Skip to navigation
ProductVoicesVoice Cloning

What files do you accept for voice cloning?

For Instant Voice Cloning and Professional Voice Cloning, we accept a range of file types. We strongly recommend MP3 at 192kbps or above.

Recommended format

  • MP3, 192kbps or higher

Recommended length

  • Instant Voice Cloning: 1–2 minutes of good audio
  • Professional Voice Cloning: 30–180 minutes of good audio

Minimum length for Instant Voice Cloning

When you upload samples in the app, each file must be at least 5 seconds long, and all your samples together must add up to at least 10 seconds. For a good clone, aim for the recommended length above.

Uncompressed formats such as WAV usually do not improve clone quality, and they can cause problems with the upload process. Focus on recording quality instead: use a clean recording with no background noise, room reverb, or multiple speakers, at a consistent volume and tone, without long gaps of silence.

For more information, see Instant Voice Cloning (IVC) and Professional Voice Cloning (PVC).