Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

💡Recent updates to the Live API - Significantly higher rate limits - Enhanced session management + reliability - Configurable voice activity detection (VAD) - Expanded voice + language options And MORE.

Google AI Developers

44,500 subscribers

34,992 views • 1 year ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Google AI Developers1 year ago

Blog for details → Live API docs → Google AI Studio →

AssemblyAI1 year ago

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

LLM1 year ago

What are you all trying to accomplish with this compared to Firebase? It just doesn't seem to make sense.

ᐸGerardSans/ᐳ🚀🇬🇧1 year ago

Explore the new Live API features through the Angular Web Console with the GenAI SDK. It’s the easiest way to get started with voice-first AI agents that support tools, code execution, and web searches.

Kaizenus Imperium1 year ago

This is insane

Azy1 year ago

@googledevs What are you guys trying to do with this VS firebase it makes no sense

ThisAndThat1 year ago

I love Gemini 2.0 Live API So underrated!

ᗩᗰEᖇIᑕᗩᑎ ᗰᗩᗪE ᗰEᗪIᗩ1 year ago

Great work 👏 Lets bring Imagen to another level as well.

Tomer Nosrati1 year ago

I just tried it out. It really works. Wow.. we live in the future.

Sundew1 year ago

Great update! The configurable VAD and expanded language options are a thoughtful touch for better accessibility.

Related Videos

Voice AIs handle speaker turns & interruptions with Voice Activity Detection. VAD is brittle and will trigger due to background noise, creating frequent hiccups. Moshi gets rid of it completely, so you can use it in the most chaotic settings. I myself couldn't hear Moshi here 😅

Voice AIs handle speaker turns & interruptions with Voice Activity Detection. VAD is brittle and will trigger due to background noise, creating frequent hiccups. Moshi gets rid of it completely, so you can use it in the most chaotic settings. I myself couldn't hear Moshi here 😅

Neil Zeghidour

31,970 views • 1 year ago

Developers are building great voice experiences with the Realtime API. See how Lemonade uses it to power AI Maya, their friendly and engaging voice agent. The Realtime API's automatic voice detection and low latency enable them to offer 24/7 multilingual phone support 📞

Developers are building great voice experiences with the Realtime API. See how Lemonade uses it to power AI Maya, their friendly and engaging voice agent. The Realtime API's automatic voice detection and low latency enable them to offer 24/7 multilingual phone support 📞

OpenAI Developers

126,054 views • 1 year ago

OpenAI just announced "GPT-4o". It can reason with voice, vision, and text. The model is 2x faster, 50% cheaper, and has 5x higher rate limit than GPT-4 Turbo. It will be available for free users and via the API. The voice model can even pick up on emotion and generate emotive voice.

OpenAI just announced "GPT-4o". It can reason with voice, vision, and text. The model is 2x faster, 50% cheaper, and has 5x higher rate limit than GPT-4 Turbo. It will be available for free users and via the API. The voice model can even pick up on emotion and generate emotive voice.

Lior Alexander

485,014 views • 2 years ago

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

LiveKit

126,817 views • 1 year ago

Last week we brought voice to Stitch powered by the Gemini Live API. Today, the team announced Gemini 3.1 Flash Live and we are very excited! 🚀 We believe that your voice will be the future driver of design. Huge congrats on the updates to latency, instruction following, and natural dialogue. 👀

Last week we brought voice to Stitch powered by the Gemini Live API. Today, the team announced Gemini 3.1 Flash Live and we are very excited! 🚀 We believe that your voice will be the future driver of design. Huge congrats on the updates to latency, instruction following, and natural dialogue. 👀

Stitch by Google

41,308 views • 2 months ago

Voice Cloning is now live via the xAI API! Create a custom voice in less than 2 minutes or select from our library of 80+ voices across 28 languages to personalize your voice agents, audiobooks, video game characters, and more.

Voice Cloning is now live via the xAI API! Create a custom voice in less than 2 minutes or select from our library of 80+ voices across 28 languages to personalize your voice agents, audiobooks, video game characters, and more.

xAI

204,001,687 views • 1 month ago

What will you build with Vision Agents? Out-of-the-box support for: - Turn detection - Speech-to-text + text-to-speech - Voice activity detection - MCP & function-calling support Open-source. Video-first. Ready to build.

What will you build with Vision Agents? Out-of-the-box support for: - Turn detection - Speech-to-text + text-to-speech - Voice activity detection - MCP & function-calling support Open-source. Video-first. Ready to build.

Stream

226,723 views • 5 months ago

Update 8.0 is live NOW! 🌷 New Spring seasonal event 🌀 Angry Birds Digiverse rift ✨ Huge QoL updates, including expanded sandbox options and outdoor toilets AND SO MUCH MORE!

Update 8.0 is live NOW! 🌷 New Spring seasonal event 🌀 Angry Birds Digiverse rift ✨ Huge QoL updates, including expanded sandbox options and outdoor toilets AND SO MUCH MORE!

Two Point Museum 🫟

10,328 views • 3 months ago

We just rolled out a way to quickly check the rate limits for other API tiers in Google AI Studio, a building block for future updates to come : )

We just rolled out a way to quickly check the rate limits for other API tiers in Google AI Studio, a building block for future updates to come : )

Logan Kilpatrick

67,267 views • 3 months ago

Plus users will get up to 5x higher limits, and earliest access to features like our new macOS desktop app and next-generation voice and video capabilities.

Plus users will get up to 5x higher limits, and earliest access to features like our new macOS desktop app and next-generation voice and video capabilities.

OpenAI

963,473 views • 2 years ago

Day 1 of 3 days of MLX: Introducing MLX-Audio-Swift SDK 🚀 A modular Swift SDK for voice agents and tasks on Apple Silicon built by Lucas Newman and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️ Text-to-Speech (TTS) 👂 Speech-to-Text (STT) 🔄 Speech-to-Speech (STS) 🎙️ Voice Activity Detection (VAD) and more. Only import the capabilities you need, nothing extra. Get started today and leave us a star ⭐️

Day 1 of 3 days of MLX: Introducing MLX-Audio-Swift SDK 🚀 A modular Swift SDK for voice agents and tasks on Apple Silicon built by Lucas Newman and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️ Text-to-Speech (TTS) 👂 Speech-to-Text (STT) 🔄 Speech-to-Speech (STS) 🎙️ Voice Activity Detection (VAD) and more. Only import the capabilities you need, nothing extra. Get started today and leave us a star ⭐️

Prince Canuma

160,131 views • 3 months ago

🛠️WIP expanded🛠️ Further experimenting with face-tracking and PNG/MP4/GIF-Tubing by combing OBS & Live2D to communicate. Now we have the mouth voice-detection. It's still a bit buggy but the idea gets more real as it goes. Lots of potential forward

🛠️WIP expanded🛠️ Further experimenting with face-tracking and PNG/MP4/GIF-Tubing by combing OBS & Live2D to communicate. Now we have the mouth voice-detection. It's still a bit buggy but the idea gets more real as it goes. Lots of potential forward

AlpineShowTime -🎃Halloween Event VTuber🎃

46,361 views • 1 year ago

StepAudio 2.5 TTS is live now! Control emotion, pacing, pauses, and delivery with plain natural language. No tags, no preset combos. Just describe what you want the voice to do. Zero-shot voice cloning with full timbre + emotion control. Available via Pay-as-you-go API or Step Plan.

StepAudio 2.5 TTS is live now! Control emotion, pacing, pauses, and delivery with plain natural language. No tags, no preset combos. Just describe what you want the voice to do. Zero-shot voice cloning with full timbre + emotion control. Available via Pay-as-you-go API or Step Plan.

StepFun

17,024 views • 1 month ago

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

ElevenLabs

293,329 views • 2 years ago

Flux Multilingual is live. Real-time conversational speech-to-text for voice agents in 10 languages, with monolingual-grade accuracy, turn detection, and code-switching. Deploy once and launch globally. Learn more →

Flux Multilingual is live. Real-time conversational speech-to-text for voice agents in 10 languages, with monolingual-grade accuracy, turn detection, and code-switching. Deploy once and launch globally. Learn more →

Deepgram

14,730 views • 1 month ago

📣 You can now have a conversation with Meta AI using voice. It’s super fast, connected to the web, natural and conversational and even comes with celebrity voice options from Awkwafina, Kristen Bell, John Cena, and more. What voice speaks to you? (pun intended 😆)

📣 You can now have a conversation with Meta AI using voice. It’s super fast, connected to the web, natural and conversational and even comes with celebrity voice options from Awkwafina, Kristen Bell, John Cena, and more. What voice speaks to you? (pun intended 😆)

Ahmad Al-Dahle

112,760 views • 1 year ago

Add near real-time voice translation to your apps with Gemini 3.5 Live Translate via the Gemini Live API. 🎙️ Watch how the model handles live broadcast ingestion and translation with continuous speech-to-speech streaming (S2ST) and synced transcripts, letting users tune into global radio broadcasts in their native language.

Add near real-time voice translation to your apps with Gemini 3.5 Live Translate via the Gemini Live API. 🎙️ Watch how the model handles live broadcast ingestion and translation with continuous speech-to-speech streaming (S2ST) and synced transcripts, letting users tune into global radio broadcasts in their native language.

Google AI Developers

18,239 views • 5 days ago

How to build the world's fastest voice AI bot: - Self-host speech-to-text, LLM inference, and text-to-speech all together in the same container/cluster. - Route audio over the internet using WebRTC and edge networking. - Configure timings for voice activity detection, phrase endpointing, and other parts of the pipeline to optimize for latency. (There are trade-offs to doing this!) Here's a LLama 3 voice bot that has voice-to-voice response times of ~500ms. We used Deepgram's STT and TTS for this bot, and everything is hosted on cerebriumai's serverless GPU infrastructure.

How to build the world's fastest voice AI bot: - Self-host speech-to-text, LLM inference, and text-to-speech all together in the same container/cluster. - Route audio over the internet using WebRTC and edge networking. - Configure timings for voice activity detection, phrase endpointing, and other parts of the pipeline to optimize for latency. (There are trade-offs to doing this!) Here's a LLama 3 voice bot that has voice-to-voice response times of ~500ms. We used Deepgram's STT and TTS for this bot, and everything is hosted on cerebriumai's serverless GPU infrastructure.

kwindla

282,518 views • 2 years ago

.Vogent Voicelab is a high-performance API to run top open-source voice models, like Sesame CSM-1B, Dia, and more. Voicelab optimizes inference for each model so you can run them quickly and scalably— and they post-train select models to improve performance and reliability.

.Vogent Voicelab is a high-performance API to run top open-source voice models, like Sesame CSM-1B, Dia, and more. Voicelab optimizes inference for each model so you can run them quickly and scalably— and they post-train select models to improve performance and reliability.

Y Combinator

54,718 views • 11 months ago

.Vogent just released Vogent-Turn-80M: an open-source, state-of-the-art turn-detection model for voice AI. It improves any voice AI stack by detecting when to wait and when to speak, reducing interruptions and making conversations more humanlike.

.Vogent just released Vogent-Turn-80M: an open-source, state-of-the-art turn-detection model for voice AI. It improves any voice AI stack by detecting when to wait and when to speak, reducing interruptions and making conversations more humanlike.

Y Combinator

18,913 views • 7 months ago