Offline TTS

Offline TTS

Ragmir TTS renders local WAV audio through Transformers.js. Download the model once with non-sensitive text, then render confidential content offline.

printf '%s\n' "Non-sensitive model preload text." > /tmp/ragmir-tts-preload.txt
rgr audio /tmp/ragmir-tts-preload.txt --allow-remote-models --out .ragmir/audio/preload.wav
rgr audio ./brief.md --offline --out .ragmir/audio/brief.wav

The first command warms .ragmir/models/tts. The second requires the local model and does not download anything. Generated audio stays under ignored .ragmir/audio/ state.

For an online MP3 voice, choose Edge explicitly:

rgr audio ./brief.md --engine edge --out .ragmir/audio/brief.mp3

Use Edge only when sending the narration text to the external service is acceptable.

Canonical source: docs/offline-tts-preload.md.