Available now

MiniMax Voice Cloning: voice cloning

By MiniMax

Create a voice from your own recording with MiniMax Voice Cloning. Add a short line for the preview so you can check the voice before writing a longer script.

Model ID
Maker
MiniMax

Input

Fields marked * are required. Review the price before generating.

Uploading a file needs an account. Create account

MP3, WAV · up to 50 MB

Additional settings

Enable noise reduction for the cloned voice

Enable volume normalization for the cloned voice

Text validation accuracy threshold (0-1)

Text to generate a TTS preview with the cloned voice (optional)

TTS model to use for preview. Options: speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo

Price$2.86 / run

You sign up first. Your settings are kept.

About this model

Overview

Upload a clean recording of one speaker, at least 10 seconds long. MiniMax Voice Cloning builds a cloned voice from it and reads a preview text of up to 1000 characters with it, so you hear the result right away.

Noise reduction and volume normalization help with home recordings. A cloned voice that is not used for speech within 7 days is deleted.

What you can build

  • A narrator voice reused across a series of videos
  • Your own voice for course and tutorial narration
  • A consistent character voice for a game or podcast

Prompting tips

  • Use a recording with one speaker, no music and little room echo.
  • Turn on noise reduction when the sample was recorded at home or outdoors.
  • Write the preview line in the style you will use the voice for, such as a calm narration.

What to check

Compare the preview with the sample for pronunciation, tone and recording noise.

Inputs

  • Audio (required): URL of the input audio file for voice cloning. Should be at least 10 seconds long. To retain the voice permanently, use it with a TTS (text-to-speech) endpoint at least once within 7 days. Otherwise, it will be automatically deleted.
  • Noise Reduction (optional): Enable noise reduction for the cloned voice.
  • Need Volume Normalization (optional): Enable volume normalization for the cloned voice.
  • Accuracy (optional): Text validation accuracy threshold (0-1).
  • Text (optional): Text to generate a TTS preview with the cloned voice (optional).
  • Model (optional): TTS model to use for preview. Options: speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo. Options: speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo.

Output and limits

  • Clone only a voice you own or have permission to use.
  • Sung or spoken words can come out unclear or differ from your text.
  • Exact length, tempo and key are not guaranteed; listen to the whole result before you use it.
  • Prompts that name real artists or protected songs can be refused.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to · 1,000 characters: $2.86 / run