OpenAI Introduces Combined Text-audio-vision Chatbot model, GPT-4o
Enjoyed this video? Join my Locals community for exclusive content at
keneci.locals.com!
21 days ago
69
According to OpenAI blog post, GPT-4omni accepts as input any combination of text, audio, and image and generates any combination of text, audio, and image outputs. It can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time(opens in a new window) in a conversation
Loading comments...
-
1:55
Keneci
4 days agoTrump Slams Judge After Hush Money Guilty Verdict By Jury
331 -
LIVE
Matt Kohrs
3 hours agoGameStop Squeeze Saga, Breaking Market News & Live Trading || The MK Show
2,087 watching -
1:28:36
Game On!
12 hours agoJustin Jefferson Gets Paid More Than Crickett! | Sports Morning Espresso Shot
13.2K3 -
5:07
Chrissy Clark
16 hours agoMan Spent $14K To Become A Dog, Regrets His Choice In Animal…
22.8K70 -
10:23
TENET Media
20 hours agoElection Rigging & Lawfare: Should We Still Believe In The System? | Benny Johnson
28.4K46 -
19:11
NC Dirt Hunter
1 day agoLeft behind in a Civil War Foxhole. Several very rare finds with the Minelab Manticore
27.7K2 -
1:11
Michael Heaver
18 hours agoNigel Farage Starts Political EARTHQUAKE
30.1K18 -
18:57
Crypto Crew University
1 day agoWARNING: BITCOIN JUST DID THIS – GET READY
23.3K13 -
10:05
DEADBUGsays
1 day agoJason Thornberg, The Dumpster Killer | DEADBUG'S Bedtime Stories #7
24.1K4 -
1:33:21
World Nomac
18 hours ago$1,500 gets you THIS in LUXURY Bangkok Thailand 🇹ðŸ‡
23.2K4