Minimax Voice Cloning

Minimax Voice Cloning creates custom AI voices from just 5 seconds of audio. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Voice CloningAudio TrainingTTS Integration

4.1k runs

$3 per output

Commercial

🚀Function Overview

A model that creates custom voice clones from short audio samples for integration with Minimax's text-to-speech systems, requiring only 5 seconds of audio for training.

Key Features

Creates voice clones from MP3/M4A/WAV files (10s-5min)
Supports noise reduction and volume normalization
Provides voice ID and preview URI for TTS models
Trains with minimal audio input (as little as 5s)

Use Cases

•Creating personalized voices for TTS applications
•Dubbing and voiceover content creation
•Accessibility tools for custom synthetic voices
•Audio content personalization

⚙️Input Parameters

voice_file

string

Voice file 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.

model

string

The text-to-speech model to train

accuracy

number

Text validation accuracy threshold

need_volume_normalization

boolean

Enable volume normalization

💡Usage Examples

Example 1

Input Parameters

{
  "model": "speech-02-turbo",
  "accuracy": 0.7,
  "voice_file": "https://replicate.delivery/czjl/21U5IFboRwrhBlKks9pmaz119Hvo1ISryE0LNUKuerpqS9UKA/output.wav",
  "need_noise_reduction": false,
  "need_volume_normalization": false
}

Output Results

{ "model": "speech-02-turbo", "preview": "https://replicate.delivery/xezq/p80hlWW4YWptBh3YGnNEDmR8ldh9QQDCxZNrICRge2HgT9UKA/tmpuo0ipa91.mp3", "voice_id": "R8_FDU1SV5S" }

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type
Run Count: 4.1k
Commercial Use: Supported
Pricing: $3 per output
Platform: Replicate