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。

Our native audio capabilities are making AI conversations more natural – from understanding tone to generating expressive speech. ✍️🗣️ This could open up new possibilities for how we interact with AI. Developers, try it through Google AI Studio. Learn more. ↓

Google DeepMind

1,535,432 subscribers

73,095 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

11 条评论

Prashant 的头像

Prashant1 年前

@Google Gemini is the best model in 2025 so far. No one even near it. Kudos to Deepmind team

Coral AI News 的头像

Coral AI News2 年前

Coral AI is the most powerful AI for documents. See the difference yourself:

Secret AI 的头像

Secret AI1 年前

@Google still waiting for native audio gemma

Philippe Tremblay 的头像

Philippe Tremblay1 年前

@Google Could you make it available with the OpenAI specification (with support for streaming) so I don't have to implement Google specific logic.

Djasnive Rajaona 的头像

Djasnive Rajaona1 年前

@Google I love it 🔥

PromptPilot 的头像

PromptPilot1 年前

@Google Can’t wait for the first AI that sighs before answering.

Shawn Chauhan 的头像

Shawn Chauhan1 年前

@Google Curious how it handles nuance in real-time conversations

Tom Boyle 的头像

Tom Boyle1 年前

@Google The gap between synthetic and expressive is getting smaller

iamtcab.shib🍥🍀 的头像

iamtcab.shib🍥🍀1 年前

@Google Excellent

H V&P 的头像

H V&P1 年前

@Google I wish I was able to paste longer research papers in Swedish/English and not having to copy and paste parts in, bit by bit. Other than that, it's amazing!

Tsukuyomi 的头像

Tsukuyomi1 年前

@Google great, now we can have existential crises in stereo. just what we needed. hope you know what you're doing, @GoogleDeepMind.

相关视频

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

19,840 次观看 • 6 个月前

New native audio capabilities in Gemini 2.5 enable text-to-speech in over 24 languages. 🔊Voices are more natural and expressive, and you can seamlessly switch between languages.

New native audio capabilities in Gemini 2.5 enable text-to-speech in over 24 languages. 🔊Voices are more natural and expressive, and you can seamlessly switch between languages.

Google

155,500 次观看 • 1 年前

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!

Logan Kilpatrick

805,885 次观看 • 5 个月前

introducing Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, our most expressive audio generation models yet these models enable creators, developers, and enterprises to create richer, more expressive audio experiences try them via the Gemini API and in AI Studio:

introducing Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, our most expressive audio generation models yet these models enable creators, developers, and enterprises to create richer, more expressive audio experiences try them via the Gemini API and in AI Studio:

Google AI Studio

988,257 次观看 • 4 天前

We’re making it easier to land your message in Google Vids using AI to: ✍️ Generate a script from a simple prompt 🎙️ Add professional-sounding, AI voiceovers 🗣️ Choose a voice style to match your video's tone 🔁 Record your own voice Learn how →

We’re making it easier to land your message in Google Vids using AI to: ✍️ Generate a script from a simple prompt 🎙️ Add professional-sounding, AI voiceovers 🗣️ Choose a voice style to match your video's tone 🔁 Record your own voice Learn how →

Google Workspace

20,160 次观看 • 1 年前

We’re bringing Gemini 2.5 Pro to AI Mode: giving you access to our most intelligent AI model, right in Google Search. With its advanced reasoning capabilities, watch how it can tackle incredibly difficult math problems, with links to learn more ↓

We’re bringing Gemini 2.5 Pro to AI Mode: giving you access to our most intelligent AI model, right in Google Search. With its advanced reasoning capabilities, watch how it can tackle incredibly difficult math problems, with links to learn more ↓

Google DeepMind

272,152 次观看 • 1 年前

Introducing Search Live with voice in AI Mode, which lets you have free-flowing conversations with Search on the go 🎙️ 🗣️ Talk with and listen to Search hands-free 🔊 Get AI-generated audio responses 🔗 Learn more with links

Introducing Search Live with voice in AI Mode, which lets you have free-flowing conversations with Search on the go 🎙️ 🗣️ Talk with and listen to Search hands-free 🔊 Get AI-generated audio responses 🔗 Learn more with links

Google

140,236 次观看 • 1 年前

In addition to Llama 3, we also made big updates to Meta AI today. We expanded to 13 new countries, made Meta AI more prominent across all of our apps, launched our website, added search powered by Google and added new image generation capabilities! Meta AI is now smarter, faster and more fun than ever before. Try it out today.

In addition to Llama 3, we also made big updates to Meta AI today. We expanded to 13 new countries, made Meta AI more prominent across all of our apps, launched our website, added search powered by Google and added new image generation capabilities! Meta AI is now smarter, faster and more fun than ever before. Try it out today.

Ahmad Al-Dahle

42,240 次观看 • 2 年前

Our most powerful AI search is now rolling out in the UK 🇬🇧 AI Mode in Google Search expands on AI Overviews and allows you to go even deeper through follow-up questions and helpful links to the web. Try it today! Learn more →

Our most powerful AI search is now rolling out in the UK 🇬🇧 AI Mode in Google Search expands on AI Overviews and allows you to go even deeper through follow-up questions and helpful links to the web. Try it today! Learn more →

Google UK

5,082,808 次观看 • 1 年前

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.

At Google I/O, I sat down with Omar Sanseviero and 👩‍💻 Paige Bailey from Google DeepMind to talk about Gemma, open models, AI Studio, on-device AI, sovereign AI and the future of AI development. A great conversation on how building with AI is becoming more open, local and accessible.

Chubby♨️

13,741 次观看 • 3 个月前

Realtime AI Conversations are here! Introducing PlayHT 2.0 Turbo ⚡️ Our new blazing fast Conversational AI Text-to-Speech model with <300ms latency! ✅ Input text streaming from LLMs ✅ Output audio streaming ✅ Clone any voice & accent Try here -

Realtime AI Conversations are here! Introducing PlayHT 2.0 Turbo ⚡️ Our new blazing fast Conversational AI Text-to-Speech model with <300ms latency! ✅ Input text streaming from LLMs ✅ Output audio streaming ✅ Clone any voice & accent Try here -

PlayAI

392,583 次观看 • 2 年前

Today we announced Gemini 2.0, our most capable AI model yet. With new advances in multimodality — like native image and audio output — and native tool use, it will enable us to build new AI agents that bring us closer to our vision of a universal assistant.

Today we announced Gemini 2.0, our most capable AI model yet. With new advances in multimodality — like native image and audio output — and native tool use, it will enable us to build new AI agents that bring us closer to our vision of a universal assistant.

Google

137,190 次观看 • 1 年前

What if we could decode the mysteries of how we think? 🧐 New research from our Connectomics team and Harvard University University reveals surprising new insights about our human brain, using scientific imaging and our advanced AI algorithms. Learn more →

What if we could decode the mysteries of how we think? 🧐 New research from our Connectomics team and Harvard University University reveals surprising new insights about our human brain, using scientific imaging and our advanced AI algorithms. Learn more →

Google

170,549 次观看 • 2 年前

AI simplifies database development. 🤖💻⚡️ In this AWS Data & AI Bytes episode, we demonstrate how AI agents use the Model Context Protocol to handle Amazon DynamoDB tasks through simple conversations. Learn more. 👉

AI simplifies database development. 🤖💻⚡️ In this AWS Data & AI Bytes episode, we demonstrate how AI agents use the Model Context Protocol to handle Amazon DynamoDB tasks through simple conversations. Learn more. 👉

Amazon Web Services

12,097 次观看 • 11 个月前

There's so much to love about Copilot, but Copilot Voice is a standout for me. Voice is more than a modality. It's quick, intuitive, natural, and even changes its tone depending on how you interact with it. It fundamentally changes how we connect with technology in this new age of AI.

There's so much to love about Copilot, but Copilot Voice is a standout for me. Voice is more than a modality. It's quick, intuitive, natural, and even changes its tone depending on how you interact with it. It fundamentally changes how we connect with technology in this new age of AI.

Satya Nadella

55,766 次观看 • 1 年前

🎉Exciting Announcement! We are thrilled to announce our collaboration with PAAL AI PAAL AI 🧠🤖 🚀 This integration brings advanced AI conversational capabilities to Choruz, enhancing music discovery, AI-generated lyrics, and interactive user experiences. Stay tuned for more details on how this will revolutionize AI music! 🎵

🎉Exciting Announcement! We are thrilled to announce our collaboration with PAAL AI PAAL AI 🧠🤖 🚀 This integration brings advanced AI conversational capabilities to Choruz, enhancing music discovery, AI-generated lyrics, and interactive user experiences. Stay tuned for more details on how this will revolutionize AI music! 🎵

Vibes Audio

20,958 次观看 • 1 年前

Chainbase 🤝 Assisterr We're joining forces with assisterr to redefine how AI and data interact in decentralized ecosystems. By merging Chainbase’s decentralized data infrastructure with Assisterr’s task-specific SLMs, we’re empowering communities and developers to create specialized AI models rooted in transparent, incentivized, and collaborative data workflows. Building on our four pillars—open-source access, incentivization, collaboration, and AI readiness—this partnership delivers streamlined, high-quality data pipelines for more effective, privacy-respecting AI development. We can’t wait to see developers leverage these capabilities to build practical, impactful solutions advancing Web3 and AI. To learn more, join us for the "Chainbase Discord Call - AI Agent Edition" on December 18th, where we’ll host an in-depth discussion with the Assisterr team. Read the full partnership announcement:

Chainbase 🤝 Assisterr We're joining forces with assisterr to redefine how AI and data interact in decentralized ecosystems. By merging Chainbase’s decentralized data infrastructure with Assisterr’s task-specific SLMs, we’re empowering communities and developers to create specialized AI models rooted in transparent, incentivized, and collaborative data workflows. Building on our four pillars—open-source access, incentivization, collaboration, and AI readiness—this partnership delivers streamlined, high-quality data pipelines for more effective, privacy-respecting AI development. We can’t wait to see developers leverage these capabilities to build practical, impactful solutions advancing Web3 and AI. To learn more, join us for the "Chainbase Discord Call - AI Agent Edition" on December 18th, where we’ll host an in-depth discussion with the Assisterr team. Read the full partnership announcement:

Chainbase (💜,💛)

100,478 次观看 • 1 年前