Skip to main content
AmigoFish

Google for Developers

Google for DevelopersVideo

Format:
YouTube channel
New videos:
Daily
Typical length:
about 1 minute
Latest video:
Not rated yet

About this show

Welcome to Google for Developers! Subscribe for the latest tools, APIs, and frameworks. Get step-by-step guides for Gemini and Google AI Studio, master modern engineering practices, and discover next-generation builds, to build what’s next with Google for Developers.

Videos come from the channel's public YouTube feed. The artwork is the newest video thumbnail. Last updated . Names, artwork and text belong to their publishers.

Cosmos

Similar by topic and creator

See the full Cosmos

Videos

  • Real-time golf swing coaching with Gemini 3.8 Live

    · 42 sec

    See Gemini 3.8 Live in action as it turns high-speed motion capture data into real-time, conversational coaching cues and interactive slow-motion replays to help improve a golf swing, powered by Google DeepMind’s latest live model. Try Gemini 3.8 Live today! 🔗Resources: Blog → https://goo.gle/4ziuJMW Developer documentation → https://goo.gle/4y7z7NL Have questions? Drop them in the comments. Subscribe to Google for Developers → https://goo.gle/developers Speakers: Sam Goldstein Products Mentioned: Gemini

    Not rated yet
  • 🧶 From Gemini code to textile art

    · 25 sec

    Carrie transforms code into textile art using Google AI Studio and Gemini, bringing custom yarn designs to life inspired by binary algorithms. 🔗 Explore the build → https://goo.gle/4iN1AEx Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini, Google AI Studio Speaker: Carrie Sun

    Not rated yet
  • Turning code into fabric with Gemini

    · 1 min

    Look what you can do! Explore the intersection of binary coding and fabric-making with Computational Knitting. Built with Gemini, Carrie's project transforms algorithmic processes into unique textile designs knit on a computerized knitting machine. Watch as she brings these digital designs to life stitch by stitch on a computerized knitting machine. Try building today → https://goo.gle/4djpF2k Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini, Google AI Studio Speaker: Carrie Sun

    Not rated yet
  • Top 3 new model launches at Gemini Audio at Night

    · 1 min

    Catch up on the highlights from Gemini Audio at Night in San Francisco! Google DeepMind’s Paige Bailey breaks down the top 3 developer takeaways from the event and shows how these new audio models come to life through hands-on demos. Discover how you can build with: *Gemini 3.8 TTS models: Text-to-speech with voice personalization, including custom emotions and resonance. *Gemini 3.5 Live Translate: Real-time translation for audio and video feeds across 100+ languages. *Gemini 3.8 Live models: New multimodal features, including function calls and other features built specifically for developers. Learn more about Gemini Audio and let us know what you build in the comments → https://goo.gle/3TCXNzx Subscribe to Google for Developers → https://goo.gle/developers Speaker: Paige Bailey Products Mentioned: Gemini

    Not rated yet
  • Introducing EmbeddingGemma 2: An open model for natively multimodal embeddings

    · 3 min

    Sebastian Russo, Ivan Llanos, and Sahil Dua from Google DeepMind introduce EmbeddingGemma 2, a lightweight open model that maps text, images, video, and audio into a single unified embedding space. At just 740 million parameters, EmbeddingGemma 2 is engineered for on-device use cases. Watch this video to discover: *EmbeddingGemma 2’s modular architecture with optional audio and vision encoders *Instant media search and video moment retrieval running fully offline on device *Retrieval-augmented generation (RAG) pipelines where sensitive data never leaves the hardware *Fine-tuning for domain-specific use cases 🔗 Resources: Learn about the model → https://goo.gle/4hE3Lb9 Read the developer guide → https://goo.gle/4hFnyqO Explore on-device embeddings with Google AI Edge → https://goo.gle/3VSXqS1 Download model weights from HuggingFace → https://goo.gle/4i45qbp Get started with the Gemma Cookbook → https://goo.gle/3TCsqVO Have questions? Drop them in the comments. Subscribe to Google for Developers → https://goo.gle/developers Speakers: Sebastian Russo, Ivan Llanos, Sahil Dua Products Mentioned: Gemma, Google AI Edge

    Not rated yet
  • 🧾 Building a voice-to-print mirror with Gemini

    · 16 sec

    Gayatri built a custom journaling device using Nano Banana and Gemini through Antigravity and Google AI Studio to transform spoken memories into physical keepsakes. 🔗 Explore the build → https://goo.gle/4z2vI3I Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini, Google Antigravity, Google AI Studio Speaker: Gayatri Kalra

    Not rated yet
  • How to transform audio into physical prints using Gemini and Google AI Studio

    · 1 min

    Using Nano Banana and Gemini through Antigravity and Google AI Studio, Gayatri found a way to transform spoken words and everyday thoughts into lasting visual artifacts. Watch to explore the build and see how memories become physical prints. Try building today → https://goo.gle/3VfKNQR Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini, Google Antigravity, Google AI Studio Speaker: Gayatri Kalra

    Not rated yet
  • Per-Layer Embeddings (PLE) in Gemma 4 explained

    · 2 min

    Learn how per-layer embeddings, or PLE, work in Gemma 4 E2B and E4B, Google's open source language model. Google DeepMind’s Maarten Grootendorst breaks down how PLE gives each token a layer-specific embedding for more diverse representation, boosting model performance without increasing the parameters used during computation. Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemma 4 Speaker: Maarten Grootendorst

    Not rated yet
  • The next generation of voice AI with Google DeepMind and Sierra AI

    · 5 min

    Valeria Wu (Google DeepMind) and Soham Ray (Sierra AI) explore the latest advances in native audio models and the challenges of building better real-time voice experiences. They discuss conversational latency, multilingual code-switching, agentic voice tasks, and how new benchmarks can better measure the quality of real-world dialogue. Watch along and learn: *How native speech-to-speech models preserve the tone and prosody traditional pipelines lose. *The engineering tradeoffs behind sub-second response times and seamless, human-like interruption handling. *How models smoothly navigate mixed-language phrasing and dialect shifts without dropping context. *How to orchestrate API calls and stateful tasks while maintaining an uninterrupted vocal flow. *Moving beyond Word Error Rate toward dynamic metrics that measure conversational flow and turn-taking. 🔗Resources: Gemini Audio → https://goo.gle/47uVQrZ Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Google DeepMind Speakers: Valeria Wu, Soham Ray Chapters: 00:00 – Introduction & The State of Real-Time Voice AI 0:50 – Understanding Sierra & TAU 01:48 – Latency 03:52 – Fluid Multilinguality 04:22 – What’s Next?

    Not rated yet
  • Gemma 4 12B: The encoder-free model explained

    · 2 min

    Learn what makes Gemma 4 12B, Google's encoder-free open source language model, unique in the Gemma 4 family. Google DeepMind’s Maarten Grootendorst explains how it processes audio and image inputs without encoders. Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemma 4 Speaker: Maarten Grootendorst

    Not rated yet
  • Understand the Gemma 4 model family

    · 2 min

    Learn about the Gemma 4 family of multimodal open source language models from Google. Google DeepMind’s Maarten Grootendorst walks through all five model sizes across four architectures, from the efficient E2B and E4B models with per-layer embeddings to the encoder-free 12B, the 26B mixture of experts model, and the most capable 31B dense model. Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemma 4 Speaker: Maarten Grootendorst

    Not rated yet
  • 🪄 Gemini Live API in action

    · 1 min

    See what’s new in the Gemini Live API! Thor Schaeff breaks down async function calling, Proactive Audio, real-time context injection with sendClientContent, frontier-level background reasoning in native audio. Products Mentioned: Gemini Live API, Gemini Speaker: Thor Schaeff

    Not rated yet
  • What's new in the Gemini Live API

    · 7 min

    Did you know that Gemini Live API enables low-latency, real-time voice and vision interactions with Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking? Watch along as Google DeepMind’s Thor Schaeff demonstrates: * *Async function* calling for background tool execution * *Proactive audio,* meaning the agent only speaks when relevant * *The context injection* with send_ client_content feature * *Frontier-level* background reasoning with Gemini 3.8 Live Extended Thinking Check out the Gemini Live API today and begin using these native audio experiences for yourself. 🔗 *Resources:* * Gemini Live API overview → https://ai.google.dev/gemini-api/docs/live-api * Live API in Google AI Studio → https://aistudio.google.com/live-api #Gemini #AIDevelopers Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini Live API, Gemini Speaker: Thor Schaeff

    Not rated yet
  • Manage your agents while you’re on the move with the Antigravity Remote Control

    · 48 sec

    The Antigravity Remote Control lets you manage and monitor agents across different machines from a single interface. Launch your long-running agents, monitor them via browser or app, and step in exactly when needed. To get started with Antigravity Remote Control go to https://antigravity.google/docs/remote-control/

    Not rated yet
  • Celebrating one billion Gemma downloads

    · 56 sec

    Google DeepMind's Paige Bailey catches up with developers at the Gemma 1 billion downloads event to hear how they're using Gemma in their work. Watch along and hear about: * Blind and low vision accessibility research * AI race car coaching * Interactive create writing possibilities * Running Gemma 4 locally #Gemma #AIDevelopers Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemma Speakers, Paige Bailey, Daniel Han, Rahul Chand, Selali Adobor, Alex Chen, Miguel Villa Floran, Zack Li, Alan Zhu

    Not rated yet
  • Agentic approaches to processing long videos with Gemini

    · 1 min

    Save this for your next project with heavy video processing 📌 Agentic video understanding transforms how developers process long-form content across demanding applications, leading to massive token reductions, faster latency, and better accuracy. Products Mentioned: Gemini Speaker: Maarten Grootendorst

    Not rated yet
  • Agentic video understanding in Gemini

    · 3 min

    Processing long videos can use a lot of tokens. Learn how to do this more efficiently using our latest agentic video understanding capability available in Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. In this video, Google DeepMind’s Maarten Grootendorst explains how agentic video understanding works, and how this approach reduces token costs while improving accuracy on the parts of the video that actually matter. Resources: https://goo.gle/4xzZaxJ Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini Speaker: Maarten Grootendorst

    Not rated yet
  • Koray Kavukcuoglu on frontier models, coding agents, and building AGI

    · 26 min

    Google DeepMind SVP and Chief AI Architect Koray Kavukcuoglu joins host Logan Kilpatrick to reflect on the journey from DeepMind’s early reinforcement learning milestones to Gemini and what it means to build AGI at Google. Watch along and learn: * What made Gemini 3.7 Flash a breakthrough for engineers * The ambitions of the Gemini 4 pre-training run * What it takes to stay at the frontier of AI research * How co-building AGI with users shapes everything the Google DeepMind team does 00:00 Intro 00:24 From models to coding agents 03:07 Gemini 4 pre-training 04:08 Why the frontier is all that matters 06:38 Leading frontier AI at Google 08:53 Why there's no test for AGI 10:58 Early days at DeepMind 15:08 Atari vs. real-world ambiguity 17:18 20 years of deep learning 18:47 The reality of engineering hill climbs 21:05 Why Google is the place to build AGI 22:19 Parallel model development 23:34 The shift to agentic coding 24:57 What makes models more intelligent Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini Speakers: Logan Kilpatrick, Koray Kavukcuoglu

    Not rated yet
  • Build voice-first apps with Gemini 3.5 Transcribe

    · 1 min

    See how Gemini 3.5 Transcribe allows you to build voice-first interfaces and transcribing multi-speaker recordings, delivering fast, contextually accurate transcriptions ready to be deployed in your apps. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Thor Schaeff

    Not rated yet
  • How to build with Gemini 3.5 Transcribe

    · 4 min

    Learn how to build with Gemini 3.5 Transcribe, our latest transcription model, which is now available on the Interactions API and Live API. Google DeepMind’s Thor Schaeff gives a demo of real-time transcription of email addresses, phone numbers, and multilingual speech, and shows how custom vocabulary and language hints improve accuracy across 85+ supported languages. Subscribe to Google for Developers → https://goo.gle/developers Products Mentioned: Gemini Speaker: Thor Schaeff

    Not rated yet

More in Technology

See all Technology shows