Loading video...

Video Failed to Load

Go Home

Learn how to build a real-time voice AI agent using Gemini Live. In this demo created by Software Mansion, users solve a mystery in this interactive game featuring an AI narrator.

googleaidevs's profile picture

Google AI Developers

117,546 subscribers

10,345 views • 7 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

8 Comments

Google AI Developers's profile picture
Google AI Developers7 months ago

Get the code and play the game:

Google AI Developers's profile picture
Google AI Developers7 months ago

Join the Deep Sea Stories livestream on Thursday, Feb 12 at 7 PM CET to see if @GoogleDeepMind’s @thorwebdev can crack the case live and stay for the technical deep dive:

ALT Music's profile picture
ALT Music7 months ago

@swmansion Building a persistent AI companion ('Project Resurrection') in Android Studio right now. The latency in this demo looks incredibly low. Does this implementation handle long-context retention well? I need my agent to remember who 'Zach' is 20 minutes later! 🧠📱

Barrak's profile picture
Barrak7 months ago

@swmansion This interactive mystery game demo is brilliant! Building a real-time voice AI agent with Gemini Live that has natural conversation and narration creates such an immersive experience. Voice AI is transforming gaming! 🎮

🫏 BullishMule 📈's profile picture
🫏 BullishMule 📈7 months ago

@swmansion What game what work around just deliver wtf 😂😂🤯

Vu2day🆗's profile picture
Vu2day🆗7 months ago

@swmansion Building a talking detective sounds like the ultimate weekend project. Just hope the AI doesn't figure out "whodunnit" before the players even start!

Rachel Stuppy's profile picture
Rachel Stuppy7 months ago

@swmansion Love this!

Dmitrii Malakhov's profile picture
Dmitrii Malakhov6 months ago

@swmansion claude can do this too. real-time voice, interactive games, same pattern. the api isn't the moat.

Related Videos

Can AI chain tools together to complete complex tasks in real-time? Gemini 2.0 can. Here's a React demo using the new Multimodal Live API to chain code execution + real-time Google Search. I'm amazed at how fast this is.
2:17

Can AI chain tools together to complete complex tasks in real-time? Gemini 2.0 can. Here's a React demo using the new Multimodal Live API to chain code execution + real-time Google Search. I'm amazed at how fast this is.

Addy Osmani

17,804 views • 1 year ago

Learn how to build an AI agent in 175 lines of Python.
5:11

Learn how to build an AI agent in 175 lines of Python.

Lee Robinson

72,218 views • 1 year ago

I just built a Voice AI Agent for insurance claims using Gemini 3.1 Flash Live and Google ADK. Talk to it. It fills the intake form, extracts claim details, and routes to an adjuster in real-time. 100% Opensource.
2:04

I just built a Voice AI Agent for insurance claims using Gemini 3.1 Flash Live and Google ADK. Talk to it. It fills the intake form, extracts claim details, and routes to an adjuster in real-time. 100% Opensource.

Shubham Saboo

73,280 views • 5 months ago

This is crazy. I created this real-time AI voice agent to handle reservations for a fictitious restaurant, all without coding and in a few minutes 🤯 Link and tutorial in the comments.
0:43

This is crazy. I created this real-time AI voice agent to handle reservations for a fictitious restaurant, all without coding and in a few minutes 🤯 Link and tutorial in the comments.

Alvaro Cintas

452,869 views • 2 years ago

Learn how to build an audiobook voice agent using Gradium and Pipecat AI Gradium's TTS handles the narration and Pipecat's built-in WebRTC transport delivers the audio to the browser.
4:40

Learn how to build an audiobook voice agent using Gradium and Pipecat AI Gradium's TTS handles the narration and Pipecat's built-in WebRTC transport delivers the audio to the browser.

Gradium

11,247 views • 4 months ago

Vibe code video games with dynamic AI commentary using the latest Gemini Live in Google AI Studio! 🏏 I made a cricket game to show you how: - Real-time AI reactions - Switches to Urdu/Hindi - Play as Sundar Pichai or Demis Hassabis (assets via nano banana) Demo + code below 👇
0:41

Vibe code video games with dynamic AI commentary using the latest Gemini Live in Google AI Studio! 🏏 I made a cricket game to show you how: - Real-time AI reactions - Switches to Urdu/Hindi - Play as Sundar Pichai or Demis Hassabis (assets via nano banana) Demo + code below 👇

Ammaar Reshi

19,495 views • 1 year ago

Build anything in the terminal with improved agentic coding in Gemini 3 Flash! Watch this demo to see how a rapid prototyping tool doesn't have to compromise code quality. Learn more about using Gemini 3 Flash with Gemini CLI →
0:52

Build anything in the terminal with improved agentic coding in Gemini 3 Flash! Watch this demo to see how a rapid prototyping tool doesn't have to compromise code quality. Learn more about using Gemini 3 Flash with Gemini CLI →

Google Cloud Tech

38,480 views • 8 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 • 1 year ago

Watch this ADK TypeScript tutorial from Mandy Chan to build an AI agent using the open-source toolkit. 04:50 Science Teacher Agent demo 08:30 Customer Order Agent demo
15:43

Watch this ADK TypeScript tutorial from Mandy Chan to build an AI agent using the open-source toolkit. 04:50 Science Teacher Agent demo 08:30 Customer Order Agent demo

Google AI Developers

24,948 views • 8 months ago

Build an AI Research Planner & Executor Agent using Google Interactions API. Combine Gemini 3 Pro, Gemini 3 Flash and Google Deep Research Agent in a single flow. 100% Opensource code with step-by-step tutorial.
0:52

Build an AI Research Planner & Executor Agent using Google Interactions API. Combine Gemini 3 Pro, Gemini 3 Flash and Google Deep Research Agent in a single flow. 100% Opensource code with step-by-step tutorial.

Shubham Saboo

43,369 views • 9 months ago

Watch this demo from Thor 雷神 ⚡️ to see Gemini 3.1 Flash Live in action as a real-time DJ. The model uses function calling (to the Gemini API) to generate custom 30-second clips using Lyria 3️⃣ Start your own studio session in Google AI Studio:
2:31

Watch this demo from Thor 雷神 ⚡️ to see Gemini 3.1 Flash Live in action as a real-time DJ. The model uses function calling (to the Gemini API) to generate custom 30-second clips using Lyria 3️⃣ Start your own studio session in Google AI Studio:

Google AI Developers

11,216 views • 5 months ago

🚨 this chinese guy makes over $1,000,000 a year… by building AI agents. no employees. no massive startup. he just keeps building. while most people are still asking ChatGPT random questions, he’s using Claude to build software that solves real problems. this is what people call vibe coding. he opens Claude and says: “build me an AI agent for real estate businesses that creates property videos.” Claude writes the code. builds the interface. adds subscriptions. helps deploy the app. within a day, he has a working product. then he starts building the next one. that’s the part most people don’t understand. he isn’t trying to build one billion-dollar company. he’s building dozens of AI agents, each solving one problem for one industry. → an AI agent for dentists → an AI agent for ecommerce brands → an AI agent for podcasters → an AI agent for real estate businesses each one automates work that people normally do by hand. each one is built with simple prompts. each one can become a real business. the crazy part? you don’t need to be a software engineer anymore. you need to know how to think like a builder. how to spot problems. how to explain solutions to AI. and how to ship. that’s exactly why i’m reading this article: “How to Actually Build Your First AI Agent.” because this is the skill that’s creating the next generation of builders. the people who learn to build AI agents today won’t just use AI. they’ll own the tools everyone else ends up paying for.
1:15

🚨 this chinese guy makes over $1,000,000 a year… by building AI agents. no employees. no massive startup. he just keeps building. while most people are still asking ChatGPT random questions, he’s using Claude to build software that solves real problems. this is what people call vibe coding. he opens Claude and says: “build me an AI agent for real estate businesses that creates property videos.” Claude writes the code. builds the interface. adds subscriptions. helps deploy the app. within a day, he has a working product. then he starts building the next one. that’s the part most people don’t understand. he isn’t trying to build one billion-dollar company. he’s building dozens of AI agents, each solving one problem for one industry. → an AI agent for dentists → an AI agent for ecommerce brands → an AI agent for podcasters → an AI agent for real estate businesses each one automates work that people normally do by hand. each one is built with simple prompts. each one can become a real business. the crazy part? you don’t need to be a software engineer anymore. you need to know how to think like a builder. how to spot problems. how to explain solutions to AI. and how to ship. that’s exactly why i’m reading this article: “How to Actually Build Your First AI Agent.” because this is the skill that’s creating the next generation of builders. the people who learn to build AI agents today won’t just use AI. they’ll own the tools everyone else ends up paying for.

MIKE

39,041 views • 3 months ago

This is a real-time demo showcasing avatars + function calling. Avatars can fill out forms, schedule meetings, and much more. The future website has two interfaces: 1. The traditional UI to convey information. 2. An AI agent with a face that users can talk to Give your AI agents a face using LemonSlice - a 24/7 spokesperson that your users trust Demo and open source links below. Made by Bryce 👇️
1:11

This is a real-time demo showcasing avatars + function calling. Avatars can fill out forms, schedule meetings, and much more. The future website has two interfaces: 1. The traditional UI to convey information. 2. An AI agent with a face that users can talk to Give your AI agents a face using LemonSlice - a 24/7 spokesperson that your users trust Demo and open source links below. Made by Bryce 👇️

LemonSlice

46,205 views • 5 months ago

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:
2:41

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,965 views • 1 year ago

Google just made AI voice agents stupidly easy. Gemini 3.1 Flash Live lets you build real-time voice apps in minutes. Language tutors. Interview coaches. Virtual receptionists. Daily planners. Even custom agents with saved history using Firebase. This is what happens when voice AI stops feeling robotic and starts feeling useful.
15:45

Google just made AI voice agents stupidly easy. Gemini 3.1 Flash Live lets you build real-time voice apps in minutes. Language tutors. Interview coaches. Virtual receptionists. Daily planners. Even custom agents with saved history using Firebase. This is what happens when voice AI stops feeling robotic and starts feeling useful.

Julian Goldie SEO

24,087 views • 6 months ago