正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Voicebox, a new breakthrough generative speech system based on Flow Matching, a new method proposed by Meta AI. It can synthesize speech across six languages, perform noise removal, edit content, transfer audio style & more. More details on this work & examples ⬇️

AI at Meta

840,815 subscribers

445,280 次观看 • 3 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

AI at Meta 的头像

AI at Meta3 年前

Like other generative AI work, Voicebox is able to create high-quality outputs from scratch or modify samples, but instead of images/video, it produces high-quality audio. Unlike autoregressive models, it can modify any part of a given sample — not just the end of a clip.

AI at Meta 的头像

AI at Meta3 年前

Voicebox generalizes across tasks and outperforms single-purpose AI models through in-context learning. It beats the previous state of the art in a number of ways. 💬 Better word error rates 🤝 Improved audio similarity ⏱️ Up to 20x faster performance

AI at Meta 的头像

AI at Meta3 年前

This work represents an important step forward for this field of research. Just as other work has done for images + text, we believe the generalization & scalability of Voicebox could usher in a new era of generative AI for speech — we're excited to continue pushing it forward.

Furkan Gözükara 的头像

Furkan Gözükara3 年前

Will you release source code and models We are looking forward to that Meta ai is the best with clean and easy code release Please release including fine tuning

AI Authority 的头像

AI Authority3 年前

ElevenLabs finally has a real competitor.

bharat 的头像

bharat3 年前

show code or it didnt happen

UneditedMarble 的头像

UneditedMarble3 年前

Now waiting for the code :)

catid (e/acc) 的头像

catid (e/acc)3 年前

Is it open source? I don't see a source release.

𝕏 NiNo 的头像

𝕏 NiNo3 年前

@YannickScholich 🔥

風の民@ 的头像

風の民@3 年前

VOICEVOX

相关视频

Introducing SeamlessM4T, the first all-in-one, multilingual multimodal translation model. This single model can perform tasks across speech-to-text, speech-to-speech, text-to-text translation & speech recognition for up to 100 languages depending on the task. Details ⬇️

Introducing SeamlessM4T, the first all-in-one, multilingual multimodal translation model. This single model can perform tasks across speech-to-text, speech-to-speech, text-to-text translation & speech recognition for up to 100 languages depending on the task. Details ⬇️

AI at Meta

592,782 次观看 • 3 年前

Today we're sharing new progress on our AI speech work. Our Massively Multilingual Speech (MMS) project has now scaled speech-to-text & text-to-speech to support over 1,100 languages — a 10x increase from previous work. Details + access to new pretrained models ⬇️

Today we're sharing new progress on our AI speech work. Our Massively Multilingual Speech (MMS) project has now scaled speech-to-text & text-to-speech to support over 1,100 languages — a 10x increase from previous work. Details + access to new pretrained models ⬇️

AI at Meta

326,883 次观看 • 3 年前

Introducing Meta Omnilingual Automatic Speech Recognition (ASR), a suite of models providing ASR capabilities for over 1,600 languages, including 500 low-coverage languages never before served by any ASR system. While most ASR systems focus on a limited set of languages that are well-represented on the internet, this release marks a major step toward building a truly universal transcription system. 🔗 Learn more:

Introducing Meta Omnilingual Automatic Speech Recognition (ASR), a suite of models providing ASR capabilities for over 1,600 languages, including 500 low-coverage languages never before served by any ASR system. While most ASR systems focus on a limited set of languages that are well-represented on the internet, this release marks a major step toward building a truly universal transcription system. 🔗 Learn more:

AI at Meta

545,079 次观看 • 9 个月前

We're introducing two new transcription models in the API: • GPT-Live-Transcribe: built for low-latency live transcription. • GPT-Transcribe: optimized for asynchronous transcription of completed audio files and batch workloads. Both models better understand context and deliver more accurate transcription on real world audio across accents and languages, including for short phrases, numbers, specialized terminology, and speech with loud background noise.

We're introducing two new transcription models in the API: • GPT-Live-Transcribe: built for low-latency live transcription. • GPT-Transcribe: optimized for asynchronous transcription of completed audio files and batch workloads. Both models better understand context and deliver more accurate transcription on real world audio across accents and languages, including for short phrases, numbers, specialized terminology, and speech with loud background noise.

OpenAI Developers

451,946 次观看 • 1 个月前

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 ➡️

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 次观看 • 2 年前

Aizel Network Sets a New Standard for On-Chain AI. Aizel Network Ever imagined a world where AI can interact across blockchains using natural language? Well, Aizel Network just made it happen with its groundbreaking MCP-based natural language transfer. Learn More! 🧵👇

Aizel Network Sets a New Standard for On-Chain AI. Aizel Network Ever imagined a world where AI can interact across blockchains using natural language? Well, Aizel Network just made it happen with its groundbreaking MCP-based natural language transfer. Learn More! 🧵👇

Gålåxy✴️

27,300 次观看 • 1 年前

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊

Paul Couvert

149,276 次观看 • 7 个月前

🚨 New model alert! Dialog by vibx — a leading text-to-speech model — now runs on GroqCloud™. That means natural-sounding speech with ultra-low latency, making real-time voice applications smoother and more responsive. Learn more & build fast — links in the comments!

🚨 New model alert! Dialog by vibx — a leading text-to-speech model — now runs on GroqCloud™. That means natural-sounding speech with ultra-low latency, making real-time voice applications smoother and more responsive. Learn more & build fast — links in the comments!

Groq Inc

47,474 次观看 • 1 年前

OPANAI 👀: ChatGPT Work arrived as a new AI Agent, along with a completely new app based on Codex Desktop. > Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done. A merge into a Super App is complete 🤖

OPANAI 👀: ChatGPT Work arrived as a new AI Agent, along with a completely new app based on Codex Desktop. > Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done. A merge into a Super App is complete 🤖

🚨 AI News | TestingCatalog

34,254 次观看 • 1 个月前

Introducing Atlas 1. Willow's new frontier speech-to-text model. It outperforms ElevenLabs, Deepgram, OpenAI, and more by a wide margin. Built on the first scalable, human-powered transcription infrastructure ever built for real-time dictation.

Introducing Atlas 1. Willow's new frontier speech-to-text model. It outperforms ElevenLabs, Deepgram, OpenAI, and more by a wide margin. Built on the first scalable, human-powered transcription infrastructure ever built for real-time dictation.

Willow

836,797 次观看 • 5 个月前

Everdome + $DOME are now part of @HumainAssets - a new AI-driven creative engine. Merging web2, web3, humans & AI for the future of content production. More on what we're building in comments ⬇️

Everdome + $DOME are now part of @HumainAssets - a new AI-driven creative engine. Merging web2, web3, humans & AI for the future of content production. More on what we're building in comments ⬇️

Humain Web3

15,802 次观看 • 1 年前

New app update 🫰 A new discoverability page for portfolios is here You can now scroll between the different portfolios based on pilot, performance, launch date & more This is our first version of this page so be on the lookout for more to come soon

New app update 🫰 A new discoverability page for portfolios is here You can now scroll between the different portfolios based on pilot, performance, launch date & more This is our first version of this page so be on the lookout for more to come soon

Autopilot

319,327 次观看 • 1 年前

🔥 DROP 002 IS COMING🔥 401 animated NFTs each backed by a luxury physical HOODIE💎 1 VIRGO style, 4 unique colorways, & 3 new pillars of tech: 🤖 AI-generated art 📲 NFC-chipped 👕 Matching AR wearables ⚡️MINTING IN MARCH⚡️ Website for more details 👉

🔥 DROP 002 IS COMING🔥 401 animated NFTs each backed by a luxury physical HOODIE💎 1 VIRGO style, 4 unique colorways, & 3 new pillars of tech: 🤖 AI-generated art 📲 NFC-chipped 👕 Matching AR wearables ⚡️MINTING IN MARCH⚡️ Website for more details 👉

Cult & Rain

61,145 次观看 • 3 年前

🚀 New project! Launching Sturdy's brand new portfolio - had a blast on that one, got to work on more purposeful & refined animations. There are a few things to discover, check it out! Back-end by Ingamana Design by Fix Studio 👉 🔊 SOUND ON

Thom Aufresne

43,098 次观看 • 3 年前

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from Joelle Pineau. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from Joelle Pineau. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

AI at Meta

150,435 次观看 • 1 年前

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

Matthias Niessner

22,641 次观看 • 1 年前

Introducing the new Pixel 10a. It has everything you need — like a completely flat, durable design, more battery life, advanced AI tools and a best-in-class camera system* — for just $499. *Among smartphones under $500 (MSRP) in the U.S. Based on third-party evaluation of Pixel 10a.

Introducing the new Pixel 10a. It has everything you need — like a completely flat, durable design, more battery life, advanced AI tools and a best-in-class camera system* — for just $499. *Among smartphones under $500 (MSRP) in the U.S. Based on third-party evaluation of Pixel 10a.

Google

84,511 次观看 • 6 个月前

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.

AI at Meta

85,975 次观看 • 1 年前