This open text-to-speech model needs just seconds of audio to clone your voice

stapp · Feb 17, 2025

Palo Alto-based AI startup Zyphra unveiled a pair of open text-to-speech (TTS) models this week said to be capable of cloning your voice with as little as five seconds of sample audio. In our testing, we generated realistic results with less than half a minute of recorded speech.
Click to expand...

Samples of 'real' voice and clone voice provided in article.

https://www.theregister.com/2025/02/16/ai_voice_clone/

Log in or Sign up

This open text-to-speech model needs just seconds of audio to clone your voice

stapp Global Moderator

Log in or Sign up

This open text-to-speech model needs just seconds of audio to clone your voice

stapp Global Moderator

Useful Searches