# Add Me V2 Launch: Real-Time AI Avatars from One Image - Original post: https://www.twitter.com/i/status/2118017931519078609 - Source account: [@yuchenping](https://x.com/yuchenping) - Source language: English - Duration: 2:41 - Published: 2026-11-05 - Canonical URL: https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image ## Transcript [0:01](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=1) Hey, uh, is this what we're launching? Hey, I'm right here. [0:04](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=4) Oh, yeah, that's our Add Me V2. Let me- let me talk to it. [0:10](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=10) Chen Ping, are you shooting the launch video right now? [0:14](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=14) Uh, yes, I am. Hey, take a look at our set. [0:16](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=16) What do you think? [0:22](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=22) Yeah. That's a lot of lights for one guy in a chair. [0:26](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=26) Yeah, I know, right? Are you at least going to tell them I run on the most realistic avatar model in the world? [0:34](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=34) Uh, I will, but that's not the point, and let me explain. [0:38](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=38) Hey, I'm Chen Ping, CEO of Add Manity. Last time, we sold our AR company to Google. [0:44](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=44) Today, we're launching Add Me V2, our state-of-the-art real-time avatar model. [0:50](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=50) It creates an incredibly lifelike avatar you can talk to from just one image and 10 seconds of audio. [0:59](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=59) For two years, we've worked on one question: What would it take for us to sit face to face with an AI and feel like someone is actually there? [1:08](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=68) Turns out, looking human was never the point. [1:11](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=71) It's never about fooling anyone into thinking this AI is a person. [1:15](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=75) What matters is whether you enjoy talking to it, human-looking, a toy robot, or a cartoon animal. [1:23](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=83) To do that, we built two models: a body and a brain. [1:27](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=87) Add Me V2 is the body. It's a real-time video foundation model that runs live. [1:34](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=94) Causer is the brain, a model that brings context and behavior into the voice, the body, and the response. [1:40](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=100) That's what makes it lifelike. [1:44](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=104) To build with Add Me V2, copy/paste one link into your favorite coding agent, and it sets up everything for you. [1:51](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=111) Then, ship it to any platform. [1:55](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=115) And it's not just for video calls. For example, you can put a DJ into your music app, train your sales team with a tough buyer, make learning a new subject fun, or guide every visitor through your museum, and even generate whole worlds. [2:10](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=130) At its core, Add Me V2 is a video foundation model. [2:13](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=133) That means besides avatars, it can also generate regular video clips, just like C Dance or One. [2:20](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=140) The difference is that to generate a 10-second video, C Dance takes minutes and dollars, while Add Me V2 does it in seconds for pennies. [2:30](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=150) That's up to 50 times faster and up to 100 times cheaper. [2:34](https://www.translate.mom/transcript/JAL1E10OSza6/en/add-me-v2-launch-real-time-ai-avatars-from-one-image?t=154) Add Me V2 is live today. We can't wait to see what you build.