Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

OpenAI’s new GPT-4o model can translate in real-time

Dexerto's profile picture

Dexerto

1,442,534 subscribers

409,678 görüntüleme • 2 yıl önce •via X (Twitter)

Bilim & TeknolojiHaberler & PolitikaOyun
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Jak profil fotoğrafı
Jak2 yıl önce

imma get so many Italian baddies with this

Tolly Censor profil fotoğrafı
Tolly Censor2 yıl önce

Chat GPT-o is out and Duolingo is 4% down.

slushy profil fotoğrafı
slushy2 yıl önce

now put this inside elon musk’s neuralink and then we can all have 200+ iq

Barkin • ברקין • Баркин • 巴尔金 profil fotoğrafı
Barkin • ברקין • Баркин • 巴尔金2 yıl önce

Dozens of startups obliterated

feenin’ profil fotoğrafı
feenin’2 yıl önce

Now I will know why my girl keep screaming “nein” in bed

Barkin • ברקין • Баркин • 巴尔金 profil fotoğrafı
Barkin • ברקין • Баркин • 巴尔金2 yıl önce

But When are they going to be transparent about the sources of your training data? Privacy is important

steph profil fotoğrafı
steph2 yıl önce

impressive

SupahAndre⚡️ profil fotoğrafı
SupahAndre⚡️2 yıl önce

google translate 2.0

ForgetfuIPerson profil fotoğrafı
ForgetfuIPerson2 yıl önce

Will definitely be cool to see how much more this evolves. I’m curious about if AI can reach a point to allow communications between more intelligent life such as orcas and dolphins, and some primates too. Maybe find a way for octopus as well

Alberto profil fotoğrafı
Alberto2 yıl önce

Siri better get it together 😳

Benzer Videolar

OpenAI has just demonstrated its new GPT-4o model doing real-time translations 🤯
1:14

OpenAI has just demonstrated its new GPT-4o model doing real-time translations 🤯

Tom Warren

8,428,791 görüntüleme • 2 yıl önce

OpenAI demos real-time language translation with its latest GPT-4o model.
1:11

OpenAI demos real-time language translation with its latest GPT-4o model.

TechCrunch

7,886,873 görüntüleme • 2 yıl önce

OpenAI’s newly released GPT-4o can not only describe what it sees, such as clothes and facial expressions, but it also can communicate with another GPT-4o
0:55

OpenAI’s newly released GPT-4o can not only describe what it sees, such as clothes and facial expressions, but it also can communicate with another GPT-4o

TechCrunch

28,856 görüntüleme • 2 yıl önce

Say hello to GPT-4o, our new flagship model which can reason across audio, vision, and text in real time: Text and image input rolling out today in API and ChatGPT with voice and video in the coming weeks.
1:22

Say hello to GPT-4o, our new flagship model which can reason across audio, vision, and text in real time: Text and image input rolling out today in API and ChatGPT with voice and video in the coming weeks.

OpenAI

22,830,026 görüntüleme • 2 yıl önce

Is GPT-4o the only tool that can reason across audio, vision and text in real time?… No! So can projects powered $KARRAT
0:39

Is GPT-4o the only tool that can reason across audio, vision and text in real time?… No! So can projects powered $KARRAT

Karrat

58,967 görüntüleme • 2 yıl önce

Dubbing for live events… in real time? 😮 Here’s OpenAI’s new GPT-Realtime-Translate model in action in Vimeo. Those translations are happening completely live. No pre-loaded captions. Live dubbing is one of the many features we’re exploring this year... (Hopefully) more soon. But in the meantime, we just had to show you! Bravo OpenAI Developers 👏
0:51

Dubbing for live events… in real time? 😮 Here’s OpenAI’s new GPT-Realtime-Translate model in action in Vimeo. Those translations are happening completely live. No pre-loaded captions. Live dubbing is one of the many features we’re exploring this year... (Hopefully) more soon. But in the meantime, we just had to show you! Bravo OpenAI Developers 👏

Vimeo

17,010 görüntüleme • 4 ay önce

🧠 OpenAI announced a new model, GPT-4o, which will soon allow real-time conversation with an AI assistant. In a May 13 demo ( OpenAI members showed that the model can provide breathing feedback, tell a story, and help solve a math problem, among other applications.
2:17

🧠 OpenAI announced a new model, GPT-4o, which will soon allow real-time conversation with an AI assistant. In a May 13 demo ( OpenAI members showed that the model can provide breathing feedback, tell a story, and help solve a math problem, among other applications.

CRYPTO JOKER

17,913 görüntüleme • 2 yıl önce

OpenAI just dropped GPT-Realtime-2, Realtime-Translate and Realtime-Whisper. Reason. Translate. Transcribe. In real time.
0:37

OpenAI just dropped GPT-Realtime-2, Realtime-Translate and Realtime-Whisper. Reason. Translate. Transcribe. In real time.

Min Choi

60,081 görüntüleme • 4 ay önce

VITA-1.5 Towards GPT-4o Level Real-Time Vision and Speech Interaction
2:12

VITA-1.5 Towards GPT-4o Level Real-Time Vision and Speech Interaction

AK

31,540 görüntüleme • 1 yıl önce

Introducing GPT-4o, our new model which can reason across text, audio, and video in real time. It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):
5:54

Introducing GPT-4o, our new model which can reason across text, audio, and video in real time. It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):

Greg Brockman

4,362,928 görüntüleme • 2 yıl önce

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.
4:03

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,666,973 görüntüleme • 4 ay önce

Taking talking shop to a whole new level. We just shipped Glean’s real-time voice capability, powered by OpenAI’s newest speech model GPT-Realtime-2. Grounded in the context across your org, it feels like a real AI coworker and can keep up with how work gets finished. In internal evals, GPT-Realtime-2 delivered a 42.9% relative increase in helpfulness over its previous version. Give it a try. It speaks for itself. OpenAIDevs
1:55

Taking talking shop to a whole new level. We just shipped Glean’s real-time voice capability, powered by OpenAI’s newest speech model GPT-Realtime-2. Grounded in the context across your org, it feels like a real AI coworker and can keep up with how work gets finished. In internal evals, GPT-Realtime-2 delivered a 42.9% relative increase in helpfulness over its previous version. Give it a try. It speaks for itself. OpenAIDevs

Glean

16,588 görüntüleme • 4 ay önce

💥 Introducing MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device ✨ Highlights: ~Match GPT-4o-202405 in vision, audio and multimodal live streaming ~End-to-end real-time bilingual audio conversation ~Voice cloning & emotion control ~Advanced OCR & video understanding ~Offline iPad-compatible multimodal live streaming 🔗 Try it out: GitHub: HF: Demo:
6:40

💥 Introducing MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device ✨ Highlights: ~Match GPT-4o-202405 in vision, audio and multimodal live streaming ~End-to-end real-time bilingual audio conversation ~Voice cloning & emotion control ~Advanced OCR & video understanding ~Offline iPad-compatible multimodal live streaming 🔗 Try it out: GitHub: HF: Demo:

OpenBMB

97,844 görüntüleme • 1 yıl önce

The new Qwen 3.5 4B runs incredibly well on M5. The model is close to GPT-4o in benchmarks. Running fully on-device with MLX.
0:20

The new Qwen 3.5 4B runs incredibly well on M5. The model is close to GPT-4o in benchmarks. Running fully on-device with MLX.

Adrien Grondin

230,466 görüntüleme • 6 ay önce

Did you hear? OpenAI's newest model can reason across audio, vision, and text in real time. How does GPT-4o do with math tutoring?🤔 Salman Khan and his son test it on a Khan Academy math problem. You can get AI-powered math tutoring right now with Khanmigo:
3:20

Did you hear? OpenAI's newest model can reason across audio, vision, and text in real time. How does GPT-4o do with math tutoring?🤔 Salman Khan and his son test it on a Khan Academy math problem. You can get AI-powered math tutoring right now with Khanmigo:

Khan Academy

283,895 görüntüleme • 2 yıl önce