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。

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

25,670 subscribers

746,030 次观看 • 9 个月前 •via X (Twitter)

科学技术新闻政治教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

This is the most realistic voice cloning I’ve seen. It doesn’t just copy the voice — it captures tone, rhythm, and emotion. Built with Hume’s EVI 3 speech-to-speech model and it even works with external LLMs like Groq, Anthropic, and DeepSeek. Just listen to this Ricky Gervais voice clone — same voice, same feeling 🎧 Try talking to the clone yourself →

This is the most realistic voice cloning I’ve seen. It doesn’t just copy the voice — it captures tone, rhythm, and emotion. Built with Hume’s EVI 3 speech-to-speech model and it even works with external LLMs like Groq, Anthropic, and DeepSeek. Just listen to this Ricky Gervais voice clone — same voice, same feeling 🎧 Try talking to the clone yourself →

Arsalan

26,923 次观看 • 1 年前

This is the most realistic Voice CLONING I’ve ever heard⚠️ It is not just the sound — it mimics rhythm, tone, and even how someone speaks. And it’s speech-to-speech—no text in between.

This is the most realistic Voice CLONING I’ve ever heard⚠️ It is not just the sound — it mimics rhythm, tone, and even how someone speaks. And it’s speech-to-speech—no text in between.

Dipti Sharma

41,193 次观看 • 1 年前

🚨 BREAKING: Claude just got a major upgrade and it changes how you do research. Anthropic just launched Research + Google Workspace integration. Here’s why it matters (and how it works): 🧵

🚨 BREAKING: Claude just got a major upgrade and it changes how you do research. Anthropic just launched Research + Google Workspace integration. Here’s why it matters (and how it works): 🧵

Brendan Jowett

46,887 次观看 • 1 年前

I just built a chicken waterer that doesn’t freeze and is always clean. Here’s how it works.

I just built a chicken waterer that doesn’t freeze and is always clean. Here’s how it works.

Justin Rhodes

10,922 次观看 • 4 个月前

Can you accurately transcribe fast speech? Tested ' new Speech-to-Text model (Scribe) with Eminem's "Rap God" (4.28 words/sec!) & it nailed it. Great quality and supports 99+ languages.

Can you accurately transcribe fast speech? Tested ' new Speech-to-Text model (Scribe) with Eminem's "Rap God" (4.28 words/sec!) & it nailed it. Great quality and supports 99+ languages.

Addy Osmani

108,722 次观看 • 1 年前

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Aoden Teo

5,146,007 次观看 • 1 个月前

Zayn giving a heartfelt speech to the fans last night: “I wrote all these words.. hearing you sing lyrics that i wrote myself..It was way harder than I thought it was gonna be to write a whole record, but we did it. It feels good to hear you sing the words honestly, it’s like a dream! It’s crazy!” 🥹

Zayn giving a heartfelt speech to the fans last night: “I wrote all these words.. hearing you sing lyrics that i wrote myself..It was way harder than I thought it was gonna be to write a whole record, but we did it. It feels good to hear you sing the words honestly, it’s like a dream! It’s crazy!” 🥹

Zayn Malik Updates

65,403 次观看 • 1 年前

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →

AssemblyAI

1,017,880 次观看 • 1 年前

What if voice AI could understand context, intent, and emotion — not just words? 🎙️ Meet Seed Speech 2.0. A new speech AI stack designed for natural, expressive conversations — with major upgrades in both text-to-speech (TTS) and speech recognition (ASR). Built for developers and creators who want natural conversational speech. What’s inside: - Natural and expressive speech generation - Prompt-controlled emotion and tone - High-accuracy multilingual recognition - Strong contextual reasoning Built for: 🎧 Voice content creation 🤖 AI assistants ☎️ Customer service 🎬 Dubbing & subtitling 📊 Audio-video analysis Voice AI built for expression, accuracy, and understanding. Try it now → Read more about Seed Speech here → #SeedSpeech #VoiceAI #SpeechAI #AI

What if voice AI could understand context, intent, and emotion — not just words? 🎙️ Meet Seed Speech 2.0. A new speech AI stack designed for natural, expressive conversations — with major upgrades in both text-to-speech (TTS) and speech recognition (ASR). Built for developers and creators who want natural conversational speech. What’s inside: - Natural and expressive speech generation - Prompt-controlled emotion and tone - High-accuracy multilingual recognition - Strong contextual reasoning Built for: 🎧 Voice content creation 🤖 AI assistants ☎️ Customer service 🎬 Dubbing & subtitling 📊 Audio-video analysis Voice AI built for expression, accuracy, and understanding. Try it now → Read more about Seed Speech here → #SeedSpeech #VoiceAI #SpeechAI #AI

BytePlus

19,740 次观看 • 3 个月前

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

ElevenLabs

113,343 次观看 • 2 年前

OpenAI's S2S preview is polished but it still thinks in steps. Speech → text → model → text → speech. That's not how humans converse. Introducing Hydra. A native speech-to-speech model that doesn't wait for turn-taking, doesn't flatten emotion into text, and doesn't break when you interrupt it mid-sentence. Hydra reasons asynchronously, speaks and listens simultaneously, and preserves emotion because it never leaves the audio domain. It's still in beta, but the shift is obvious. If you want early access, the link is in the comments. Here's a preview of what that looks like -

OpenAI's S2S preview is polished but it still thinks in steps. Speech → text → model → text → speech. That's not how humans converse. Introducing Hydra. A native speech-to-speech model that doesn't wait for turn-taking, doesn't flatten emotion into text, and doesn't break when you interrupt it mid-sentence. Hydra reasons asynchronously, speaks and listens simultaneously, and preserves emotion because it never leaves the audio domain. It's still in beta, but the shift is obvious. If you want early access, the link is in the comments. Here's a preview of what that looks like -

Sudarshan Kamath

328,812 次观看 • 4 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

155,772 次观看 • 1 年前

Along with text, images, video and code, Gemini is able to process raw audio signal end-to-end. 🔊 It can listen to and understand speech, making it not only useful for transcription but a model that has a much more nuanced perception of its environment. ↓

Along with text, images, video and code, Gemini is able to process raw audio signal end-to-end. 🔊 It can listen to and understand speech, making it not only useful for transcription but a model that has a much more nuanced perception of its environment. ↓

Google DeepMind

140,169 次观看 • 2 年前

Republicans called a hearing on free speech, but Trump and Republicans made it clear they don’t believe in it. He threatened members of Congress, calling anyone who votes to release the Epstein files “hostile.” That certainly doesn’t sound like free speech to me.

Republicans called a hearing on free speech, but Trump and Republicans made it clear they don’t believe in it. He threatened members of Congress, calling anyone who votes to release the Epstein files “hostile.” That certainly doesn’t sound like free speech to me.

Congresswoman Jasmine Crockett

91,769 次观看 • 10 个月前

Speech translation has been one of the longest-running ML efforts at Google, and we’ve come a long way. Gemini 3.5 Live Translate is our latest speech-to-speech model, supporting 70+ languages. It enables more natural conversations across languages in everyday products and apps. Here’s an example of how partners at Grab are helping connect travelers with drivers. 🚗 Rolling out in Google Translate and via the Live API in Google AI Studio.

Speech translation has been one of the longest-running ML efforts at Google, and we’ve come a long way. Gemini 3.5 Live Translate is our latest speech-to-speech model, supporting 70+ languages. It enables more natural conversations across languages in everyday products and apps. Here’s an example of how partners at Grab are helping connect travelers with drivers. 🚗 Rolling out in Google Translate and via the Live API in Google AI Studio.

Jeff Dean

35,604 次观看 • 1 个月前

🚨 BREAKING: Google just launched the most powerful coding agent we’ve ever seen. It’s called Jules. It reads your codebase, makes a plan, builds features, writes tests and pushes the PR. No need to co-pilot. Jules just ships. Here’s how it works 👇

🚨 BREAKING: Google just launched the most powerful coding agent we’ve ever seen. It’s called Jules. It reads your codebase, makes a plan, builds features, writes tests and pushes the PR. No need to co-pilot. Jules just ships. Here’s how it works 👇

Brendan Jowett

970,300 次观看 • 1 年前

Gemini 3 is now in Search, starting with AI Mode. Find out how it works — and how it can help you learn more easily than ever — from Googlers who helped to build it. ⬇️

Gemini 3 is now in Search, starting with AI Mode. Find out how it works — and how it can help you learn more easily than ever — from Googlers who helped to build it. ⬇️

Google

73,842 次观看 • 7 个月前

Trump talking to kids at the White House and turns it into a builder lesson on the spot. Pointing at the columns, saying nobody touched it for centuries… and now he’s the one fixing it. That’s how his brain works. Everything comes back to building, fixing, improving. And honestly, moments like that stick with kids way more than any speech ever could.

Trump talking to kids at the White House and turns it into a builder lesson on the spot. Pointing at the columns, saying nobody touched it for centuries… and now he’s the one fixing it. That’s how his brain works. Everything comes back to building, fixing, improving. And honestly, moments like that stick with kids way more than any speech ever could.

ⁿᵉʷˢ Barron Trump 🇺🇸

17,195 次观看 • 3 个月前