Minimax Voice Clone

Minimax Voice Clone

Playground

MiniMax Voice Clone is a state-of-the-art voice synthesis model developed by MiniMax. It enables high-quality voice cloning from a short reference clip, producing speech that closely mimics the tone, accent, and personality of the original speaker.

Features

MiniMax Voice Clone

MiniMax Voice Clone is a state-of-the-art voice synthesis model developed by MiniMax. It enables high-quality voice cloning from a short reference clip, producing speech that closely mimics the tone, accent, and personality of the original speaker.

Key Features

• High-Fidelity Voice Cloning
  Generates speech that is perceptually close to the source speaker with natural prosody and pronunciation.

• Few-Second Voice Adaptation
  Requires only a few seconds of reference audio to accurately replicate a voice.

• Emotion and Tone Control
  Allows fine-tuned control over speaking style and emotion, useful for storytelling, games, and character dialogue.

• Multilingual Output
  Supports voice cloning across different languages and smooth code-switching.

• Low-Latency Inference
  Optimized for real-time use cases, including live interactions and dialogue generation.

Use Cases

• AI voiceovers for content creators and influencers
• Personalized digital assistants and chatbots
• Audiobook narration in a specific voice
• Interactive gaming and character voices
• Assistive speech for individuals with voice loss

Model Overview

MiniMax Voice Clone uses a neural TTS pipeline with robust speaker embedding and prosody modeling. It combines clarity, control, and speed, offering production-ready results in diverse environments.

Note

Your clone voice ID must be used at least once with one of the voice models on our platform to be saved permanently. Such as:

• minimax/speech-02-hd
• minimax/speech-02-turbo

Otherwise, we can only store it for 7 days. After that, it will be deleted and the voice ID will no longer be callable.

For easier reuse later, please make sure to use your voice ID once in one of the models above after creating it.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/minimax/voice-clone" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "model": "speech-02-hd",
    "need_noise_reduction": false,
    "need_volume_normalization": false,
    "accuracy": 0.7,
    "text": "Hello! Welcome to Wavespeed! This is a preview of your cloned voice. I hope you enjoy it!"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"