Paste up to 2,000,000 characters — a chapter, novel, or full course. FreeTTS chunks it, synthesizes every part in parallel via Azure Batch Synthesis, and packages the result as a single ZIP: chaptered audio in your chosen format (MP3, WAV, or OGG), ready-made SRT & WebVTT subtitles with cumulative timestamps across the whole book, plus a manifest.json and README so you can drop the result straight into Audacity, YouTube, or your distribution pipeline.
7-day money-back guarantee · Lifetime PRO ($199 once) available · No credit card for free tier
Open the Audiobook tab inside Advanced Studio. Paste a chapter, full novel, or course module — up to 2,000,000 characters. The form shows live character count, word count, and estimated audio duration as you type.
Choose any of 400+ voices (✨ DragonHD recommended for narration cadence). Pick the split strategy — Paragraph (default, best for novels), Sentence (dense text), or Fixed 5K (hard split at the nearest word). Pick the output format: MP3, WAV, or OGG.
Submit. Azure Batch Synthesis processes every chunk in parallel — typically 15–30 minutes for a full novel. The page polls every 7 seconds; close the tab if you want, the job runs server-side. When it finishes, download a clean ZIP: part-01.mp3 … part-NN.mp3 (or .wav / .ogg), subtitles.srt + subtitles.vtt with cumulative timestamps across every chapter, a manifest.json with durations and metadata, and a README.txt. Available for 7 days.
The same Azure Batch Synthesis pipeline Microsoft uses for long-form audio — wrapped in a UI that remembers your voice, recovers from interruptions, and packages the output for downstream pipelines.
About 24 hours of audio at typical narration pace. A 90,000-word novel fits in one job — no manual splitting, no separate uploads, no stitching MP3s afterward.
Every paragraph (or sentence, or fixed-5K block) becomes its own audio file in the ZIP, namedpart-01.mp3, part-02.mp3, … so chapters drop straight into Audacity, your DAW, or Pro Tools with boundaries already separated.
Every job ships subtitles.srt and subtitles.vtt with sentence-level cues and cumulative timestamps across the whole book — drop them on YouTube, into a karaoke player, or onto a video editor without writing a single line of code.
Pick the format your distributor wants. WAV for editing and Audible-grade ACX masters; MP3 for Spotify and Google Play Books; OGG for low-bandwidth web/app distribution.
Creator tier unlocks Azure's newest DragonHD models — the most natural narration cadence currently available, with better pacing on dialogue and emotional beats than standard neural voices.
Cheerful, sad, whispering, newscast, empathetic, narration-professional — and 89 more. Pick per chapter for fiction; lock one for nonfiction. Style intensity dial from 0.5 (subtle) to 2.0 (dramatic).
Paragraph — splits on blank lines, best for novels and narration where each paragraph is one rhetorical unit. Sentence — best for dense text without paragraph breaks. Fixed-5K — hard split every ~5,000 chars at the nearest word, best for bulk ingest pipelines.
Asynchronous. Once submitted, the job runs server-side regardless of whether you close the tab, shut your laptop, or restart your browser. The page rehydrates the job status when you come back. Result ZIPs live for 7 days behind a signed download URL that auto-refreshes on every poll.
Cancel button on every running job. Best-effort against Azure (sometimes the job has already completed by the time you click — Azure 404 is treated as success because your intent is satisfied either way). The job stops counting against your monthly character budget.
Every PRO and Creator-tier audio file ships watermark-free with a full commercial license. Publish on Audible, Google Play Books, Spotify, Apple Books, your own site — no royalty, no attribution, no disclosure to FreeTTS required.
Drop your full manuscript, pick a DragonHD narrator, get a publish-ready audiobook in 30 minutes. Output works directly with Google Play Books, Kobo, INaudio, Spotify, and Apple Books AI-narration programs.
Convert lesson scripts into per-module audio. Each chunk = one MP3 = one upload to Teachable, Thinkific, Kajabi, or Udemy. The bundled SRT/VTT subtitles drop straight onto Vimeo, Wistia, or YouTube without re-aligning timestamps.
The single best way to catch awkward phrasing and dropped words is to hear your writing read back. Drop the manuscript in, use a flat narration voice, listen at 1.4× — typos jump out within 30 seconds.
Long-form scripts that need consistent voice, calm pacing, and the option to switch to whispering style for sleep audio. The asynchronous flow means you can iterate on the script and re-batch without babysitting a synchronous loop.
Publishers turning newsletter posts into podcast episodes. Paste, pick a voice, get the MP3 — same workflow weekly. The bundled SRT means YouTube uploads are caption-ready out of the box.
Solo podcasters with no recording setup. Drop the script, pick a voice, drop the result MP3 into your distribution pipeline. For multi-host shows, switch to the Dialogue tab in Studio and assign speakers per line.
Comparison data: competitor pricing pulled from public pages May 2026. Numbers change — check each vendor before purchasing. We update this table when ours or theirs changes.
Three tectonic shifts hit at the same time: distribution opened up, voices crossed the uncanny line, and batch infrastructure went mass-market. The numbers below are the citable facts behind it.
For a 10-hour audiobook (~50,000 words / ~280,000 characters), here's the actual cost breakdown for the three production paths most authors compare.
At $39/month, the Creator subscription pays for itself the first time you skip studio narration on one book. $349 once beats the subscription in month nine — and after that, every future book, every future feature, and every future voice we add is included forever. First 100 founder seats only.
7-day money-back guarantee · 19 of 100 founder seats remaining · Yours forever, no renewals
Listeners expect specific narration profiles for each genre. Match voice to content and reviews tend to land at 4.3+ stars. Mismatch the voice and your average drops by ~0.6 stars regardless of the writing quality. Here's the cheat-sheet we use.
Browse and audition every voice on the FreeTTS voices page before committing to a long batch. Filter by ✨ HD to get the DragonHD models. Each voice has a 30-second sample.
Audiobook distribution opened up dramatically in 2024–2026. AI-narrated audiobooks were 23% of new releases in 2025. Here's the current state, ordered by reach.
Platform policies change. Always verify each distributor's current AI-narration policy before uploading. The FreeTTS commercial license bundled with PRO and Creator covers all of the above.
Just shipped — our pillar guide covering the $14B audiobook market, the new ACX 50% royalty model, every distributor's payout math, and the marketing playbook. Read the Audiobook Guide 2026 →
Use the free PDF to Audiobook converter — drop a PDF, auto-detect chapters, get per-chapter MP3s. No signup required for the basic flow.
Audition all 400+ voices on the voices page before you start a batch. The ✨ HD filter shows the DragonHD models that work best for narration.
PRO Lifetime is $199 once (pays back in month 11). Creator Lifetime is $349 once. Both include every future feature added to PRO/Creator. First 100 seats only.
Up to 2,000,000 characters per single batch job — roughly 24 hours of audio at typical narration speed. The Audiobook tab automatically splits the text into chunks (paragraph, sentence, or fixed-5,000-char strategy) and submits up to 10,000 chunks in one Azure batch synthesis job. For most novels, that's the entire book in one job.
A single ZIP containing: part-01.mp3 … part-NN.mp3 (or .wav / .ogg, your pick) — one file per chapter chunk; subtitles.srt and subtitles.vtt with cumulative sentence-level timestamps that span the entire book; manifest.json with per-part durations, format, voice, and total length; and a README.txtwith usage notes. Drop the MP3s into Audacity or your DAW, drop the SRT into YouTube, and you're done — no JSON to parse, no scripts to write.
The free tier covers 5,000 characters per month with 400+ voices — enough for short demos, narration tests, and small projects. Audiobook Batch Export is a Creator-tier feature ($39/month, or $349 once for Creator Lifetime) because the underlying Azure Batch Synthesis costs scale with audio length. There's a 7-day money-back guarantee on every paid plan and a $199 PRO Lifetime deal that pays back in month 11.
Yes. Google Play Books, Kobo Writing Life, INaudio (formerly Findaway Voices), and Spotify all accept AI-narrated audiobooks — most require a written disclosure that the narration is AI. Audible expanded its AI-narration program in 2025. Apple Books has its own AI-narration program (Apple Books Digital Narration). The commercial license bundled with PRO and Creator covers publishing on every major audiobook distributor.
For long-form narration, the DragonHD voices (Creator tier) deliver the most natural cadence — voice picker filter ✨ HD. Among the standard neural voices, en-US-Andrew, en-US-Aria, en-GB-Sonia, and en-US-Davis are the most popular for English narration. For fiction with character voices, switch to expressive styles (cheerful, sad, whispering) per chapter using the Single tab and stitch the resulting MP3s together.
A 50,000-word manuscript (~280,000 characters, ~5.5 hours of audio) typically completes in 15–30 minutes of wall-clock time on Azure's batch synthesis pipeline. The Audiobook tab polls every 7 seconds and shows live progress; you can close the tab and come back later — the job runs server-side regardless. Result ZIPs stay available for 7 days.
PDF to Audiobookis a free, signup-optional tool that takes a PDF, auto-detects chapters from the table of contents, and generates per-chapter MP3s through the real-time TTS pipeline. It's perfect for readers, students, and dyslexia accessibility. Text to Audiobook (this page) is a Creator-tier batch tool that takes raw text and uses Azure Batch Synthesis to generate jobs up to 24 hours long with multi-format output and bundled SRT + WebVTT subtitles. PDF flow = single document. Text flow = production-grade audiobook export.
Yes. The Audiobook tab shows a Cancel button while the job is in 'queued' or 'running' state. Cancellation is best-effort against Azure; the DB row is marked 'canceled' regardless and the job stops counting against your monthly character budget.
Yes — all PRO and Creator tier audio is watermark-free and ships with a full commercial license. You can publish, sell, monetize, and re-distribute the resulting MP3/WAV/OGG files on any platform without attribution, without royalty, and without disclosing FreeTTS as the source.
75+ languages across 400+ neural voices including English (US/UK/AU/IN/CA), Spanish (ES/MX/US), French (FR/CA), German, Arabic (modern standard + 17 regional), Hindi, Japanese, Mandarin (simplified and traditional), Korean, Portuguese (BR/PT), Italian, Russian, Turkish, Polish, Dutch, Swedish, Thai, Vietnamese, Indonesian, Filipino, Hebrew, Czech, Romanian, Ukrainian — and 50+ more. Voice picker has language filter and language auto-detection from the text content.
Yes — every batch ZIP ships with subtitles.srt and subtitles.vttbuilt from Azure's sentence-boundary events, with timestamps stitched cumulatively across every part so you can use them against the concatenated audio without any re-alignment. Drop them on YouTube, Vimeo, into a karaoke editor, or into a video editor like Premiere or DaVinci Resolve — they work out of the box. Per-chapter SRT is also available for individual clips generated through the Single tab via /api/srt.
Three differences. (1) Cost: FreeTTS Creator is $39/month flat for 5,000,000 chars (about 95 hours of audio); ElevenLabs Audiobooks starts at $99/month. (2) Architecture:we run on Azure Batch Synthesis — the same pipeline Microsoft itself uses for long-form audio — so jobs over 10 minutes are first-class, not a workaround. (3) Output: every ZIP ships ready-made subtitles.srt + subtitles.vtt with cumulative timestamps, plus a manifest.json for downstream tools — bundled, not a paid add-on, no scripts to write.
Free tier first. Upgrade to Creator only if you need the full batch export.
7-day money-back guarantee · Lifetime PRO available · Cancel anytime