Gemini 3.1 Flash TTS — audio model

Gemini 3.1 Flash TTS is a audio model from Google, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.

Google text-to-speech. POST /v1/audio/speech with {model, input, voice}; returns PCM audio (rate=24000, mono — response_format must be omitted; mp3 not supported). Voices: Kore, Puck, Charon, Zephyr, Aoede.

Specs

VendorGoogle
Typeaudio
Context window—
Pricing$1/M text in · $20/M audio out (PCM)
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":"google/gemini-3.1-flash-tts-preview","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