minimax/voice-cloning ❓🔢🖼️✓ → ❓

⭐ Official ▶️ 30.0K runs 📅 May 2025 ⚙️ Cog 0.16.8 ⚖️ License
text-to-speech voice-cloning

About

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

Example Output

Output

Performance Metrics

34.10s Prediction Time
34.12s Total Time
All 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
}
Input Parameters
model Default: speech-02-turbo
The text-to-speech model to train
accuracy Type: numberDefault: 0.7Range: 0 - 1
Text validation accuracy threshold (0-1)
voice_file (required) Type: string
Voice file to clone. Must be MP3, M4A, or WAV format, 10s to 5min duration, and less than 20MB.
need_noise_reduction Type: booleanDefault: false
Enable noise reduction. Use this if the voice file has background noise.
need_volume_normalization Type: booleanDefault: false
Enable volume normalization
Output Schema
Example Execution Logs
Uploaded voice file in 2.10sec
Cloned voice in 18.48sec
Generating speech with model speech-02-turbo
Generated speech in 13.18sec
Voice cloned successfully with ID: R8_FDU1SV5S
Version Details
Version ID
fff8a670880f066d3742838515a88f7f0a3ae40a4f2e06dae0f7f70ba63582d7
Version Created
November 7, 2025
Run on Replicate →