Show HN: OfflineTTS - Free browser-based TTS & STT that runs locally

Free text to speech, speech to text, subtitles, and ebook audio

OfflineTTS brings browser text to speech, audio to text, subtitle generation, and EPUB, PDF, or TXT to audio workflows into one private AI audio toolkit.

• 4 local TTS engines
• 99 STT languages
• TXT SRT / VTT exports
• EPUB PDF / TXT audio
• Workflow directory

Find the right private AI audio workflow. Start with the job: free text to speech, audio to text, subtitle generator, creator voice-over, or EPUB, PDF, and TXT listening.

Whisper STT - 99 languages

Audio to Text - Private browser transcription for uploaded audio or video with transcript and subtitle-ready exports.

• Upload audio or video files
• Export transcript or subtitles
• Keep media on your device

Captions - SRT + VTT

Subtitle Generator - Generate subtitle-ready SRT and VTT files for creator media, reviews, and accessibility workflows.

• Built around subtitle exports
• Great for Shorts and Reels
• Pairs with subtitle cleanup tools

Creator audio - WAV + MP3

Voice-Over Workflows - Generate creator narration, faceless channel audio, and short-form script voice-over directly in your browser.

• Paste scripts and generate narration
• Export WAV or MP3
• Built for repeatable creator workflows

Reading workflows - EPUB / PDF / TXT

Ebook to Audio - Convert EPUB, PDF, and TXT reading material into speech for study, accessibility, and audiobook draft listening.

• Parse long-form reading material
• Review sections before generation
• Export listening-ready audio

Platform capabilities

Local engines for TTS, STT, captions, and document audio. Choose Kokoro, Kitten, Piper, Supertonic, 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 - Kokoro - Primary free text to speech engine for natural browser voice generation and multilingual voice workflows. 8 expressions · lightweight
• Kitten - Lightweight local TTS for fast drafts, smaller devices, and quick voice-over experiments. 25 voices · CPU friendly
• Piper - CPU-friendly speech synthesis for offline narration and reliable long-form audio drafts. 5 languages · local
• Supertonic - Multilingual browser TTS with style presets for English, Spanish, Portuguese, French, and Korean. 5 languages · local
• Whisper - Audio to text, video transcription, timestamps, SRT subtitles, and VTT caption exports. 99 languages · transcription

Use cases

Built for creators, accessibility, study, and private research. The homepage links to real tools instead of thin landing pages: generate speech, transcribe audio, create subtitles, and turn documents into listening material.

• Creators - Generate narration, transcript rough cuts, subtitles, and repurposing assets without moving scripts or clips through a third-party dashboard.
• Accessibility - Turn text, documents, and spoken media into formats that are easier to listen to, caption, search, and review.
• Study & Documents - Convert reading queues, TXT exports, EPUBs, papers, and PDFs into listening workflows for revision and hands-free review.
• Teams & Research - Use local transcription for interviews, meetings, and source material when privacy matters more than cloud convenience.

Proof

Why teams pick OfflineTTS over upload-first audio tools. OfflineTTS is built around private browser processing, free usage, and direct export paths for voice, transcript, subtitle, and document audio work.

Private AI audio tools FAQ

The workflows stay browser-first, but each tool family solves a different job. Here is the short version.

Ready to try it

Start with the audio workflow you actually need. Open the voice workspace, start transcription, or jump into the tools directory for subtitle cleanup and EPUB, PDF, or TXT listening workflows.