jesulo

> Na verdade @jesulo o problema tá com nova versão da dify. Consegui até contato com os Dev lá. Na versão 0.8.3 tá de boa. E vão lançar o fix...

> From the perspective of real-time digital humans, if your TTS synthesis is slow, shouldn't you solve the TTS problem? Instead of adding buffering, perhaps you can cache the TTS...

@heyyyyou any ideas on how to modify lipasr to wait while there is a tts stream running, and not carry on with chunks of silence? regards

I did it this way, but it still doesn't work. I consulted with artificial intelligences, but they don't understand the flow and are not helpful. def run_step(self): ############################################## extract audio...

I'll try that method, do you have a contact email? El El jue, 14 ago. 2025 a la(s) 11:50 p. m., heyyyyou < ***@***.***> escribió: > *heyyyyou* left a comment...

> has_real_audio = False > # Always consume a fixed number of frames, regardless of type > for _ in range(self.batch_size * 2): > frame, audio_type, eventpoint = self.get_audio_frame() >...

Hi, have you found a way to do multiprocessing? Regards.

Hello, how many sessions were you able to achieve? > [@lipku](https://github.com/lipku) Thanks a lot for the reply. I actually tried wav2lip as well before posting, but the lip movement seemed...