Voice-Cloning

Popular

New

Voice-Cloning

pro

audio_video

Created Mar 29, 2025

$ 30000 /

Clone voices to use with Minimax's speech-02-hd and speech-02-turbo.

Technical Specifications

Service Type: Voice Cloning
Supported Formats:
- Input: Voice file URL, model selection, accuracy settings
- Output: Voice ID and preview audio

Usage Examples

Clone a voice for speech generation

User prompt:

Clone my voice using this audio file: https://storage.oaphub.ai/19/192881631470551040/13853096369321311679b73?k=48ab0f94

Result:

Here is the voice id: voice_12345 (should be shown) and preview audio which should be shown in this format: [audio](https://storage.oaphub.ai/19/192881631470551040/13853096369321311679b73?k=48ab0f94)

Raw Tool call (How LLM might use this tool)

{
  "name": "Voice-Cloning",
  "arguments": {
    "model": "speech-02-turbo",
    "accuracy": 0.7,
    "voice_file_url": "https://storage.oaphub.ai/19/192881631470551040/13853096369321311679b73?k=48ab0f94",
    "need_noise_reduction": false,
    "need_volume_normalization": false
  }
}

Raw tool result from the MCP server

{
  "type": "text",
  "text": "Here is the voice id: voice_12345 (should be shown) and preview audio which should be shown in this format: [audio](https://storage.oaphub.ai/19/192881631470551040/13853096369321311679b73?k=48ab0f94)",
  "annotations": null
}

Tools

Usage: Generate speech with Voice-Cloning

Input Arguments:

Name	Type	Required	Description
`model`	string	✓	The text-to-speech model to train. Options: "speech-02-turbo", "speech-02-hd". Default: "speech-02-turbo".
`accuracy`	number		Text validation accuracy threshold. Range: 0 to 1. Default: 0.7.
`voice_file_url`	string	✓	Voice file url to clone. Must be MP3, M4A, or WAV format, 10s to 5min duration, and less than 20MB.
`need_noise_reduction`	boolean		Enable noise reduction. Use this if the voice file has background noise. Default: false.
`need_volume_normalization`	boolean		Enable volume normalization. Default: false.