How does OfflineTTS work?

OfflineTTS runs AI models directly in your browser using WebGPU or WebAssembly. Use Kokoro, Kitten, Piper, or Supertonic for TTS and Whisper for speech to text.

Is it really free?

Yes. The models run on your hardware, so there are no per-generation server costs, no API keys, and no subscriptions.

Does it work offline?

English TTS works fully offline after model download. Non-English TTS uses lightweight phoneme conversion before local synthesis. Whisper STT works offline after model download.

What can I do beyond text to speech?

OfflineTTS also handles private audio transcription, subtitle exports, creator voice-over workflows, and ebook or document to audio conversion.

Can I use generated speech commercially?

In most creator workflows, yes. You should still review the upstream model terms for the exact engine you use before large-scale commercial deployment.

What audio formats can I export?

You can export WAV or MP3 from the voice workflows. Whisper transcription exports TXT, SRT, and VTT.