Hacker News Reader

Great product, giving it a try. Here you saying that 20 seconds is enough, and on a "clone" page there is an instruction about 30 minutes for better result. Is there any kind of instruction about how to create a good sample of the voice? For example, should I speak English, or any language will do? Do you have some stats on corellation between sample length and generation quality? Thank you!

View on HN

Thanks. What we've shared here is a demo tool to show our new speech model that can clone a voice with few seconds of audio. You can try that with English or non-English recordings, but the generated voice can only speak English at the moment. If you are looking for high-fidelity cloning, you can sign up and try it in our app here - https://play.ht/voice-cloning/

High-fidelity cloning requires at least 20 mins of good quality audio. The more the better.

Reply on news.ycombinator.com