each tile now shows the model producing it, so comparing models side by side is much easier.
Removed the Style menu — describe the look you want directly in your prompt instead.
Deleting an image now asks for confirmation first.
Fixed the remaining-generations counter showing “Infinity free left” on unlimited plans.

AI now reads your PDF pages the way you see them

Generations grounded in the actual pages — when building slides, study guides, worksheets, videos, and other content from a PDF, the AI now reads the relevant pages as full page images by default, so diagrams, equations, tables, and handwriting are read exactly as they appear instead of relying on extracted text that can drop or garble them.
Infographics and mind maps see your pages too — they now look at your PDF’s actual pages when planning, so visual material like charts and diagrams makes it into the result.

A cleaner, more consistent look across the app

Light mode got a big polish pass — hundreds of panels, cards, and labels across chat, recordings, podcasts, flashcards, settings, and more now have proper contrast, so nothing looks washed out or blends into the page.
Dark mode fixes everywhere — missing dark styles on hover states, cards, and text were filled in across the app, and equations in the page editor no longer render as white strips in dark mode.

Improvements

Print your PDFs and slides — the three-dots menu on PDF and slide viewers now has a Print option that opens your browser’s print dialog with the document ready to go.
Pasting a link no longer uses up your free file upload — links you add as sources are treated as sources, not file uploads, so your lifetime upload credit stays available for real files.
Added a Skip option to the welcome tour so you can jump straight into the app.

Bug Fixes

Quiz and exam questions now test understanding, not diagram trivia — questions built from your material no longer ask you to recall an exact value or timing read off a source’s illustrative graph (like “at what time does the curve peak?”). They now focus on the mechanism and relationships the figure is showing.
Fixed upgrading being blocked for some users — clicking an upgrade button could show “An error occurred while creating the checkout session” instead of opening the checkout page. Checkout now opens reliably, and we’ve added extra safeguards so this class of problem can’t block a purchase again.
Fixed Home and All Content sometimes reloading more of your library than needed when switching views or filters, so large libraries stay faster and smoother.
Fixed the welcome guide overstating how many free AI creations some accounts include — it now always matches your actual allowance.
Fixed pacing markers like “[slow]” occasionally appearing in AI video lecture transcripts.
Clearer help when a PDF is really just a printed document-viewer page — if you upload a “Print to PDF” of an online document viewer (SharePoint, OneDrive, or Google Docs) that was saved before the document finished loading, the file only contains the page’s web address and a page number, not the actual document. We now spot this instantly and point you to download the original file — across flashcards, quizzes, podcasts, slides, and AI videos — instead of trying for a while and then showing a confusing error.
The Print button on the Formula Sheet Generator now works everywhere — it reliably prints just your formula sheet (not the whole page), and if your browser blocks the print window it downloads the sheet for you instead of showing an error. This fixes it on iPad and iOS, where printing used to dead-end.
Fixed the billing and connections pages showing a bright white background for dark-mode users.
Fixed chart labels in flashcard statistics being nearly unreadable in dark mode.
Fixed several menus and drawers feeling sluggish when opening — they now respond instantly.
Fixed the “last viewed” time on shared content showing an older visit instead of the most recent one.

July 3rd, 2026

Custom Designs are now free for everyone

Save your own look and reuse it — on any plan — create a custom design (your style instructions plus reference images) and apply it when generating Slides, Story Books, Infographics, Mindmaps, and AI Videos. It used to be a premium-only feature; now everyone can build and use them.

Improvements

Your most-used dialogs now open instantly — Upload Content, flashcard and quiz creation, the welcome tour, and the plans dialog no longer pause for a moment the first time you open them.
Your folder’s name now shows on your phone — opening a folder on mobile now displays its name at the top, so you always know which folder you’re working in.
Deleting a custom design now asks you to confirm — removing a saved design used to happen on a single tap, which was easy to trigger by accident. We now show a quick confirmation first, so you won’t lose a saved look and its reference images by mistake.

Bug Fixes

You can now remove reference images in Custom Designs on your phone — the remove (×) button on a reference image was only visible on hover, so it couldn’t be tapped on a touchscreen. It’s now always visible on mobile, and the Save / Back buttons stack neatly instead of crowding one line.
Saved web pages now work as study material — if you add a saved web page (for example a Google Drive or Google Docs viewer page) as a source, we now pull out its readable text automatically instead of failing. When a page is really just a sign-in or viewer shell with no content, we tell you right away to download the actual file — instead of trying and failing a minute later.

July 2nd, 2026

Voice Input in Chat

Speak your message instead of typing it — there’s a new microphone button next to Send in AI Chat. Tap it and the input turns into a live recorder with a waveform that moves as you talk; tap stop and your words are transcribed straight into the message box, ready to edit or send.

Improvements

A proper welcome on your phone — new sign-ups on mobile now get a quick, phone-friendly setup: pick what you want to make (flashcards, an AI video lecture, a quiz, or a study guide), then snap a photo of your notes, choose a file, or paste text — and Scholarly starts building it right away. Previously, phones skipped the welcome tour entirely.

Help Center

A full refresh of every help guide — all 58 articles were checked against the current product, and 37 were updated so what you read matches what you see: the new model picker, PDF page selection in every create flow, typeset document themes, AI Meeting Notes, Deep Research file deliverables, and current video modes and lengths.
Four new guides: Paste Text (turn pasted notes into study material), Studying from YouTube Videos, Deleting & Restoring Content, and Account, Login & Password Recovery.
Removed outdated information across help and product pages — including references to a free trial that no longer exists and features that have been retired.

Bug Fixes

Scanned PDFs from Google Drive now work for flashcards — a scanned or image-only PDF picked from Google Drive used to fail with a “blank or unreadable” error even when it was full of content. We now read its pages as images (the same way uploaded scans already work), so it generates cards normally.
Clearer messages when a source can’t be read — if your Google Drive connection has expired you’re now told to reconnect it (instead of a generic “try again”), and empty files or not-yet-transcribed videos now explain exactly what to fix — across AI video lectures, slides, study guides, infographics, and podcasts. These cases also stop retrying pointlessly and refund your credit right away.
YouTube videos no longer fail with a “no transcript” error when building an AI Video Lecture or Podcast — some videos (most often long ones) could report no transcript even though captions were available. Scholarly now recovers the transcript automatically, so generation just works without needing to open the video first.
Fixed the billing link in payment and renewal emails — the “billing settings” link in the payment-failed and yearly-renewal emails pointed to a page that didn’t exist. It now takes you straight to your billing settings.

July 1st, 2026

Improvements

Paste Text is now a first-class way to add study material — a new Paste Text option on Home and a Paste text tab in the Add content dialog turn your pasted notes, lecture transcripts, or articles into a saved source you can study from, no file needed.
Made it clearer that YouTube links are supported: the Upload Content tile now says so, and the Add content dialog highlights YouTube in its link section.
Moved Study Guide to the front of the Home create row.
Tidied up the Home page create options: the newest AI agents — AI Timeline, AI SOP, AI Flowchart, AI Lesson Plan, and AI Outline — now live under the More menu along with the AI Image Playground, keeping the main row focused while every tool stays one click away.
Added a quick Folder shortcut and surfaced AI Chat in the Home create options, and moved Practice Exam into the More menu.
Gave the Add content dialog more comfortable side spacing on mobile, so content no longer hugs the screen edges.
Folders can now be renamed from the folder page — click the folder’s name (or the pencil icon next to it) in the header to edit it in place, just like renaming a PDF or flashcard deck. You can also generate a title with AI while editing.
Redesigned the chat model picker: a focused Recommended Models list up top, with everything else tucked into a dedicated Other Models menu instead of expanding the same list — plus a full-color Gemini logo.

Bug Fixes

Fixed AI Video Lectures coming back in English when your source material was in another language — with language set to Auto, the video now matches your source’s language (Spanish notes make a Spanish video). Picking a specific language still works as before.
AI Video Lectures now make fuller use of their runtime on dense sources instead of over-compressing, stay closer to your material (no invented facts), and preserve your own script’s wording when you provide one in the instructions.
Fixed the Custom Designs editor’s create button staying silently disabled — it now tells you what’s missing, and the design picker shows upfront that custom designs are a Premium feature.
Flashcards now work with scanned or photographed PDFs from Google Drive. If a PDF has no selectable text, Scholarly reads its pages as images instead of stopping — so a scanned textbook still turns into a full deck.
Fixed chat citations sometimes showing as raw source codes instead of clickable source badges — source links now render correctly on every chat model.
Citations now appear as clickable source badges while the answer is still streaming — previously they showed as raw citation text until the response finished.
Fixed AI Video Lecture captions appearing as huge paragraph blocks instead of readable subtitle lines.
Fixed the Build Flashcards button appearing off-center in the practice exam “What would you like to study?” empty state.
Fixed the model picker in chat not showing a hover highlight in dark mode.
Fixed Claude Sonnet 5 erroring out when Thinking was turned on in chat — it now thinks and answers normally.
A model’s thinking summary now appears above its answer instead of below it.

Changelog: Bug fixes & improvements

August 12th, 2026

More AI models for Premium

A clearer pricing page

More reliable YouTube transcripts

Longer free podcasts

Longer free video lectures

August 11th, 2026

Chat with your Research

Deep Research: source-to-artifact workspace

Simpler AI model controls

Clearer Premium plan details

Flashcards: new AI & Sources tab

Regional Pricing

Bug Fixes

August 10th, 2026

Explore: dedicated podcast, video, and flashcard pages

Bug Fixes

August 9th, 2026

Bug Fixes

August 8th, 2026

Video Lectures: color variety and Dark Mode

Stronger reasoning in paid Auto

Video lectures can include a slide deck

Bug Fixes

Clearer content tabs

Calmer podcast and video pages

August 7th, 2026

Premium plan updates

Expert styles in every AI creator

The podcast player now docks at the bottom

Podcasts now come with a research layer

Home opens with your next session

A calmer Home

Folders are just your folder now

Consistent sections on content pages

Uploads

Production QA follow-up

Reliability

August 6th, 2026

Reliability

Cleaner profile menu

August 5th, 2026

Reliability

Chat replies that stay perfectly in place

August 4th, 2026

Faster creator steps

Stop one answer and send the next

Deepseek Flash in every model picker

Simpler model pickers

Reliability

More faithful creation and first-run copy

August 3rd, 2026

A voice picker you can actually hear

Chat and AI Creations settings

Long podcasts now actually run long

A calmer AI Creations tab and podcast page

Reliability

August 2nd, 2026

A calmer, simpler sidebar

Simpler creation menus

Expert styles, where you actually decide

Clearer free media previews

Reliability

August 1st, 2026

Plan any AI creation with chat

Reliability

July 31st, 2026

One AI PDF creator for any document

New: AI File Creator

Preview Office files directly

Clearer yearly pricing on upgrade

More faithful, complete study creations

Reliability fixes

A more reliable page editor

Mobile

July 30th, 2026

Smarter Auto across Scholarly

Everything made from a source, in one place

More reliable video playback