Screenshots
Watch trailer on Steam ↗Paper2Galgame
TamikiP · Published by Mirako
Very Positive — 91% positive (139 reviews) · 11 achievements
Last updated 28 Sept 2026
Turn any PDF, TXT or DOCX into an interactive visual novel. Pick an anime companion, upload a paper or any text you want to understand, and let AI turn it into a 5–10 minute story — with quizzes, voice narration, a blackboard for formulas, and full character customization via Steam Workshop.
£5.29
Lowest price we've ever recorded
View on SteamPrices can lag the live Steam store — always confirm before buying.
Price history
Indie, Early Access, Casual · 2026 · More £5 - £15 games
About this game
Learn anything, with a character you love
Paper2Galgame (Paper2Gal) turns the things you need to read into an interactive visual novel — generated fresh by AI for every upload. Drop in a paper, a textbook chapter, lecture notes, technical docs, an article, even a recipe. Pick a companion. The AI restructures the material into a short, playable story (~5–10 minutes) that you advance chapter by chapter. The name says it all: Paper → 2 → Galgame. "Paper" as in anything worth reading. "Galgame" as in dialogue, chapters, choices, and a companion who's actually glad you showed up.
Learn like you're advancing a story
No more slogging from first page to last. Paper2Gal breaks the material into bite-size chapters and conversations, and your companion walks you through the structure and context, complex concepts, and key takeaways and conclusions. Skim a whole paper fast — or take one section slowly. Upload a recipe and let them teach you the dish. What matters isn't the file name. It's whether there's something inside you want to understand.
Build your own study partner
Who teaches you matters as much as what. Customize everything: character art and expressions, personality, speaking style, and voice. The same document plays completely differently with a different companion. Steam Workshop is supported — grab companions, backgrounds, and music made by other players, or share your own. Voice narration and output are available in English, Japanese, and Chinese.
Not just for papers
It started with one question: "Can a paper actually be fun to read?" It doesn't stop at academia. Use it for research papers and study materials, programming and tech docs, history, economics, psychology, recipes and cooking guides — any text worth understanding. If there's something you want to figure out, try turning it into an episode.
Before you start — three things to know
Paper2Gal generates content with AI in real time. For the best experience:
Each generation makes one short session of about 5–10 minutes. []Long books or papers? Split them by chapter or topic before uploading.
Feeding the AI one huge file won't make a longer story — it can lower quality or fail entirely.
Not a traditional galgame. Not a study app.
There's no fixed script, no routes, and no 50-hour visual novel here. And it's not a course, an exam bank, or a flashcard trainer either. It's a new kind of AI content: you pick the knowledge, you pick the character, and the AI writes a one-of-a-kind learning episode. We're not trying to study for you — we're trying to make the stuff you'd normally avoid just a little easier to open.
Pick a chapter. Pick a companion. Press start on your next episode. Learn anything, with a character you love.
System Requirements
Will my PC run this? →Minimum
- Requires a 64-bit processor and operating system
- OS: Windows 10 64-bit
- Processor: Intel Core i3 / AMD Ryzen 3
- Memory: 4 GB RAM
- Graphics: DirectX 11–compatible integrated or dedicated graphics
- DirectX: Version 11
- Network: Broadband Internet connection
- Storage: 8 GB available space
- Sound Card: Windows-compatible sound device
- VR Support: Not supported
- Additional Notes: An active Internet connection is required for online AI features. Steam features (achievements/stats/cloud saves) require launching the app through Steam; if Steam is not running, these features will be unavailable and the app will run in a degraded mode.
Recommended
- Requires a 64-bit processor and operating system
Supported Languages
*languages with full audio support
Latest news
Patch NotesOfficial
Paper2Galgame August Update: Custom APIs, Multiplayer, Free Reading,More Galgame
Hi everyone, this is the Paper2Gal team.It has been less than a month since Paper2Galgame officially launched on August 10, but honestly, it feels much longer than that.Over the past few weeks, we have been reading feedback from Steam reviews, the community, Discord, Bilibili, and many other channels while continuously fixing bugs, reworking parts of the experience, and adding new features. Many of the updates released in August came directly from player suggestions.If you only tried Paper2Galgame around launch, opening it again now should feel noticeably different.Here are some of the major updates we completed this month.Custom APIs and Character FeaturesCustom API support is now available again.Players can configure compatible model services in Settings and use their own APIs or other supported models for story generation.We have also improved several character-related features:Adjust character position and sizePreview characters while creating or editing themPreview character voicesKeep the currently selected character after restarting the gameAdded JPG support for character imagesFixed multiple Workshop-related character display issuesImproved character resource saving and migrationMultiplayer ModeSteam multiplayer was added in August.The host can create a room and invite Steam friends to experience the story together.Before the session starts, the game synchronizes:CharactersCharacter artworkVRM modelsVoice resourcesBackgroundsThe story begins once everyone has finished loading.During multiplayer sessions:All players can vote on story choicesThe option with the most votes becomes the final choiceTies are resolved randomlyWhen the host asks a question, everyone can see both the question and the answerVoice chat is supportedPlayers can use emotesWorkshop emote packs are supportedSteam names and avatars are displayedIn short, you can now read papers together inside Paper2Gal.Free Reading and Paper Q&AIn addition to the original story-based reading mode, Paper2Gal...Read full article on Community Announcements (peter)Patch NotesOfficial
Paper2galgame August 28 Update – Experience Optimizations
Hello everyone! Four days have passed since the August 24 update. This update focuses on improving document parsing, the story interface, and paper Q&A voice features, while also adding loading screen sound effects, character portrait positioning, Workshop and community entry points, and more.New Story UIAdded a new “full-width visual novel” story UI. The original card-style dialogue box can still be switched back in Settings.After selecting an option, the game now first shows whether the selected option is correct or incorrect before continuing to the next part of the story.Improved the story history, results screen, and various in-game control layouts.Document Parsing & Story GenerationEnhanced recognition for scanned documents, image-based PDFs, and documents with many charts and figures, allowing data charts, architecture diagrams, and experimental results from papers to be more reliably used in subsequent explanations.Improved retry handling for document image extraction and multimodal requests, reducing parsing interruptions, missing images, and occasional generation failures.Streamlined the first-time upload guide to make starting story generation more straightforward.Paper Q&A & VoiceFixed Japanese voice playback.Improved batch voice generation and usage handling for paper Q&A, reducing wait times and duplicate requests during consecutive replies.Fixed an issue where custom Latin-script languages might not take effect correctly when used as the output language.Characters, Loading & Sound EffectsFixed an issue where saved adjustments to custom character portraits—such as position, scale, and mirroring—were not applied in the story.Added a mute button to the loading minigame, and synced it with the mute state in the story.Added click sound effects for web buttons.Workshop & CommunityImproved Workshop item cards, tool entry points, and GPT-SoVITS-related operations, making browsing and managing content more compact on desktop.Stability ImprovementsStrengthened ...Read full article on Community Announcements (peter)Patch NotesOfficial
Update Notes
Hello everyone! Following the August 17 online features patch, this update focuses on expanding paper discovery, guided paper introductions, and Q&A. It also improves save management, the Workshop, and loading performance while addressing recently reported issues with the vision model, blackboard images, and voice playback.Paper Discovery and Daily RecommendationsAdded OpenAlex as a comprehensive paper search source, with Unpaywall and Europe PMC integrated to help locate legally available open-access full text.Daily recommendations are now based on recent popular papers from OpenAlex. You can select a preset research field or enter your own interests in Settings.Removed the limit on local paper image extraction, allowing long documents to be scanned in full.Guided Paper Introductions and Story GenerationGuided introductions now explain a paper's background, key methods, experimental results, and main conclusions chapter by chapter, turning difficult papers into a more approachable interactive story.Improved chapter division, heading-tree recovery, and structure recognition after standard parsing. Stories now follow the paper's table of contents more accurately, with fewer passages assigned to the wrong chapter.Strengthened the connection between generated stories and the source paper. Characters stay focused on the current chapter and can use relevant data charts and architecture diagrams when appropriate.Improved generation concurrency, fallback behavior, and loading progress to reduce stalls, missing chapters, and incomplete content.Paper Q&AAdded a continuous paper Q&A space where you can ask follow-up questions about the entire paper or the current section and review previous conversations at any time.Answers use the paper text, chapter structure, and recognized relevant images to provide more focused explanations.Voice playback can be enabled on demand. If enabled while reading, it takes effect from the next answer without interrupting the current one.Improved...Read full article on Community Announcements (TamikiP)Patch NotesOfficial
Multiplayer Mode Update
Multiplayer Mode lets you experience the story together with your Steam friends!After the host creates a room and invites friends, the game automatically synchronizes characters, sprites, Live2D and VRM models, voices, backgrounds, and other resources. The story begins once everyone has finished loading.During the game, everyone can vote on choices. The option with the most votes will be selected, while ties are decided randomly. When the host uses the question feature, other players can also see the question and answer together.This update improves Multiplayer Mode:- Characters, voices, backgrounds, and other resources are now synchronized before the game starts.- The loading screen now shows each player’s progress.- Fixed players being sent back to the loading screen after synchronization.- Fixed the first voiced line playing while players were still loading.- The player panel now shows Steam names and avatars and can be moved around the screen.- Added voice chat and player reactions.- Steam Workshop reaction packs are now supported.- Everyone can see the question and answer when the host uses the question feature.- The story now waits until every player has made a choice.- The option with the most votes is selected.- Correct answers are shown in green and incorrect answers in red. The story continues after 1.5 seconds.Multiplayer Mode is still being improved. If you encounter any problems, please let us know through the Steam Community!Read full article on Community Announcements (TamikiP)Patch NotesOfficial
Patch Update Notice
Hello everyone! This update mainly improves custom APIs, voice generation, and the overall Steam experience. ## Custom APIs - Fixed an issue that prevented some custom LLM APIs from working because of browser cross-origin restrictions. - Added and improved presets for DeepSeek, Google Gemini, Qwen, and other models. - Improved compatibility with Qwen reasoning models. - Improved connection tests and retry handling for custom models to reduce occasional loading failures. ## Voice - StepFun voice now supports both the Standard API and Step Plan API. - StepFun users can select a concurrency level that matches their account tier, helping reduce rate-limit errors. - Fixed an issue where a Workshop character's reference voice could be previewed but failed to generate speech during a story. - Improved support for reading and uploading reference audio in formats such as MP3 and WebM. - Improved voice generation and voice matching across different languages. - Added a voice indicator to the save list, making saves with generated voice easier to identify. ## Steam Experience - The mute button in the top-right corner of a story now affects only the current story and no longer changes the global sound setting. - Added an “Exit Game” button to the main menu. - Simplified Steam error messages and removed technical error IDs that were difficult for players to understand. - Fixed and improved the display and use of some Live2D and Workshop characters. Thank you for continuing to report issues. If you still encounter problems after updating, please let us know through the Steam Community.Read full article on Community Announcements (TamikiP)
