Great work, I really appreciate the additional options, and definitely like more developer options added if it is possible.
I was doing work with F5 TTS, I extracted several parts of an audiobook, like a part where she is talking happily, sad, crying, and......
So I use it with F5 and get a good result, like after 10 to 50 generations.
My suggestion is that we can give the voice different emotions in the TTS and assign a symbol for each, so that we can put in the text can get better results with less mind-numbing work. It took me weeks to record an hour of audio,
English is not my main language, I hope I made my point, and that is the main reason I need to use tts, thanks
Great work, I really appreciate the additional options, and definitely like more developer options added if it is possible.
I was doing work with F5 TTS, I extracted several parts of an audiobook, like a part where she is talking happily, sad, crying, and......
So I use it with F5 and get a good result, like after 10 to 50 generations.
My suggestion is that we can give the voice different emotions in the TTS and assign a symbol for each, so that we can put in the text can get better results with less mind-numbing work. It took me weeks to record an hour of audio,
English is not my main language, I hope I made my point, and that is the main reason I need to use tts, thanks