Audio Voices
Endpoints
Audio Voices
Browse the available voice library across both providers. Pick a voice_id for /v1/audio/speech.
GET
Audio Voices
Read-only passthrough of TTS voice catalogs across both supported providers:
- ElevenLabs — ~3,000 voices (premade + community)
- MiniMax — ~300 system voices spanning Chinese, English, Japanese, and other languages
voice_id to POST /v1/audio/speech.
Voice ↔ model compatibility: ElevenLabsvoice_ids only work witheleven-*SKUs. MiniMaxvoice_ids only work withminimax-speech-*SKUs. The two are not cross-compatible.
Query parameters
Response
200 OK. Each voice record carries a provider field so you can disambiguate when fetching ?provider=all.
Common fields
ElevenLabs-only fields
MiniMax-only fields
The full ElevenLabs catalog is large (~100 KB JSON). For a picker UI, fetch once on mount and cache client-side. The MiniMax catalog is smaller (~300 voices) and trivial to ship inline.
Cache headers
Errors
Picking the right voice for your SKU
See also
POST /v1/audio/speech— use avoice_idfrom this listPOST /v1/audio/voice-clone— create a custom voice from a reference recording (10s–5min)POST /v1/audio/voice-design— create a synthesized voice from a text description