@GoogleDeepMind's #Veo3 is generating a ton of buzz... and for good reason. I've been playing with it over the past couple days, really wanting to test the ability to represent people, generate voices, different situations, etc.
It's been a lot of fun. It's also been a bit worrying.
Make no mistake about it, Veo 3 crazy good in helping people unlock their power for for both storytelling and for dangerous misuse (scams, disinformation, deepfakes, conspiracy bait).
Here's my test: A fake documentary about ham sandwiches that come to life and disrupt society. This was a great way to create fun and safe interviews, news segments, etc. it’s ridiculous and fun. But it gets the point across.
Some details:
-- Total runtime: 3 min
-- Every clip, character, voice, and sound effect = Veo 3
-- Only outside elements: music bed + trailer-style transitions
-- I did quite a bit of editing for pacing and creative direction
I was about to add some elements to further dirty-up the 'archival footage', but thought you might enjoy seeing a less produced version before I add in those elements. This illustrates just how good Veo 3 is on it's own and before heavier post production.
Hope you enjoy it!
Tagging a few of my fav creators for their visibility: @RachelTobac@TheoMediaAI@mreflow@MattVidPro@wesroth@RosalesReport@RansomWear1@_Freakyclown_
After Google acquired my AR startup, I started thinking about the next interface, this time for AI. Text and voice work fine, just like DOS did before the Mac. But nothing’s more intuitive than face to face.
After two years of research, today we’re launching Atmee v2: a real-time avatar model that makes live video agents feel truly life-like.
• Any character from 1 image + 10s of audio
• Contextual expressions, gestures, even interacting with the environment
• Live video calls, voice only, or video generation
At its core, Atmee v2 is a video foundation model, it can render anything, but it’s built to excel at characters, which is what video models like Seedance 2.5 and Wan 3.0 are mostly used for. In comparison:
Atmee v2
• Up to 50x faster
• 10-100x cheaper
Build tutors, sales coaches, support agents, companions, game characters, even whole living worlds. The interface after text and voice starts today.
@RachelTobac 💯— sadly, our industry is cursed to repeat the security sins of our past. Seems like we have decades of “lessons learned” docs that gather virtual dust rather than become part of better informed processes.
HEADS UP, FLORIDA! If you're in IT, or concerned at all about #CyberSecurity, You'll want to be at our one-day "Surviving the Scampocalypse" event with me and @PerryCarpenter. Tickets on sale now, event March 2nd: https://t.co/EjTc4rjmC9
New Modern Rogue episode is a treat! @PerryCarpenter made an extra-scammy Robo-Brian that tried to swindle my parents. It worked, too! https://t.co/1Vz1PjLiI9
We used to argue over blurry ghost photos. Now we argue over videos that never happened.
Oct 2, 7pm ET: @PerryCarpenter on deepfakes and the future of trust.
Register free: https://t.co/DJqfaviF7b
Data breaches are like silent farts in a crowded office…
Unnoticed at first. Then suddenly… everyone’s affected.
That’s the premise behind a quick security awareness PSA I whipped up yesterday.
🧠 Script: my overly-tired, yet surprisingly juvenile brain
📣 Advice: The "Core 4" security behaviors from @StaySafeOnline and @CISAgov / @CISACyber
🎬 Video clips & voices: @GoogleDeepMind's VEO-3
🎙️ Voiceover: @elevenlabs custom voice using V3
🎵 Music & SFX: @envato Elements subscription
✂️ Editing: @descript
It’s short, weird, and (hopefully) memorable.
Enjoy!