Yeah, no basement dweller dev's are gonna be messing with that API until the costs drop by at least 100x, which I honestly only see as a near term incentive for Meta to get a Llama Voice model cookin'
@jamesjonnes
16 сағат бұрын
I'll use it, but can't wait for an uncensored open source version. Text only is too boring. I lack the patience to use text only for too long for the tasks I want, like learning languages.
@sykexz6793
2 күн бұрын
I don't think this is the same model as advanced voice mode.
@DarrenJohn10X
2 күн бұрын
Looking forward to seeing your alleged "spaghetti" code! (Right now 2 weeks ago is your latest repo)
@OliNorwell
2 күн бұрын
Great work! You must have had a busy couple of days getting it working
@meetsummdev
Күн бұрын
you can really implement it in a few hours
@jamesyoungerdds7901
2 күн бұрын
Great video, thanks Kris! I'm interesting in the function calling and structured output from the voice websocket return. Can you use agents or agentic flows with constrained and structured outputs with the voice mode 🤔
@DhairyaMarwah-l1u
Күн бұрын
Can you share the repo link ?
@boxeemusic
Күн бұрын
where can i find the code? pls help
@ibrahimaba8966
13 сағат бұрын
I just integrated it on Twilio, it changes everything, but it took me a bit of time.
@三川富資訊股份有限公
7 сағат бұрын
The Realtime API cost is high. I suggest that there is a cheaper way. 1.Using Google STT to get user's speech texts. 2.Send texts to GPT. 3. Get responses from GPT. 4.Send responses to Google TTS. 5.User gets AI responses in both texts and voices. The response time is longer and it costs lower.
@Akander20
2 күн бұрын
where can i get the repo?
@tommoves9935
2 күн бұрын
Happy to be the first to comment. Kris you are always up to date. Once again cool stuff from you. Spaghetti code... 🤣. Great that you did talk about the costs as well. I like your creative and often real funny ideas. Please keep up the great work! Regarding your phone call: saw a video from a guy in the US weeks ago (no Realtime API) - he did let his AI order a Pizza and it worked great. Latency even back then was good enough - should work perfectly. Maybe try it with an italian accent 😉. Thx from Tom!
@Dea07thox
2 күн бұрын
Can't you just better prompt it to have a less talkative output so you don't have to break it's response that often? That would make a big difference and everything more seamless :)
@MagagnaJayzxui
2 күн бұрын
What is AVA?
@DesignDesigns
2 күн бұрын
This is mindblowing...
@Bangs_Theory
2 күн бұрын
Which function controls the interruption?
@gaijinshacho
2 күн бұрын
VAD
@alarconfilms1
2 күн бұрын
What is the code used?
@khalifarmili1256
2 күн бұрын
It's not out yet
@romera9662
2 күн бұрын
@@khalifarmili1256 How long will it take?
@dievas_
2 күн бұрын
I still don't have access to it :/
@saksham3
2 күн бұрын
Doesn't it have emotions?
@micbab-vg2mu
2 күн бұрын
Thanks :)
@contentfreeGPT5-py6uv
2 күн бұрын
i tested yesterday ,but Error al conectar: 403 Acceso denegado. Verifica tu clave de API y los permisos para usar el API Realtime.
@elprox1290
2 күн бұрын
try checking your api key or just making a new one
@contentfreeGPT5-py6uv
Күн бұрын
@@elprox1290 again, thanks
@AI_Escaped
2 күн бұрын
No one is going to be even able to develop at these prices other than those with deep pockets. Just testing and figuring things out would be too expensive to even try.
@thenoblerot
2 күн бұрын
By telling it it is playing a game with the user, it might be failing on purpose to let you win!
Пікірлер: 30