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。

How does voice AI correctly replicate laughs, signs, and whispers? Our research team developed NVAlign, a new training method that uses a second model to listen for sounds like laughter and feed that feedback into speech-generation training. Here’s how it works. 👇

Bland

22,895 subscribers

393,870 次观看 • 7 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Bland 的头像

Bland7 天前

Checkout @pipecat_ai's live demo of our new voice model.

Alice The Ai Expert 的头像

Alice The Ai Expert6 天前

Incredible breakthrough NVAlign making AI sound truly human with real laughs and whispers is next level!

Bland 的头像

Bland6 天前

You wait until we start making it rap…

Max Gibbons 的头像

Max Gibbons7 天前

Love to see the Bland guy branching out

Aaliya 的头像

Aaliya7 天前

amazing teaching voice models to catch laughs, sighs and whispers makes the output feel much more natural.

Abdul Shakoor 的头像

Abdul Shakoor7 天前

This is amazing will love to give it a try

Bland 的头像

Bland6 天前

10/10 method. Would recommend.

Agentik 的头像

Agentik6 天前

training a second model just to catch laughs is a neat loop. does that feedback run only at train time, or also while generating?

Farlane 的头像

Farlane7 天前

This is what makes voice AI feel genuinely human. It has to learn the sounds between the words.

Bland 的头像

Bland6 天前

*coughs* facts.

相关视频

Google just did the unthinkable. They built a voice search model that doesn’t understand words it understands intent. It’s called Speech-to-Retrieval (S2R), and it might mark the death of speech-to-text forever. Here’s how it works (and why it matters way more than it sounds) ↓

Google just did the unthinkable. They built a voice search model that doesn’t understand words it understands intent. It’s called Speech-to-Retrieval (S2R), and it might mark the death of speech-to-text forever. Here’s how it works (and why it matters way more than it sounds) ↓

Chris Laub

746,502 次观看 • 1 年前

🤔What does it take to train an omni world model from scratch? 📽️Petabytes of video. 6⃣pipeline stages. And every improvement in data quality pays off twice when you're training a model that both generates and understands video. Our Reka Labs' data team on how it works → #PhysicalAI #WorldModels #AI #RekaLabs

🤔What does it take to train an omni world model from scratch? 📽️Petabytes of video. 6⃣pipeline stages. And every improvement in data quality pays off twice when you're training a model that both generates and understands video. Our Reka Labs' data team on how it works → #PhysicalAI #WorldModels #AI #RekaLabs

Reka

15,316 次观看 • 3 个月前

Introducing `OpenDeepResearcher` 🌎 An open-source AI agent that does comprehensive research for you. Just provide a topic, and the AI will go off, do research, and return a comprehensive report. How it works:

Introducing `OpenDeepResearcher` 🌎 An open-source AI agent that does comprehensive research for you. Just provide a topic, and the AI will go off, do research, and return a comprehensive report. How it works:

Matt Shumer

455,399 次观看 • 1 年前

We just shipped something nobody else has. Our STT API doesn't just transcribe, it returns a full voice profile in the same response: emotion, accent, age, pitch, style, each with a confidence score, all in one call. When you feed that into our Realtime API, the LLM decides not just what to say but how to say it. It adds steering tags that our TTS-2 model picks up and uses to guide how it speaks. So, if a user sounds frustrated, the voice responds with empathy. If they're excited, it matches that energy. Here's our very own Clint McLean walking you through how the full pipeline works:

Inworld AI

250,703 次观看 • 5 个月前

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!

Andy Jassy

155,926 次观看 • 1 年前

You can now turn images into explorable 3D worlds. Locally. For free. The method involves piloting a virtual 360 degree drone through your scene to map out your world and generate a synthetic dataset for gaussian splat training. Here is how it works 👇

You can now turn images into explorable 3D worlds. Locally. For free. The method involves piloting a virtual 360 degree drone through your scene to map out your world and generate a synthetic dataset for gaussian splat training. Here is how it works 👇

Mickmumpitz

54,325 次观看 • 1 个月前

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Inworld AI

327,778 次观看 • 5 个月前

“NeuralGCM is a new kind of atmospheric model. We feel it has the potential to transform how we understand climate.” ☀️ Learn how our Research team combines physics-based modeling and #AI to reveal a possible new way to build climate models. →

“NeuralGCM is a new kind of atmospheric model. We feel it has the potential to transform how we understand climate.” ☀️ Learn how our Research team combines physics-based modeling and #AI to reveal a possible new way to build climate models. →

Google AI

32,005 次观看 • 2 年前

One of these voice clones *actually* sounds like the original. That’s because Mirage audio generates more expressive output than other models on the market. Our research team built Mirage audio to create more realistic voices. Launching today, this new model solves 3 common challenges in AI audio: 1. It preserves the original speaker’s accent 2. The performance feels dynamic, not flat 3. Delivery matches how people really speak Thanks to our frontier AI research, our voice clone feature preserves the little details that make your voice unique. So your voice actually sounds like you.

One of these voice clones actually sounds like the original. That’s because Mirage audio generates more expressive output than other models on the market. Our research team built Mirage audio to create more realistic voices. Launching today, this new model solves 3 common challenges in AI audio: 1. It preserves the original speaker’s accent 2. The performance feels dynamic, not flat 3. Delivery matches how people really speak Thanks to our frontier AI research, our voice clone feature preserves the little details that make your voice unique. So your voice actually sounds like you.

Mirage

14,946 次观看 • 10 个月前

We show how to turn an old TV into a Smart TV using only a USB cable and a smartphone with a simple method that works on any television model

We show how to turn an old TV into a Smart TV using only a USB cable and a smartphone with a simple method that works on any television model

Fit_Fusion

80,361 次观看 • 10 个月前

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

PlayAI

105,686 次观看 • 2 年前

How did a tiny, scrappy team build one of the most powerful AI voice models? In a deep dive with Sesame CTO Ankit Kumar and a16z's Anjney Midha, we explore how Sesame is pushing the boundaries of AI conversation, why it open-sourced its speech generation model, and the power of small teams to outdo much larger AI labs on product focus. A part of their secret: a relentless focus on real-time, natural conversations over raw intelligence, and a deep commitment to voice, personality, and user experience. By opening up its speech generation model, Sesame is paving the way for even more breakthroughs in AI-native conversation 👇

How did a tiny, scrappy team build one of the most powerful AI voice models? In a deep dive with Sesame CTO Ankit Kumar and a16z's Anjney Midha, we explore how Sesame is pushing the boundaries of AI conversation, why it open-sourced its speech generation model, and the power of small teams to outdo much larger AI labs on product focus. A part of their secret: a relentless focus on real-time, natural conversations over raw intelligence, and a deep commitment to voice, personality, and user experience. By opening up its speech generation model, Sesame is paving the way for even more breakthroughs in AI-native conversation 👇

a16z

29,930 次观看 • 1 年前

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:

The new Factory software AI agents just combined OpenAI’s Codex, Devin, and Cursor into one product. They are fully autonomous agents called Droids that perform deep code research, technical docs, and do autonomous end-to-end coding. Here’s how it works (with real examples)👇:

Alvaro Cintas

94,884 次观看 • 1 年前

Listen to our Artificial Intelligence voice agent booking a service call after 6 weeks of training. Our AI partner is delivering Agentic AI tools that will be a game changer... More than just "voice intake". The next generation of productivity, marketing + CX enhancements...

Listen to our Artificial Intelligence voice agent booking a service call after 6 weeks of training. Our AI partner is delivering Agentic AI tools that will be a game changer... More than just "voice intake". The next generation of productivity, marketing + CX enhancements...

Chris Hoffmann

99,304 次观看 • 1 年前

What is a generalisable model? A model that can adapt to previously unseen data. How does that translate to self-driving? An AI driver that can adapt to any vehicle, and drive in any city, in any weather. What does that look like in practice? 👇

What is a generalisable model? A model that can adapt to previously unseen data. How does that translate to self-driving? An AI driver that can adapt to any vehicle, and drive in any city, in any weather. What does that look like in practice? 👇

Wayve

50,824 次观看 • 3 年前

So helped me to unlock the voice now it works! It's trained on my Lex Fridman podcast It's 99% perfect but the training data apparently still has some Lex "hummm" sounds in it that sometimes show up I think they call this "crosstalk" and it's hard to remove with AI so I think there's no other choice than to listen to the 1 hour of training data and remove those bits and re-train But then we have a good AI model to turn my book MAKE into an audio book without having to read it for hours/days/weeks

So helped me to unlock the voice now it works! It's trained on my Lex Fridman podcast It's 99% perfect but the training data apparently still has some Lex "hummm" sounds in it that sometimes show up I think they call this "crosstalk" and it's hard to remove with AI so I think there's no other choice than to listen to the 1 hour of training data and remove those bits and re-train But then we have a good AI model to turn my book MAKE into an audio book without having to read it for hours/days/weeks

@levelsio

169,787 次观看 • 1 年前