List Audio Voices

GET /v1/audio/voices View .md

A speech model's voices: its built-in speakers, and the design and clone voices that select voice design and cloning.

Query parameters

model string required

The text-to-speech model, e.g. qwen3-tts-12hz-1.7b.

Responses

application/json · audio-voices-response-payload

3 fields

object string

list
model string
data array of objects
5 fields
- id string
  
  The value to send as voice.
- name string
- mode string
  
  What the voice selects, e.g. custom_voice, voice_design or base (cloning).
- native_language string
- description string

curl https://api.vultrinference.com/v1/audio/voices?model=model \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY"

import os
import requests

response = requests.get(
    "https://api.vultrinference.com/v1/audio/voices?model=model",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
)
print(response.json())

const response = await fetch("https://api.vultrinference.com/v1/audio/voices?model=model", {
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
  },
});
console.log(await response.json());

Response · 200

{
    "object": "list",
    "model": "string",
    "data": [
        {
            "id": "string",
            "name": "string",
            "mode": "string",
            "native_language": "string",
            "description": "string"
        }
    ]
}