Audiobooks Subtitles Speech to Text
Convert text to speech online directly in your browser with voices from Kokoro, Piper, Kitten, Supertonic, and Pocket TTS. This offline text to speech workflow needs no signup or OfflineTTS per-character bill. English voices can work offline after download when cached models and the selected engine support local generation.
5
local TTS engines
99
STT languages
TXT
SRT / VTT exports
EPUB
PDF / TXT audio
Try text to speech now
Paste your text, choose an English voice, and generate private speech without leaving this page. Your text and generated audio stay in your browser.
The embedded homepage control accepts up to 1,500 characters and provides five curated American or British English voices, three speed presets, waveform playback, and WAV or MP3 download. It is designed for a quick first generation, not as the full four-engine workspace. Open the advanced TTS tool for longer scripts, every Kokoro voice, model precision, history, and optional subtitle timing.
The first generation downloads the Kokoro model and voice assets. English text and generated audio are not uploaded to an OfflineTTS synthesis account, while model delivery, hosting, and ordinary site analytics remain network activity covered by the Privacy Policy. Listen for names, numbers, pronunciation, and pacing, and check the upstream model, voice, source-text, and publication rights before commercial use.
Four simple steps
Use the homepage tool for a fast voice preview, waveform playback, and downloadable audio. The model stays unloaded until you ask it to generate speech.
First visit: download the Kokoro model. Later visits: reuse the browser cache and generate English speech offline when supported.
Paste up to 1,500 characters into the homepage text to speech tool. Your draft remains in the browser.
Pick a curated American or British English voice and select a relaxed, natural, or brisk generation speed.
Select Generate Speech. Kokoro downloads only on first use, then creates the audio on your device with WebGPU or WASM.
Review the result with the waveform player, seek to any point, and download the finished speech as WAV or MP3.
Workflow directory
Start with the job: free text to speech online, audio to text, subtitle generator, creator voice-over, or EPUB, PDF, and TXT listening.
Whisper STT
99 languagesPrivate browser transcription for uploaded audio or video with transcript and subtitle-ready exports.
Subtitle cleanup
SRT / VTTRemove timestamps, labels, and formatting from existing SRT or VTT files before editing or text-to-speech.
Creator audio
WAV + MP3Generate creator narration, faceless channel audio, and short-form script voice-over directly in your browser.
Reading workflows
EPUB / PDF / TXTConvert EPUB, PDF, and TXT reading material into speech for study, accessibility, and audiobook draft listening.
TTS directory
Jump straight to a dedicated TTS page for your language or creative job — each with curated voices, local audio synthesis, and WAV/MP3 export.
Creator workflows
Use browser-based voice-over, transcription, and caption workflows to move from a creator script or recording to narration, searchable text, and subtitle files.
Choose the output you need, then open the dedicated tool for your video, podcast, or short-form workflow.
Free AI voice
Turn a draft into browser-based narration, accessibility audio, or a downloadable WAV or MP3 sample without an account.
Text to voice →Creator voice-over
Generate YouTube, Shorts, TikTok, Reels, and faceless-channel narration in one browser voice workspace.
Script to voice-over →Private transcription
Turn local audio or video into text, timestamps, SRT, or VTT without uploading the source file.
Transcript and captions →Subtitle cleanup
Remove timestamps, speaker labels, tags, and duplicate lines from SRT or VTT before repurposing.
Clean subtitle text →Script preparation
Break long paragraphs into speaking units, add pacing cues, and estimate narration duration.
TTS-ready script →Text preparation
Strip URLs, HTML, emoji, and formatting artifacts before voice generation.
Clean narration text →Long-form listening
Parse EPUB, TXT, and text-based PDF files into resumable paragraph audio and a local read-along.
Document audio →Platform capabilities
Choose Kokoro, Kitten, Piper, Supertonic, Pocket TTS, or Whisper from the same browser-first platform for voice generation, transcription, subtitles, and reading workflows.
All core tools run in the browser. English TTS and Whisper STT can work offline after model download.
54 voices · 9 languages
Primary free text to speech engine for natural browser voice generation and multilingual voice workflows.
8 expressions · lightweight
Lightweight local TTS for fast drafts, smaller devices, and quick voice-over experiments.
25 voices · CPU friendly
CPU-friendly speech synthesis for offline narration and reliable long-form audio drafts.
31 languages · local
31-language multilingual browser TTS with local Unicode processing and ten built-in voices.
8 voices · voice cloning
Clone your voice by recording it or uploading audio, plus 8 built-in voices — all generated locally in your browser.
99 languages · transcription
Audio to text, video transcription, timestamps, SRT subtitles, and VTT caption exports.
Use cases
Start with text to speech on this page, then use focused tools to transcribe audio, create subtitles, and turn documents into listening material.
Generate narration, transcript rough cuts, subtitles, and repurposing assets without moving scripts or clips through a third-party dashboard.
Turn text, documents, and spoken media into formats that are easier to listen to, caption, search, and review.
Convert reading queues, TXT exports, EPUBs, papers, and PDFs into listening workflows for revision and hands-free review.
Use local transcription for interviews, meetings, and source material when privacy matters more than cloud convenience.
Proof
OfflineTTS is built around private browser processing, free usage, and direct export paths for voice, transcript, subtitle, and document audio work.
| Feature | OfflineTTS | Typical upload-first service |
|---|---|---|
| Speech processing | Runs in the browser | Media or text is commonly sent to the provider |
| Account | Not required for the public tools | Often required for generation or saved projects |
| Product charge | No OfflineTTS subscription or per-character meter | Depends on the provider's current plan |
| Offline behavior | Engine, language, cache, and asset dependent | Depends on the provider and application |
| Responsibility | User reviews output and upstream terms | Provider features and terms vary |
Direct answers about free voice generation, downloads, offline use, available voices, and browser privacy.
Ready to try it
Open the voice workspace, start transcription, or jump into the tools directory for subtitle cleanup and EPUB, PDF, or TXT listening workflows.