jtgi
@jtgi
built a playground to mess with ai voice infra this week, goal is to see how natural and quick i can get it.
6 replies
5 recasts
30 reactions
jtgi
@jtgi
It's a basic websocket server I hand rolled at the moment. Using elevenlabs for speech to text and text to speech and gpt-4o to generate responses. Gonna start swapping components and vendors to see how fast I can get it.
2 replies
0 recast
7 reactions
depatchedmode
@depatchedmode
Check out whisperx I’ve been running it locally for speech to text and then just using the in browser SpeechSynthesis API Lots of room to tune but it’s cool to have everything run local
1 reply
0 recast
1 reaction
Giuliano Giacaglia 🌲
@giu
This is pretty cool!
0 reply
0 recast
1 reaction
Hanisa ☘️
@hanisa12d
/impact multi-tip: 3 $HUNT /impact rewards you for your impact
0 reply
0 recast
0 reaction
Hanisa ☘️
@hanisa12d
/impact multi-tip: 3 $HUNT /impact rewards you for your impact
0 reply
0 recast
0 reaction
Hanisa ☘️
@hanisa12d
/impact multi-tip: 3 $HUNT /impact rewards you for your impact
0 reply
0 recast
0 reaction