Recitare turns any document into lifelike audio with word-by-word karaoke highlighting and Max, an AI study companion that answers with citations you can verify.
PDF · DOCX · PPTX · Images · Web articles · arXiv · PubMed
attention-is-all-you-need.pdf
PII-safeWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.
Max: What does the model lose, and gain, by dropping recurrence? [Page 1]
How it works
Drop a PDF, DOCX, PPTX, or image, or pull a paper straight from arXiv, PubMed, and Project Gutenberg. Recitare handles the messy formatting for you.
Six lifelike voices read to you while each word lights up in sync. Follow along, glance away, and never lose your place in a dense argument.
Ask questions, get Socratic prompts, and receive answers cited to the exact page. Turn passive listening into real comprehension.
recitare: reader
PreviewDrop your paper
Parsed: 15 pages, 6,204 words
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks.
Each head attends to the sentence from a different angle, so the model captures several relationships at once. [Page 4]
Max: Q, K and V are three “views” of your sentence, attention scores how much each word should look at every other word.
Cited from your diagramDrop in any paper, parsed in seconds
Signature feature
Six lifelike voices powered by Inworld TTS-1.5, each word highlighted the instant it's spoken. It's the difference between hearing a paper and actually reading it.
6 lifelike voices
attention-is-all-you-need.pdf
PII-safeWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.
Max: What does the model lose, and gain, by dropping recurrence? [Page 1]
Five reading modes
Switch modes without re-uploading. Each is tuned for a different moment in how you actually study.
Rewrites dense papers to your level, from graduate depth down to a clear first-pass explainer, while preserving citations. No other listening app does this.
Original
“Attentional gating modulates encoding fidelity within the phonological loop.”
Simplified
“Focusing your attention helps your brain hold sounds more clearly.”
Hands-free playback with karaoke sync for commutes and long sessions.
ExploreMax asks Socratic questions and cites every answer to the source page.
ExploreAuto-generated quizzes and flashcards drawn straight from your material.
ExploreCross-reference, highlight, and export notes with a client-side toolkit.
ExploreStudy depth
A Socratic tutor that never just hands you the answer, it helps you reach it, then shows you where it came from.
Fig. 2: no caption, no mercy.
Max: Each “head” reads the sentence from a different angle, then the results are combined, like three readers highlighting the same page for different reasons.
Cited from your diagram, Page 4Structured recaps and revision guides generated from the source, not the open web.
Spaced-repetition cards created from the concepts you actually listened to.
A two-host podcast-style discussion of your paper for a relaxed first pass.
Trust, by design
Not a legal page of promises, concrete mechanisms wired into how Recitare handles your research.
Names, emails, and identifiers are stripped before anything is sent to an AI model.
Every response from Max cites the exact [Page X] it came from, no unsourced claims.
Your documents are yours. They are never used to train models, full stop.
Data encrypted at rest and in transit, with a forensic audit log of every access.
Pricing
Lock in early-adopter rates for life while Recitare is pre-launch. Prices rise for new users after launch, never for you.
Everything you need to try real guided listening.
For the steady reader working through a real stack.
For power readers who live in dense material.
Secure payment via Stripe. Cancel anytime from your account.
Why I built Recitare
“I spent my PhD drowning in papers I understood but never retained. I wanted a tool that let me listen like I study, slowly, with a tutor beside me and a citation for every claim.”
The founder · Recitare is independently built and pre-launch. No investors telling us to chase skimmers instead of serious readers.
Recitare is pre-launch, so we won't invent quotes or numbers. Real words from real early users will live here. Want to be one of them?
Join the first cohortFAQ
Yes. When you sign up you get 20,000 free words to start, enough to listen all the way through a full paper (or two) with the same lifelike voices and word-by-word karaoke as the paid plans, no credit card. It's a one-time welcome grant that waits until you use it; after that, Free continues at 1,000 words a week.
PDFs, Word docs, PowerPoint, and images (we OCR them), plus any web article. You can also pull papers straight from arXiv, PubMed, and Project Gutenberg with one click.
Max only answers from the document in front of you and cites the exact [Page X] it drew from, no open-web guessing or invented sources. Anything personal is stripped out before it ever reaches a model.
Never. Your documents are yours. Personal details are auto-redacted before any AI call, everything is encrypted in transit and at rest, and every access is logged.
See how we handle your data →Yes. Subscribe while Recitare is pre-launch and your rate is locked for life. Prices only rise for new users after launch, never for you.
Recitare runs in any modern browser on desktop and mobile, and a Chrome extension can read any webpage aloud. There is no app to install.
Six lifelike Inworld voices across American, British, and Australian accents, all with word-by-word karaoke highlighting, on every plan.
Yes, one click from your account. Billing is handled securely by Stripe.
Turn your next dense paper into guided listening in under a minute. Free to start, no card required.
Works in any modern browser: desktop & mobile · Chrome extension included