API documentation & playground
Choose an API below for endpoint details, parameters, and live testing with your API key.
- Text to Speech (HTTP)
REST synthesis with your voice model ID and engine options.
- Text to Speech (HTTP v2)
Synthesize speech with a voice ID and optional engine settings.
- TTS WebSocket
Streaming speech over WebSocket for realtime use cases.
- TTS WebSocket v2
Updated WebSocket protocol for TTS.
- Speech to Text
Transcribe audio from a public URL.
- Voice clone — create model
Upload reference audio to create a voice model.
- Voice clone — delete model
Remove a voice model by ID.
- Voice clone — list models
List public and personal voice models.
- Lip sync — create task
Create a lip-sync video generation task.
- Lip sync — query task
Poll task status and results by ID.
- Lip sync — list tasks
List lip-sync tasks and statistics.
- User profile (API)
Remaining API quota and basic account info.