Thank you for this great project. When I use xtts as the speech engine and try to stream audio playback, I observe that the code outputs the audio to the player only after the entire audio synthesis is completed. However, when I directly call OpenAI's TTS API, I can play the audio during the synthesis process.
Thank you for this great project. When I use xtts as the speech engine and try to stream audio playback, I observe that the code outputs the audio to the player only after the entire audio synthesis is completed. However, when I directly call OpenAI's TTS API, I can play the audio during the synthesis process.