Comment by ZeroCool2u
8 hours ago
Gemini live has been able to do this for over a year now. I can just activate it on my phone and it really works surprisingly well, especially the interruption. I've tested it with my 95 year old Dutch grandmother and it switched seamlessly between English and Dutch with her and handled her poor hearing very well, including her asking for repetition.
I'm a little surprised by how much OAI is playing catch up here.
Gemini live is also pretty decent at computer vision stuff too. I've used it while working on my bike & car a few times, with my phone camera and it'll circle/highlight specific screws and parts. You can set your phone up on a tripod and it'll walk you through complete repairs for things.
I used it for double checking some stuff while helping my friend build his PC! I had it in tight spaces and it helped me verify some details around which nvme slot to use first.
ChatGPT has had this for over a year too. This is a better model.
One thing Simon pointed out: Usually live voice models are not as capable as the frontier ones. What makes this one special is that it can delegate the task to a frontier model while talking to you.
Is gemini live the same app I have on my oneplus 15? I don't think that's full duplex?
it is not full duplex. I think this GPT-Live thing is the first full duplex speech to speech model
ehh, no? definitely not.
https://kyutai.org/blog/2024-07-03-meet-moshi/
What do you mean? OpenAI has had a real-time voice model since August of last year. This is a new model with better performance.
Well Google has been working on voice assistants for years now on android. It makes sense that they had a head start