Closed yumianhuli2 closed 1 month ago
If there are more than one speaker in a long long sentence, how does this work with edge-tts? Is there an example? Thank you!
It's not possible because custom SSML is not available. You could just create another generation with a different voice.
If there are more than one speaker in a long long sentence, how does this work with edge-tts? Is there an example? Thank you!