Any length of source
WAV, MP3, FLAC or OGG. Long recordings are processed in smooth segments.
Audio Clone
Perform it once. Hear it in any voice.
Text can’t always capture timing, laughter or a dramatic pause. With Audio Clone you bring the performance, and Musa Echo changes who is speaking.
Available on: Free and Pro
What you get
Built for real work
Any target voice
Use a 3–10 second clip, or choose from My Voices.
The performance stays
The words and timing come from your recording. Only the voice changes.
CPU or GPU
Runs well on a CPU, and about six times faster with the GPU pack.
Engines
Powered by Musa engines
How it works
In 3 steps
1
Add the source
The recording whose voice you want to change.
2
Add the target
A short clip of the voice to apply, or a saved voice.
3
Convert
Download the result as a WAV.
FAQ
Common questions
How is this different from Voice Clone Pro?
Voice Clone Pro starts from text. Audio Clone starts from a recording, so your own delivery is kept.
How many conversions do I get?
One a day on the free plan, unlimited on paid plans.
Try Audio Clone on your own computer
Install Musa TTS free. Upgrade only when you need more.