List a provider's TTS models

List a provider's available TTS models

curl --request GET \
  --url https://eu-gcp-api.vg-stuff.com/v3/voices/{provider}/models \
  --header 'Authorization: Bearer <token>'

{
  "provider": "<string>",
  "models": [
    "<string>"
  ]
}

GET

voices

{provider}

models

List a provider's available TTS models

curl --request GET \
  --url https://eu-gcp-api.vg-stuff.com/v3/voices/{provider}/models \
  --header 'Authorization: Bearer <token>'

{
  "provider": "<string>",
  "models": [
    "<string>"
  ]
}

Different providers expose model-specific voice catalogs. The most common ones:

Provider	Models
`elevenlabs`	`eleven_multilingual_v2`, `eleven_flash_v2_5`, `eleven_turbo_v2_5`, …
`deepgram`	`aura-2`, `aura` (different voices per model)
`cartesia`	`sonic-3`, `sonic-2-2025-03-07`, `sonic-turbo-2025-03-07`, …
`openai`	`gpt-4o-mini-tts`, `tts-1`, `tts-1-hd`
`rime-ai`	`mistv2`, `mist`, `arcana`
`minimax`	`speech-02-hd`, `speech-02-turbo`
`ultravox`	`ultravox-v0.7`, `ultravox-v0.6`, `ultravox-v0.6-llama3.3-70b`, …
`google-live`	`gemini-2.5-flash-preview-native-audio-dialog`, `gemini-2.0-flash-live-001`

google-cloud has hundreds of named voices but no model layer — it returns [].

This endpoint does not consume credits.

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

provider

string

required

Provider slug. One of: elevenlabs, deepgram, cartesia, rime-ai, openai, google-cloud, google-live, ultravox, minimax, playht, azure.

Successful response

provider

string

required

models

string[]

required