Loading video...

Video Failed to Load

Go Home

Every millisecond counts for voice agents. Introducing Gemma 4 31B on LiveKit Inference! Optimized for real-time voice agents: - 354ms time to first audio - 192ms time to first token - Beats GPT-4.1 in agentic tool use (31B achieves 76.9% on tau2bench) Fast, capable, and efficient!

googlegemma's profile picture

Google Gemma

91,942 subscribers

144,260 views • 1 day ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gemma 4 is live on Cerebras, the fastest multimodal inference ever! Running on Gemma 4 31B open-weight model at a blistering 1,500+ tokens/sec. That's a 15x speedup, unlocking real-time visual and agentic loops without the GPU lag.
1:33

Gemma 4 is live on Cerebras, the fastest multimodal inference ever! Running on Gemma 4 31B open-weight model at a blistering 1,500+ tokens/sec. That's a 15x speedup, unlocking real-time visual and agentic loops without the GPU lag.

Google Gemma

111,112 views • 3 days ago

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.
4:03

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,648,946 views • 2 months ago

We shipped Agent Console, a realtime debugging surface for voice agents. Talk to your agent and see the entire pipeline live, from audio and latency to tool calls, transcripts, and participant state. Available now in the LiveKit Cloud dashboard.
4:52

We shipped Agent Console, a realtime debugging surface for voice agents. Talk to your agent and see the entire pipeline live, from audio and latency to tool calls, transcripts, and participant state. Available now in the LiveKit Cloud dashboard.

LiveKit

11,915 views • 3 months ago

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)
0:30

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Sarah Chieng

452,438 views • 9 months ago

Talk to Gemma 4 31B with our voice app! It sees and searches the web faster than you blink. Thanks to Cerebras’ ultra fast inference, the LLM is almost instantaneous. The whole stack is fully open-source, and is a drop-in replacement for OpenAI's realtime API. Demo:
1:46

Talk to Gemma 4 31B with our voice app! It sees and searches the web faster than you blink. Thanks to Cerebras’ ultra fast inference, the LLM is almost instantaneous. The whole stack is fully open-source, and is a drop-in replacement for OpenAI's realtime API. Demo:

Andi Marafioti

88,125 views • 16 days ago

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:
2:08

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

Cerebras

256,753 views • 17 days ago

Jeremy Allaire on the agentic economy: agents will pay other agents for intelligence. Once agents start contracting and settling in real time, the compounding effect is explosive.
1:07

Jeremy Allaire on the agentic economy: agents will pay other agents for intelligence. Once agents start contracting and settling in real time, the compounding effect is explosive.

Circle

687,297 views • 1 month ago

Agents on Solana are running continuous, real-time decision loops. To power this new workload, Sonic launches North Star: Instant private execution sessions for real-time agents. Every Solana agent and dApp gets its own isolated execution session. Run fast, settle back to Solana.
0:44

Agents on Solana are running continuous, real-time decision loops. To power this new workload, Sonic launches North Star: Instant private execution sessions for real-time agents. Every Solana agent and dApp gets its own isolated execution session. Run fast, settle back to Solana.

Sonic SVM

31,003 views • 17 days ago

Introducing BEACN Headset. A voice-first headset designed for creators, gamers, and professionals who refuse to compromise on audio. Powered by Broadcast Voice™ DSP, BEACN Headset delivers real-time, onboard microphone processing for clear communication wherever you work, play, and create. Pre-order available soon at ✨
1:16

Introducing BEACN Headset. A voice-first headset designed for creators, gamers, and professionals who refuse to compromise on audio. Powered by Broadcast Voice™ DSP, BEACN Headset delivers real-time, onboard microphone processing for clear communication wherever you work, play, and create. Pre-order available soon at ✨

BEACN

60,225 views • 3 months ago

This is the first implementation of Grok voice API by xAI on a robot thanks to atariorbit (not perfect yet)! Feels like this could unlock some fun new use cases for robotics agents given that it ranks #1 on Big Bench Audio, the leading audio reasoning benchmark that measures voice agents’ capabilities to solve complex problems!
2:55

This is the first implementation of Grok voice API by xAI on a robot thanks to atariorbit (not perfect yet)! Feels like this could unlock some fun new use cases for robotics agents given that it ranks #1 on Big Bench Audio, the leading audio reasoning benchmark that measures voice agents’ capabilities to solve complex problems!

clem 🤗

45,359 views • 7 months ago

Everyone's bringing compute, storage, sensors to @Consensus_hk We bring conversation layer. @dTelecom is Solana-native infra for real-time comms: voice, video, AI Agents powering FROGY 🐸, dMeet 🤙, agentic apps Coordinate humans/agents in ms >> find us @Consensus_hk
0:29

Everyone's bringing compute, storage, sensors to @Consensus_hk We bring conversation layer. @dTelecom is Solana-native infra for real-time comms: voice, video, AI Agents powering FROGY 🐸, dMeet 🤙, agentic apps Coordinate humans/agents in ms >> find us @Consensus_hk

dTelecom

78,334 views • 5 months ago

Time to ditch fake onchain AI agents running on centralized ChatGPT API. Introducing the first truly decentralized agents (dAgent) on Base. Just tweet at Eternal AI with an idea. Your dAgent & token are deployed on Base instantly. Trustless. Verifiable. Unstoppable.
0:32

Time to ditch fake onchain AI agents running on centralized ChatGPT API. Introducing the first truly decentralized agents (dAgent) on Base. Just tweet at Eternal AI with an idea. Your dAgent & token are deployed on Base instantly. Trustless. Verifiable. Unstoppable.

Eternal AI

59,894 views • 1 year ago

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.
0:45

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.

Vedant

15,714 views • 1 month ago

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.
0:26

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

Akshay 🚀

468,265 views • 6 months ago

You can now create a REAL-TIME chatbot with any voice and customize its personality. Steps: 1. Go to ElevenLabs 2. Click on voices 3. you can type in a name for the voice 4. then you can drag in an audio file to use for your voice 5. then go to the agents tab in side panel 6. and create a new agent 7. the voice 8. Create system instructions 9. Optional (Upload knowledge docs) 10. Test This can be easily implemented into your applications. I'll make a tutorial on that soon.
1:24

You can now create a REAL-TIME chatbot with any voice and customize its personality. Steps: 1. Go to ElevenLabs 2. Click on voices 3. you can type in a name for the voice 4. then you can drag in an audio file to use for your voice 5. then go to the agents tab in side panel 6. and create a new agent 7. the voice 8. Create system instructions 9. Optional (Upload knowledge docs) 10. Test This can be easily implemented into your applications. I'll make a tutorial on that soon.

Riley Brown

40,108 views • 1 year ago

We added 600+ new voices on Together AI! Introducing MiniMax Speech 2.8 Turbo on Together AI, an enterprise TTS model for expressive real-time voice agents. AI natives can now deploy MiniMax (official) Speech 2.8 Turbo on Together AI dedicated infrastructure, and try the voices directly in voice finder.
0:37

We added 600+ new voices on Together AI! Introducing MiniMax Speech 2.8 Turbo on Together AI, an enterprise TTS model for expressive real-time voice agents. AI natives can now deploy MiniMax (official) Speech 2.8 Turbo on Together AI dedicated infrastructure, and try the voices directly in voice finder.

Together AI

21,814 views • 1 month ago

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.
2:02

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

105,616 views • 2 years ago

Introducing Scribe v2 Realtime – the most accurate real-time Speech to Text model. Built for voice agents, meeting notetakers, and live applications, it transcribes in 150ms across 90+ languages, including English, French, German, Italian, Spanish, Portuguese, Hindi, and Japanese. Available today by API and through ElevenLabs Agents.
1:21

Introducing Scribe v2 Realtime – the most accurate real-time Speech to Text model. Built for voice agents, meeting notetakers, and live applications, it transcribes in 150ms across 90+ languages, including English, French, German, Italian, Spanish, Portuguese, Hindi, and Japanese. Available today by API and through ElevenLabs Agents.

ElevenLabs

317,630 views • 8 months ago

Introducing OpenAI o3 and o4-mini—our smartest and most capable models to date. For the first time, our reasoning models can agentically use and combine every tool within ChatGPT, including web search, Python, image analysis, file interpretation, and image generation.
0:44

Introducing OpenAI o3 and o4-mini—our smartest and most capable models to date. For the first time, our reasoning models can agentically use and combine every tool within ChatGPT, including web search, Python, image analysis, file interpretation, and image generation.

OpenAI

3,720,760 views • 1 year ago