Voxtral Mini TTS — audio model

Voxtral Mini TTS is a audio model from Mistral AI, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.

Mistral text-to-speech with zero-shot voice cloning. POST /v1/audio/speech with {model, input, voice, response_format}; returns mp3. Voice naming: lang_name_emotion (e.g. en_paul_sad).

curl https://api.hormouz.net/v1/audio/speech \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/voxtral-mini-tts-2603","voice":"alloy","input":"Hello from Hormouz."}' \
  --output speech.mp3