gemini-3.1-flash-tts-preview through MixRoute’s native Gemini endpoint.
For Gemini 3.8 TTS, see Flash TTS and Flash-Lite TTS. Update speaking instructions to speechMetadata and handle the unary WAV response; changing only the model ID is insufficient.
Key capabilities
- Text-to-speech - Convert text into generated audio
- Voice selection - Configure a prebuilt voice
- Audio output - Returns generated speech data
Quick example
- cURL
- Python