←back to thread

652 points toebee | 2 comments | | HN request time: 0.6s | source
Show context
hemloc_io ◴[] No.43755481[source]
Very cool!

Insane how much low hanging fruit there is for Audio models right now. A team of two picking things up over a few months can build something that still competes with large players with tons of funding

replies(3): >>43757397 #>>43758495 #>>43760210 #
1. kreelman ◴[] No.43758495[source]
This is amazing. Is it possible to build in a chosen voice, a bit like Eleven Labs does? ...This may be on the git summary, being lazy and asking anyway :=) Thanks for your work.
replies(1): >>43759095 #
2. JonathanFly ◴[] No.43759095[source]
Yes, see: https://github.com/nari-labs/dia/blob/main/example/voice_clo...