{"toolsTextToSpeech":{"heroBadge":"Text-to-Speech","heroTitle":"Listen to Your Documents as","heroTitleHighlight":"One Natural MP3","heroDesc":"Upload a PDF, report, chapter, or set of notes and Scholarly reads the whole thing aloud in a natural voice, then hands you a single MP3 file. Not a summary and not a chatty multi-speaker show — your document, word for word, in your ears.","heroCta":"Turn a document into audio","heroCtaSecondary":"Want a summary instead?","heroNote":"1 AI Creation Credit per 10,000 words · Included on every paid plan","heroSocialProof":"Used by 200,000+ learners and professionals","trustStat1":"30,000","trustStat1Label":"Words per narration","trustStat2":"25+","trustStat2Label":"Voices to choose from","trustStat3":"1 file","trustStat3Label":"One unified MP3","eyebrowAnswer":"Quick answer","answerTitle":"What is a document text-to-speech tool?","answerBody":"A document text-to-speech tool converts written material into spoken audio so you can listen instead of read. Scholarly takes a PDF, Word document, slide deck, web page, or your own notes, strips out the formatting a voice should never say out loud, and reads the full text in a natural AI voice. The result is one continuous MP3 rather than a folder of clips — so it plays end to end in any podcast app, car stereo, or headset. Nothing is summarized, reworded, or skipped: it is your document, read aloud.","answerUpdated":"Updated August 2026. Voice options, length limits, and credit costs reflect the current version of Scholarly.","eyebrowHow":"How it works","howTitle":"From document to MP3 in three steps","howDesc":"Under a minute of setup, then it runs in the background while you do something else.","step1Title":"Add your document","step1Desc":"A PDF, Word file, PowerPoint, text file, web page, or something already in your library. Combine up to five sources into one narration, and pick a page range if you only need part of a long PDF.","step2Title":"Pick a voice and pace","step2Desc":"Choose from over 25 natural voices and set the speed anywhere from 0.75× to 1.5×. Narration is available in the same languages Scholarly supports everywhere else.","step3Title":"Listen anywhere","step3Desc":"It generates in the background and lands in your library as a single MP3. Play it in Scholarly, or download it once and listen on your commute, at the gym, or offline.","eyebrowCompare":"Text-to-Speech vs. summarize","compareTitle":"Two different jobs, two different tools","compareDesc":"Text-to-Speech reads what is actually on the page. An audio summary rewrites it into a shorter spoken recap. Pick the one that matches what you need from the material.","compareReadTitle":"Text-to-Speech reads it","compareRead1":"Every sentence of the source, in order, unchanged","compareRead2":"Right when the exact wording matters — contracts, regulations, papers, coursework","compareRead3":"Long-form: a full chapter or report, not a highlight reel","compareRead4":"One MP3 that plays end to end anywhere","compareSummaryTitle":"An audio summary rewrites it","compareSummary1":"Condensed into the key ideas, in a host's own words","compareSummary2":"Right when you want the gist of something you will not read in full","compareSummary3":"Short-form: 5 to 12 minutes for a whole chapter","compareSummary4":"Chapters, a synced transcript, and citations back to the source","eyebrowExpect":"What you get","expectTitle":"What a narration actually gives you","expectDesc":"Built for people who need the material in their ears, not a novelty voice demo.","expect1Title":"Formatting that stays silent","expect1Desc":"Markdown symbols, table pipes, and heading marks are stripped before anything is spoken, so the voice never reads \"hash hash Introduction\" at you.","expect2Title":"A voice you choose","expect2Desc":"Over 25 voices with different warmth, pace, and character. Preview them, pick one, and every narration you make uses it until you change it.","expect3Title":"Speed you control","expect3Desc":"0.75× when the material is dense, 1.5× when you are reviewing something you already know. Set it before generation so the file is right on the first play.","expect4Title":"Your language","expect4Desc":"Narration follows the language setting you use everywhere else in Scholarly, so a document you study in one language reads back in it.","expect5Title":"A real file you keep","expect5Desc":"One MP3 in your library. Download it and it is yours — no app required, no streaming, no expiry.","expect6Title":"Runs in the background","expect6Desc":"Start it and close the tab. A long report takes a few minutes; Scholarly opens the finished audio for you when it is done.","eyebrowFaq":"FAQ","faqTitle":"Text-to-Speech questions","faq1Q":"How much does it cost to narrate a document?","faq1A":"One AI Creation Credit per 10,000 words, rounded up, with a one-credit minimum. A 6,000-word article costs one credit; a 24,000-word report costs three. You are charged when the narration starts, and refunded automatically if it fails.","faq2Q":"How long can a document be?","faq2A":"Up to 30,000 words in a single narration, which is roughly three hours of audio. For anything longer, narrow the page range or split it into two narrations — you can select a page range on any PDF before you start.","faq3Q":"What file types can I narrate?","faq3A":"PDFs, Word documents, PowerPoint decks, plain text and Markdown files, spreadsheets, saved web pages, and anything already sitting in your Scholarly library. You can also paste a URL and narrate the page behind it.","faq4Q":"Is this a summary?","faq4A":"No. Text-to-Speech reads the source as written, in order, with nothing added or removed. If you want a shorter spoken version that explains the material rather than reciting it, use the audio summary generator instead.","faq5Q":"Can I download the MP3?","faq5A":"Yes. The narration is saved to your library as a normal MP3 file, and you can download it and play it in any podcast app, media player, or car stereo. It works offline once downloaded.","faq6Q":"How long does it take to generate?","faq6A":"A short article is usually ready in a minute or two. A full-length report can take several minutes because the audio is synthesized in pieces and then assembled into one file. It runs in the background, so you can close the tab and come back.","faq7Q":"Can I choose the voice?","faq7A":"Yes. Over 25 voices are available, each with a distinct character and pace, and you can preview them before choosing. You can also set the playback speed between 0.75× and 1.5× before the narration is generated.","faq8Q":"Does it read tables, formulas, and citations?","faq8A":"It reads the text it can extract from your document, and strips formatting characters that would otherwise be spoken aloud. Dense tables and mathematical notation do not narrate well by nature — for material like that, a study guide or audio summary is usually the better format.","relatedHeading":"Related tools","relatedSubheading":"Other ways to turn your material into something you can listen to, study, or share.","related1Title":"Audio summary generator","related1Desc":"A short spoken recap of a chapter instead of the full read.","related2Title":"AI podcast generator","related2Desc":"A multi-speaker conversation that explains your source material.","related3Title":"Podcasts feature","related3Desc":"See how Scholarly turns sources into podcast episodes.","related4Title":"PDF to podcast","related4Desc":"Turn a PDF into a hosted episode with chapters.","related5Title":"Audio to text","related5Desc":"The reverse trip — transcribe a recording into text.","related6Title":"Audio to notes","related6Desc":"Turn a recording into structured study notes.","related7Title":"Summarizer","related7Desc":"Condense a long document into the key points in writing.","related8Title":"AI study guide","related8Desc":"Build a structured guide from the same source.","eyebrowPricing":"Pricing","bottomTitle":"Start listening to what you have to read","bottomDesc":"One AI Creation Credit per 10,000 words, on every paid plan. Upload a document and get an MP3 back.","bottomCtaSecondary":"Explore audio features","seoTitle":"Text-to-Speech for Documents — Turn PDFs Into One MP3","seoDescription":"Convert PDFs, reports, and notes into one natural-sounding MP3 you can listen to anywhere. Full text read aloud, 25+ voices, and adjustable speed.","seoKeyword1":"text to speech","seoKeyword2":"pdf to speech","seoKeyword3":"document to audio","seoKeyword4":"pdf to mp3","seoKeyword5":"read documents aloud","seoKeyword6":"text to speech mp3","seoKeyword7":"ai voice reader","seoKeyword8":"listen to pdf","seoKeyword9":"document narration","seoKeyword10":"text to audio converter","seoFeature1":"Full-text narration of PDFs, Word files, slides, and web pages","seoFeature2":"One unified MP3 you can download and keep","seoFeature3":"25+ natural AI voices","seoFeature4":"Adjustable narration speed from 0.75x to 1.5x","seoFeature5":"Up to 30,000 words per narration","seoFeature6":"Runs in the background and saves to your library","seoHowToName":"How to turn a document into speech","seoHowToStep1Name":"Add your document","seoHowToStep1Text":"Upload a PDF, Word file, slide deck, or text file, paste a URL, or pick something from your Scholarly library. Select a page range if you only need part of it.","seoHowToStep2Name":"Choose a voice and speed","seoHowToStep2Text":"Pick from over 25 natural voices and set the narration speed between 0.75x and 1.5x. Scholarly quotes the credit cost before you start.","seoHowToStep3Name":"Listen or download","seoHowToStep3Text":"The narration generates in the background and lands in your library as a single MP3. Play it in Scholarly or download it to listen offline."}}