Voice Management
Clone, list, and delete Open API voices.
CN API paths use a separate contract
This English reference describes the global FishAudio Open API. For Kitta Audio China integrations, use the CN API Reference, API Playground, and API Keys in this site.
Voice Management
Voice management endpoints let you clone voices from reference audio, list available voices, and delete custom voices you no longer need.
Voice cloning and list endpoints both return voiceId, which can be passed directly into TTS requests.
Endpoints
| Capability | Method and path | Docs |
|---|---|---|
| Voice cloning | POST /api/open/v1/voices | Voice cloning |
| List voices | GET /api/open/v1/voices | List voices |
| Delete voice | DELETE /api/open/v1/voices/{voiceId} | Delete voice |
Authentication
All voice management endpoints require an Open API key:
Authorization: Bearer FISHAUDIO_API_KEYCall these endpoints from your server rather than directly from a browser so your API key is not exposed.
Typical Flow
- Call Voice cloning when a user uploads reference audio.
- Call List voices to fetch public and personal voices.
- Store the returned
voiceId, then pass it directly in TTS requests. - Call Delete voice for personal voices that should no longer be available.
Continue with runnable API checks
Docs and executable requests stay in the same CN-site surface. After reading the reference, open the API Playground for curl examples or manage API keys in the developer workspace.