Skip to content
OmniRail
← All models

Mistral · Voice model

Voxtral TTS 3

mistralai/voxtral-mini-tts-3-0
  • Voice
Released Oct 20, 2026

Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in...

Specifications

Input
text, up to 20,000 characters per call
Output
mp3 (default) or raw pcm
Voice
`voice`, default voice_3150 · voice_3150, voice_478, voice_447, voice_485, en_paul_sad, en_paul_neutral, en_paul_happy, en_paul_frustrated, en_paul_excited, en_paul_confident, en_paul_cheerful, en_paul_angry, … (66 in all)
Billing
per character of input text

Use it

POST /api/v1/audio/speech · MCP speak · full reference

curl https://omnirail.org/api/v1/audio/speech \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"mistralai/voxtral-mini-tts-3-0","input":"Hello from OmniRail. Every model, one key.","response_format":"mp3"}' \
  --output hello.mp3