MiniMax Voice Cloning

MiniMax Voice Cloning creates a cloned voice from a publicly accessible audio file. After the endpoint returns voice_id, pass that value as the voice field when calling /v1/audio/speech with MiniMax Speech 2.8.

Endpoint

POST /v1/audio/voice-cloning

Model

Model	Description
minimax-voice-cloning	MiniMax quick voice cloning

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	Use minimax-voice-cloning
audio_url	string	Yes	Publicly accessible source audio URL
text	string	No	Preview text. When provided, the response usually includes a preview audio URL
preview_model	string	Conditional	Required when text is provided. Use speech-2.8-hd or speech-2.8-turbo
accuracy	number	No	Similarity requirement, commonly 0.7
need_noise_reduction	boolean	No	Whether to enable noise reduction
need_volume_normalization	boolean	No	Whether to enable volume normalization
clone_prompt	object	No	Prompt audio and matching text for better stability

clone_prompt fields:

Parameter	Type	Required	Description
prompt_audio_url	string	Yes	Prompt audio URL, recommended to be shorter than 8 seconds
prompt_text	string	Yes	Text matching the prompt audio, preferably ending with punctuation

Audio Requirements

Item	Description
Format	mp3, m4a, wav
Duration	At least 10 seconds and no more than 5 minutes
File size	No more than 20 MB
Content	A clear single-speaker recording with low background noise is recommended

Create A Voice

curl -X POST "https://cubicspaces.cloud/v1/audio/voice-cloning" \
  -H "Authorization: Bearer $NEW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-voice-cloning",
    "audio_url": "https://example.com/voice.mp3",
    "text": "This text is used to preview the cloned voice.",
    "preview_model": "speech-2.8-hd",
    "accuracy": 0.7,
    "need_noise_reduction": true,
    "need_volume_normalization": true
  }'

Response Example

{
  "demo_audio_url": "https://example.com/demo.mp3",
  "voice_id": "voice_abc123"
}

Use The Cloned Voice

curl -X POST "https://cubicspaces.cloud/v1/audio/speech" \
  -H "Authorization: Bearer $NEW_API_KEY" \
  -H "Content-Type: application/json" \
  --output cloned-voice.mp3 \
  -d '{
    "model": "minimax-speech-2.8-hd",
    "voice": "voice_abc123",
    "input": "This is an example generated with a cloned voice.",
    "response_format": "mp3",
    "speed": 1
  }'

Fast-cloned voices may be temporary. After creating one, call that voice_id through /v1/audio/speech as soon as possible to confirm that it is available.