News for hackers. Stuff that matters.

A comment on Neural Codec Language Models Are Zero-Shot Text to Speech Synthesizers. Parent comment

Re:Neural Codec Language Models Are Zero-Shot Text to Speech... by klysm on Friday January 06, 2023 @12:02AM (#34271179)
What’s real time text to speech mean? Like latency from space bar to spoken?
[ Parent | on HN ]
Re:Neural Codec Language Models Are Zero-Shot Text to Speech... by recursive on Friday January 06, 2023 @12:54AM (#34271493)
Not latency. Like it can synthesize at least as fast as it plays back. Meaning an hour of audio can be generated in an hour or less.
[ Parent | on HN ]
Re:Neural Codec Language Models Are Zero-Shot Text to Speech... by junon on Friday January 06, 2023 @03:11AM (#34272229)
More importantly, can it synthesize as a stream.
[ Parent | on HN ]