Grok Voice TTS — audio model

Grok Voice TTS is a audio model from xAI, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.

xAI text-to-speech. POST /v1/audio/speech with {model, input, voice, response_format}; returns mp3. Voices: eve, leo, rex (+more); 20+ languages.

Specs

VendorxAI
Typeaudio
Context window—
Pricing$15/M characters (mp3)
APIspeech

Code example

curl https://api.hormouz.net/v1/audio/speech \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"x-ai/grok-voice-tts-1.0","voice":"alloy","input":"Hello from Hormouz."}' \
  --output speech.mp3

Use via Hormouz

Connect to this model and 450+ others with one API key — stable under heavy load and optimized for Iran.

Get started

Related models