Realtime Streams

[KhokharJunaid]

I want to know if meloTTS provides real time audio streams in response instead of one audio file at output

[piercarlo62]

Dear [KhokharJunaid] if you look at the code (infer.py), meloTTS doesnt offer stream, but you can modify the file adding a stream output instead to save all in one audio file. But in any case it will be a pseudo-stream because if you check the code the input text is splitted in sentences and then inferred. So this means if you have a long sentence without some punctuation inside, it will infer all text and output the result in one lump. Max you can do is stream each output. Bye