Gemini Live Avatars

0:00 Welcome. I'm Jennifer. I'm ready to dive into the latest F1 action with you. >> Hey Jennifer, who won the latest Grand Prix? >> George Russell won the latest Grand Prix

0:09 in Azerbaijan. He had a fantastic race holding off Max Versstappen to take the win. >> So where did Kimmy Antonelli come? >> Kim Anteneelli finished in fifth place

0:19 after a really impressive recovery drive from 16th on the grid. >> Okay, so that was Google's new live avatars with Gemini 3.8 Live. So, I've talked about the live models in the

0:30 past. These are the birectional models that basically have multimedia going in being audio and video. And up until recently could just produce text or audio back. Well, Google's now updated

0:42 that. So, you can actually have a live rendering face that kind of lives what the actual audio is. So, up until recently, if you wanted to do any sort of AI agent with a face that could

0:52 actually hold a conversation, you were generally sort of stitching together four different things. You had some kind of speech to text, you had an LLM, you had a TTS model creating the voice back,

1:03 and then there was some sort of avatar service on the end doing lip sync. And the challenge has always been with that kind of thing is that every one of those points adds a lot of latency. And by the

1:13 time the mouth starts moving, the conversation has often already started to fall apart. Now, I won't say that Google's got this perfect, but what they've done is pretty impressive.

1:22 They've made their Gemini 3.8 a live avatar system generally available. And there are actually a few caveats to that which I'll mention later on in the video. But this whole thing basically

1:31 collapses down those four models that you had to take care of yourself into a single stream. It can listen. It can see what's on your screen. It can call tools in the background. As you can see in the

1:42 example I just showed, it was using Gemini search to basically get the latest results from Saturday's Grand Prix. And the cool thing here is it can do all of this in 97 languages. So, I've

1:53 been playing with this for a while and I've built some demos that I'm going to go through in a second and show you. But let's put this into a little bit of context. So, while we've still yet to

2:01 see a Gemini Pro model come out now for I think it's about 7 months, this has still been a pretty busy week for Google on the audio side. So, in my last video, I talked about the whole new TTS system

2:12 that they launched with the voice cloning, with those sorts of things. And actually before that they updated Gemini 3.8 live and live extended thinking and now they've released live avatar. And

2:23 like I said in the last video wherever you think about Google is in the LOM race at the moment the multimodal and audio stuff has been really strong. They've had omni live translate

2:34 transcribe the TTS models and now this live avatar. So I guess quickly what does generally available actually mean here? Basically it's ready for production on Google cloud. But the sad

2:45 thing here is that not everything is generally available. You get a library of pre-built avatars. If you want a custom avatar, one made from your own reference photo, your own sort of voice,

2:55 that kind of thing, that's behind an allow list and a verification process. And even things like the live extended thinking version of live is still in private preview. So in this video, I'm

3:05 just going to show what you could go and do and build right now and show that in my demos, etc. If you want to see an example of the custom agents, they've got a video in there with a demo of

3:15 making a custom avatar for an avatar with a really bad Australian accent that I think only a bank owned by Crocodile Dundee would actually want to use. So, with what they've actually made

3:24 generally available in here, you've got a bunch of different visual avatars that you can pick from. So, here I've made an avatar studio, which is basically a front-end app that's running this and

3:36 streaming the live avatars through the back end in here. So here we can basically just pick any of the avatars that we want to. I can then basically choose a voice that I've got and they've

3:46 got a set of voices that we can actually pick. We can pick the sort of persona preset that we want. Let's go for a time traveling tour from 2126. And then we've got system instructions. Now obviously

3:58 the system instructions you can fully customize yourself. You can get all of that set up and then you can add in tools if you want. So here I've basically got Google ground searching

4:07 for this. Now, since we're talking to someone from the future, that actually might not be good. I will leave that off for now. And then basically what I can do is I can just start it. And then I've

4:17 got the choices once I start. >> Wow, it is so incredible to finally see the quaint 21st century in person. >> Okay. And you can see there that now I'm talking to Vera. Vera, how are you doing

4:30 today? >> I am doing absolutely wonderful. Thank you. Exploring this era is just pure magic. These are actually a perfect vintage replica of 2026 fashion. So you

4:42 could say I dress the part to blend in perfectly. >> Okay. So what I want to show is that we can actually type to you as well. So I'm going to ask you a question in a second

4:51 and I only want you to answer the question when you see the typed question. >> Understood. I am ready and waiting for your typed question. I'm doing

4:59 absolutely fantastic. Just the incredible energy of 2026. You can see there that basically she was able to take the type or voice and she's still listening to me. Aren't you Vera?

5:12 >> Exactly. I'm processing everything perfectly no matter how it reaches me. >> Okay, I'm going to stop her there. So, you can get a sense from that this is actually pretty responsive right now.

5:23 There is a delay and obviously we're going to get the transcript back ever so slightly before the actual voice comes back which kind of makes sense. But you can see for something where now we can

5:34 go through and pick any of the different avatars. You can pick photorealistic avatars or you can pick sort of cartoonish avatars in here. And so the cool thing here is you can actually make

5:44 a bunch of fun demos with this. So not only can we do all of this in English, we can actually come in here and we can pick different languages. So if we want to have a cafe and we want to put it in

5:56 a different place, we can actually sort of make this a conversational app for teaching us to speak a different conversation, etc. So you can see here we basically got something where it's

6:08 going to teach me. Let's try Japanese, right? See how that goes. And what I'm going to do is try and have a conversation with her. Hi there. Can you tell me how to order a coffee in

6:18 Japanese? Please say coffee please. >> Is coffee. >> Okay. So, how do I say I would like one coffee?

6:36 >> Say one coffee, please. >> How do I pronounce it? Can you give me the corrections for how I should pronounce it? Repeat after me.

6:56 Okay, so enough of me embarrassing myself not being able to speak Japanese, but you can see here that we can basically set this up to teach us vocabulary to do a whole bunch of

7:07 different things. And we could change it so that we start with something that's really beginner and something that then gets right through to something much more advanced in here. Another thing

7:16 that you can actually do for fun is that you can actually have multiple characters and have them communicate to each other. So here we're going to start a debate over whether pineapple belongs

7:27 on pizza or not. And you can see moderator esteemed guests. Culinary purists often mistake rigidity for tradition, but love and gastronomy thrives on daring unions. To deny the

7:42 pineapple its rightful throne upon the pizza is to deny the very spirit of romance which seeks the unexpected harmony of sweet and savory. Imagine the sundrenched tropics marrying the rustic

7:55 warmth of baked dough. It is not just a topping, Carmen. It is poetry on a crust. >> Quickly it is then. Leo, while I appreciate your poetic vision, culinary

8:06 harmony requires more than just sweet and savory colliding. From a practical standpoint, the excessive moisture and pineapple compromises the structural integrity of the crust, turning a crisp

8:19 base into a soggy mess. >> You are right, moderator. There is wisdom in her words that I must respect. Yet, Carmen, true passion often withstands a few.

8:30 >> Okay, I'm going to stop it there. But you can get a sense there of that these two can actually sort of communicate to each other. So you can have some sort of fun with that. Probably I'd go back and

8:39 actually change the system prompt to make them a little bit more concise for my demo. And it doesn't stop there. You can also do things like where because you can also activate the camera. You

8:49 can then hold up things and have a conversation about them with the avatar. Now, if you want to see a video of me actually explaining the code and going through it a little bit and stuff like

8:58 that and showing you how to get started, etc. I'm going to put the link for that in the description. That's going to be on my second channel. You actually go through and get this all started

9:05 yourself. Okay. So, just to finish off, I would say that while this doesn't have the flexibility that perhaps we would like at the moment, again, this is Google having to be conservative with

9:16 how they do things. They don't want 500 people uploading pictures of Trump and making a Trump avatar or something like that. My guess is there going to be quite a number of safety features around

9:25 that kind of avatar system. You can imagine also that Google's going to be pretty strict about the different use cases for this. If you want to try it out, this is in Google Cloud now. You

9:34 can actually just come in and look at the Gemini live avatar. You can pick from the avatars that they've actually got set up in here. So, you can certainly get a demo of this up for a

9:43 business or to show people how to use it, etc. Now, the pricing for this is going to be pretty pricey coming out. I think the simple fact that this just uses so much compute means that we're

9:54 probably not going to see this get super cheap in the really near term. But it's definitely going to be interesting to see where this goes. And I'd love to hear from people where you see the best

10:02 use cases of this are actually going to be. Let me know in the comments what you think about those. But hopefully it won't be too long before we see an open version of this perhaps from Nvidia or

10:11 from one of the other companies that are actually releasing open models out there as well. Anyway, as always, if you found the video useful, please click like and subscribe, and I will talk to you in the

10:19 next video. Bye for now.