Text-to-Speech

Use text-to-speech to generate audio from text input.

POST /v1/audio/speech

Request

curl https://api.voxvey.com/v1/audio/speech \
  -H "Authorization: Bearer $VOXVEY_TOKEN" \
  -H "Content-Type: application/json" \
  -o speech.mp3 \
  -d '{
    "model": "openai/gpt-4o-mini-tts",
    "input": "Welcome to Voxvey.",
    "voice": "alloy"
  }'

Required fields

Field	Type	Notes
model	string	Provider-prefixed speech model ID
input	string	Text to render as speech

Notes

• OpenAI-compatible speech models return audio bytes.
• xai/grok-tts is supported for xAI text-to-speech.
• Gemini TTS models are adapted by the gateway when available.