Audio

Voice Management

List, design, and manage voices for MiniMax TTS. Create custom voices with specific characteristics or manage your voice library.

List Voices

POST/v1/audio/voices

Retrieve all available voices including built-in and custom-cloned voices.

cURL

curl -X POST https://api.metriqual.com/v1/audio/voices \
  -H "Authorization: Bearer mql_your_key" \
  -H "Content-Type: application/json" \
  -d '{}'

TypeScript SDK

const voices = await mql.audio.getVoices();
console.log(voices);

Python SDK

voices = mql.audio.get_voices()
for v in voices:
    print(v)

Delete Voice

POST/v1/audio/voices/delete

Body Parameters

voice_idstringrequired

ID of the custom voice to delete

TypeScript SDK

await mql.audio.deleteVoice({
  voice_id: 'my-cloned-voice'
});

Python SDK

mql.audio.delete_voice("my-cloned-voice")

Design Voice

POST/v1/audio/voice-design

Body Parameters

voice_idstringrequired

Custom ID for the designed voice

genderstring

Voice gender

Options: male, female

agestring

Voice age range

Options: young, adult, senior

languagestring

Voice language

descriptionstring

Natural language description of desired voice characteristics

cURL

curl -X POST https://api.metriqual.com/v1/audio/voice-design \
  -H "Authorization: Bearer mql_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "voice_id": "custom-narrator",
    "gender": "male",
    "age": "adult",
    "description": "Deep, warm narrator voice"
  }'

TypeScript SDK

const voice = await mql.audio.designVoice({
  voice_id: 'custom-narrator',
  gender: 'male',
  age: 'adult',
  description: 'Deep, warm narrator voice'
});

Python SDK

voice = mql.audio.design_voice(
    voice_id="custom-narrator",
    gender="male",
    age="adult",
    description="Deep, warm narrator voice",
)

Upload Prompt Audio

POST/v1/audio/prompt-audio/upload

Upload a reference audio file for voice enhancement and style matching during TTS generation.

Quick Start