When generating speech, can I have it adapt to a specific speaker style?

[shamoons (Shamoon Siddiqui)]

I want to generate some speech from text (English), but have it sound like a particular speaker. How can I accomplish this?

[shamoons (Shamoon Siddiqui)]

I see something here, https://github.com/mozilla/TTS/pull/472, but am unsure how to implement.

[othiele (Olaf Thiele)]

Please search before you post, we had the same question 3 days ago. If you have further questions, please search before you post:

Is it possible to create a deepfake voice that directly changes your speech?

You are right, TTS is not yet able to do that for end users. Check resemble.ai for that. If you are into programming, there is branch here to train that in order to work with this repo from one of the guys from resemble. But it will be a lot of work.