Загрузка видео...

Не удалось загрузить видео

На главную

SeamlessStreaming is an AI translation model that can deliver state-of-the-art results on streaming translation with <2 seconds of latency. One core piece of our latest Seamless Communication research work by teams at FAIR. More on this project ➡️

AIatMeta's profile picture

AI at Meta

838,735 subscribers

472,731 просмотров • 2 лет назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля DebateHimBro
DebateHimBro2 лет назад

Is it real-time translation, or a Google-like Gemini demo?

Фото профиля AI at Meta
AI at Meta2 лет назад

Try the demo for yourself on @huggingface ⬇️

Фото профиля Mark Zuckerberg - CEO of Facebook - Parody
Mark Zuckerberg - CEO of Facebook - Parody2 лет назад

Very good! Let's get the latency even lower

Фото профиля Fran D' Agostino
Fran D' Agostino2 лет назад

Is a commercial license planed?

Фото профиля Swamy G
Swamy G2 лет назад

This will be a game changer when it's integrated into WhatsApp. Finally my mom can understand my gf and vice versa.

Фото профиля Llamar
Llamar2 лет назад

Can't wait until AI auto-fills what I am about to say

Фото профиля Furkan Gözükara
Furkan Gözükara2 лет назад

even whisper transcription making so much errors. still not very dependable

Фото профиля Blizado
Blizado2 лет назад

Breaking language barriers is really a very good goal. But first it must be very good and make as less errors as possible. Wrong words can start a war. Words can be very powerful.

Фото профиля Manav Agrawal
Manav Agrawal2 лет назад

Haven't tested yet but can AI projects like this be used for critical conversations?

Фото профиля D@RWIN
D@RWIN2 лет назад

Can we use it to translate text-to-text on large documents? say, documents over 50K tokens?

Похожие видео

Last week we introduced SeamlessStreaming — an AI translation model that can deliver streaming translation with <2 seconds of latency. One of the core pieces of our recent Seamless Communication announcement. More details on this work ➡️
2:53

Last week we introduced SeamlessStreaming — an AI translation model that can deliver streaming translation with <2 seconds of latency. One of the core pieces of our recent Seamless Communication announcement. More details on this work ➡️

AI at Meta

71,513 просмотров • 2 лет назад

Today we're sharing the next milestone in our Seamless Communication research — a new family of AI translation models that preserve expression and deliver near-real time streaming translations. More on this new work ➡️ More on the individual models 🧵
2:53

Today we're sharing the next milestone in our Seamless Communication research — a new family of AI translation models that preserve expression and deliver near-real time streaming translations. More on this new work ➡️ More on the individual models 🧵

AI at Meta

728,765 просмотров • 2 лет назад

Yesterday we introduced SeamlessExpressive — a new model that preserves unique vocal styles & expression for speech translation, built on our SeamlessM4T v2 foundation model. More details on the family of Seamless Communication models ➡️
2:36

Yesterday we introduced SeamlessExpressive — a new model that preserves unique vocal styles & expression for speech translation, built on our SeamlessM4T v2 foundation model. More details on the family of Seamless Communication models ➡️

AI at Meta

189,972 просмотров • 2 лет назад

10 years of FAIR. 10 years of advancing the state of the art in AI through open research. We're celebrating the 10th anniversary of Meta's Fundamental AI Research team and continuing that legacy by sharing our work on three exciting new research projects today. Details below 🧵
1:12

10 years of FAIR. 10 years of advancing the state of the art in AI through open research. We're celebrating the 10th anniversary of Meta's Fundamental AI Research team and continuing that legacy by sharing our work on three exciting new research projects today. Details below 🧵

AI at Meta

450,416 просмотров • 2 лет назад

Our latest work on structures of translation initiation complexes trapped by natural product inhibitors kasugamycin, edeine and GE81112 is out in the Biorxiv…
0:28

Our latest work on structures of translation initiation complexes trapped by natural product inhibitors kasugamycin, edeine and GE81112 is out in the Biorxiv…

WilsonLab

13,068 просмотров • 1 год назад

New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details ➡️ Demo on Hugging Face ➡️ Building on our previous work on CoTracker, this new model demonstrates impressive tracking results where points can be tracked for a long time even when they're occluded or leave the field of view. CoTracker3 achieves state-of-the-art, outperforming all recent point tracking approaches on standard benchmarks — often by a substantial margin. We've released the research paper, code and a demo on Hugging Face — along with models available under an A-NC license to support further research in this space.
0:27

New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details ➡️ Demo on Hugging Face ➡️ Building on our previous work on CoTracker, this new model demonstrates impressive tracking results where points can be tracked for a long time even when they're occluded or leave the field of view. CoTracker3 achieves state-of-the-art, outperforming all recent point tracking approaches on standard benchmarks — often by a substantial margin. We've released the research paper, code and a demo on Hugging Face — along with models available under an A-NC license to support further research in this space.

AI at Meta

219,026 просмотров • 1 год назад

🎶Welcome to the world of Harmony, a platform where seamless communication knows no boundaries! Let's dive into how we're revolutionizing the way you connect by breaking down language barriers with the power of our built-in AI translation. 🚀
0:35

🎶Welcome to the world of Harmony, a platform where seamless communication knows no boundaries! Let's dive into how we're revolutionizing the way you connect by breaking down language barriers with the power of our built-in AI translation. 🚀

Harmony

127,280 просмотров • 1 год назад

Quick demo of the voice to voice translation between English and Twi that you can try today on our web app. This one is from the perspective of a tourist visiting Ghana and needing to get around. Brought to you by the amazing team at Ghana Natural Language Processing (NLP) Algorine Research
1:29

Quick demo of the voice to voice translation between English and Twi that you can try today on our web app. This one is from the perspective of a tourist visiting Ghana and needing to get around. Brought to you by the amazing team at Ghana Natural Language Processing (NLP) Algorine Research

Paul Azunre

165,124 просмотров • 2 лет назад

We previously shared our research on Layer Skip, an end-to-end solution for accelerating LLMs from researchers at Meta FAIR. It achieves this by executing a subset of an LLM’s layers and utilizing subsequent layers for verification and correction. We’re now releasing inference code and fine-tuned checkpoints for this work. Model weights on Hugging Face ➡️ More details ➡️ We hope that releasing this work will open up new areas of experimentation and innovative new research in optimization and interpretability.
1:12

We previously shared our research on Layer Skip, an end-to-end solution for accelerating LLMs from researchers at Meta FAIR. It achieves this by executing a subset of an LLM’s layers and utilizing subsequent layers for verification and correction. We’re now releasing inference code and fine-tuned checkpoints for this work. Model weights on Hugging Face ➡️ More details ➡️ We hope that releasing this work will open up new areas of experimentation and innovative new research in optimization and interpretability.

AI at Meta

156,618 просмотров • 1 год назад

I couldn’t be more excited to share our latest AI research breakthrough. We call it Meta Movie Gen and it’s a collection of state-of-the-art models that combine to deliver the most advanced video generation capability ever created. Check it out:
1:14

I couldn’t be more excited to share our latest AI research breakthrough. We call it Meta Movie Gen and it’s a collection of state-of-the-art models that combine to deliver the most advanced video generation capability ever created. Check it out:

Ahmad Al-Dahle

356,704 просмотров • 1 год назад

📣 The Schedule has been set! 🔥 Excited to share that the dates with our project management teams are set for the release of our core products. 1. AI-Marketplace: June 2. GPU Marketplace: June 3. Solidus Ai Tech Data Centre: July ➡️ Learn more:
1:10

📣 The Schedule has been set! 🔥 Excited to share that the dates with our project management teams are set for the release of our core products. 1. AI-Marketplace: June 2. GPU Marketplace: June 3. Solidus Ai Tech Data Centre: July ➡️ Learn more:

AITECH CLOUD NETWORK

243,919 просмотров • 2 лет назад

Introducing Veo 2, our new, state-of-the-art video model (with better understanding of real-world physics & movement, up to 4K resolution). You can join the waitlist on VideoFX. Our new and improved Imagen 3 model also achieves SOTA results, and is coming today to 100+ countries in ImageFX.
0:40

Introducing Veo 2, our new, state-of-the-art video model (with better understanding of real-world physics & movement, up to 4K resolution). You can join the waitlist on VideoFX. Our new and improved Imagen 3 model also achieves SOTA results, and is coming today to 100+ countries in ImageFX.

Sundar Pichai

4,573,660 просмотров • 1 год назад

Very excited to share what our research team at Covariant has been working on: RFM-1, our latest Robotics Foundation Model. Built on top of high-quality multimodal data the Covariant robotics fleet has collected over the years, this project embodies our commitment to pushing the boundaries of how AI can interact with and understand the physical world. We're eager to share this milestone with the community and invite feedback and collaboration. Read more at
0:40

Very excited to share what our research team at Covariant has been working on: RFM-1, our latest Robotics Foundation Model. Built on top of high-quality multimodal data the Covariant robotics fleet has collected over the years, this project embodies our commitment to pushing the boundaries of how AI can interact with and understand the physical world. We're eager to share this milestone with the community and invite feedback and collaboration. Read more at

Rocky Duan

31,833 просмотров • 2 лет назад

Still buzzing from our live #COMPUTEX demos! Watching Chang Liu speak Mandarin while an AMD AI PC translated her words into English — live, on-device, with zero cloud assistance — was a true milestone. This demo proved real-time, voice-to-voice translation can run privately and with low latency on a single Ryzen AI system. Huge thanks to Nick Ni for orchestrating this seamless demo, Chang for her perfect delivery, and the entire AMD AI Group for turning months of hard work into that unforgettable moment. Why it matters: • Latency so low it feels natural — conversations flow smoothly • Data stays on-device — privacy uncompromised This is what next-gen Ryzen AI processors unlock — and it’s only the beginning. We’re committed to improving accuracy and reducing latency as we push the boundaries of what’s possible.
1:12

Still buzzing from our live #COMPUTEX demos! Watching Chang Liu speak Mandarin while an AMD AI PC translated her words into English — live, on-device, with zero cloud assistance — was a true milestone. This demo proved real-time, voice-to-voice translation can run privately and with low latency on a single Ryzen AI system. Huge thanks to Nick Ni for orchestrating this seamless demo, Chang for her perfect delivery, and the entire AMD AI Group for turning months of hard work into that unforgettable moment. Why it matters: • Latency so low it feels natural — conversations flow smoothly • Data stays on-device — privacy uncompromised This is what next-gen Ryzen AI processors unlock — and it’s only the beginning. We’re committed to improving accuracy and reducing latency as we push the boundaries of what’s possible.

Jack Huynh

14,634 просмотров • 1 год назад

🚨NEW: CHATGPT LIVE VOICE MODEL NOW DELIVERS REAL-TIME CONVERSATIONAL TRANSLATION Built on a full-duplex architecture, GPT-Live is a new generation of voice models that can listen and speak simultaneously, enabling more natural human-AI interactions. The breakthrough unlocks fluid back-and-forth conversations, real-time translation, and a far more human sense of timing and context.
2:32

🚨NEW: CHATGPT LIVE VOICE MODEL NOW DELIVERS REAL-TIME CONVERSATIONAL TRANSLATION Built on a full-duplex architecture, GPT-Live is a new generation of voice models that can listen and speak simultaneously, enabling more natural human-AI interactions. The breakthrough unlocks fluid back-and-forth conversations, real-time translation, and a far more human sense of timing and context.

Coin Bureau

29,085 просмотров • 1 месяц назад

"We've started to work on an AI project that is deeply intertwined with the identity layer we're building" Lou spills the beans in our latest CyberLink!
27:51

"We've started to work on an AI project that is deeply intertwined with the identity layer we're building" Lou spills the beans in our latest CyberLink!

XBorg

17,705 просмотров • 1 год назад

"The State Of Bitcoin Core" by Mike Schmidt of Brink "There's a paradox in Bitcoin Core in that... the code is transparent, but understanding of the code is scattered in IRC and other places" 100 slides on the who & what of the Bitcoin Core Project project.
25:08

"The State Of Bitcoin Core" by Mike Schmidt of Brink "There's a paradox in Bitcoin Core in that... the code is transparent, but understanding of the code is scattered in IRC and other places" 100 slides on the who & what of the Bitcoin Core Project project.

OPNEXT 2026

15,323 просмотров • 3 месяцев назад

The release of my new project, OVERLOAD, will take place on Art Blocks on Monday at 12:00 PM CDT. An article about the project can be found here: And this is a thread of my thoughts on the project.
0:36

The release of my new project, OVERLOAD, will take place on Art Blocks on Monday at 12:00 PM CDT. An article about the project can be found here: And this is a thread of my thoughts on the project.

Shvembldr

10,449 просмотров • 3 лет назад

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.
0:30

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

AI at Meta

2,265,716 просмотров • 1 год назад