News for hackers. Stuff that matters.

A comment on Launch HN: Vocode (YC W23) – Library for realtime voice conversation with LLMs.

Re:Launch HN: Vocode (YC W23) – Library for realtime voice c... by mkagenius on Wednesday March 29, 2023 @03:45PM (#35362327)
How is this achieving the real time response time? My chatGPT api calls are so slow.
[ Parent | on HN ]
Re:Launch HN: Vocode (YC W23) – Library for realtime voice c... by ajaynraj on Wednesday March 29, 2023 @04:04PM (#35362648)
The short answer is that everything is streaming — as tokens come back from ChatGPT we send them as soon as possible to the synthesizer. The long answer is found in our code[0] :).

[0] https://github.com/vocodedev/vocode-python/blob/main/vocode/...

[ Parent | on HN ]
Re:Launch HN: Vocode (YC W23) – Library for realtime voice c... by og_kalu on Wednesday March 29, 2023 @05:30PM (#35364012)
how is it sounding good though. usually text to speech models need the full context to sound reasonable.
[ Parent | on HN ]
Re:Launch HN: Vocode (YC W23) – Library for realtime voice c... by KianHooshmand on Wednesday March 29, 2023 @09:24PM (#35366498)
We chunk it up per sentence so it has some context!
[ Parent | on HN ]