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.

Process multimodal media entirely offline with zero server calls. The modular design lets you drop unused vision and audio pieces to save memory, while flexible dimension sizes reduce storage requirements by up to 6x in local databases. Since all media connects directly without messy translation, you can easily build... show more

Google for Developers

2,578,037 subscribers

60,524 views • 19 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

2 Comments

Google for Developers19 days ago

EmbeddingGemma 2 from @googlegemma, our compact 740M-parameter AI model built specifically for on-device and edge apps, has arrived. While the first-generation model delivered best-in-class text embedding, EmbeddingGemma 2 natively understands it all, connecting text, images, audio, and video in one shared space. This means you can search across different formats like text, images, audio, and video, without having to manually organize, translate, or label them first.

Google for Developers19 days ago

— Weights are live on @HuggingFace and @Kaggle — Get out-of-the-box support for LiteRT, MediaPipe, @LangChain, and @llama_index — Start Mapping:

Related Videos

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

The QVAC SDK puts the "brain" directly into your pocket. From real-time on-device translation to multimodal understanding, build apps that work everywhere, even 30,000 feet in the air. Local AI is here: 💡Offline-First: No cloud, no latency, no "Department of Truth". 💻 Universal API: One codebase for iOS, Android, macOS, and Linux. 🔍 Multimodal: Understanding text, audio, and images without a server. If you can dream it, you can build it. The era of Stable Intelligence has begun. Start building:

QVAC

36,652 views • 6 months ago

Gemini 3.1 Flash-Lite is the model to build always on multimodal AI Agents. I just built a memory agent with Google ADK that runs 24/7. Feed it text, images, audio, video or PDFs. It reads, connects and consolidates everything while you sleep. 100% Opensource code.

Gemini 3.1 Flash-Lite is the model to build always on multimodal AI Agents. I just built a memory agent with Google ADK that runs 24/7. Feed it text, images, audio, video or PDFs. It reads, connects and consolidates everything while you sleep. 100% Opensource code.

Shubham Saboo

24,930 views • 7 months ago

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!

Omar Sanseviero

125,865 views • 4 months ago

Wait Xiaomi has also released the best 9B model in the world?! This model is based on Qwen-9B... And you can easily run it even on 8GB of memory! - MIT license - Multimodal (image + text) - Solid for coding/agentic tasks Perfect to use locally and offline... even on a laptop with unified memory!

Wait Xiaomi has also released the best 9B model in the world?! This model is based on Qwen-9B... And you can easily run it even on 8GB of memory! - MIT license - Multimodal (image + text) - Solid for coding/agentic tasks Perfect to use locally and offline... even on a laptop with unified memory!

Paul Couvert

85,496 views • 1 month ago

Sign language AI should not depend on Wi-Fi or expect Deaf folks to do all the adapting. Meet KawanIsyarat, a local-first mobile tool bridging BISINDO and spoken Indonesian offline using Gemma 4. Gemma 4 handles all vision, audio, and text processing directly on-device. Congrats to the team on their Cactus category win for the Gemma 4 Good Hackathon.

Sign language AI should not depend on Wi-Fi or expect Deaf folks to do all the adapting. Meet KawanIsyarat, a local-first mobile tool bridging BISINDO and spoken Indonesian offline using Gemma 4. Gemma 4 handles all vision, audio, and text processing directly on-device. Congrats to the team on their Cactus category win for the Gemma 4 Good Hackathon.

Google Gemma

21,615 views • 1 month ago

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with Qdrant and taught by Dylan Couzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the mobile app. Enroll for free:

Build an assistant that can store and search what it sees, hears, and is told, all without leaving the device. In Building AI Assistants with On-Device Memory, you'll build a local memory system that recalls text, voice, and images, and teach it to recognize something new from a few photos. Built in partnership with Qdrant and taught by Dylan Couzon, Developer Experience Engineer at Qdrant. This course also includes our new AI coding lab, so you can practice building with an AI coding agent from the mobile app. Enroll for free:

DeepLearning.AI

17,175 views • 1 month ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

162,636 views • 7 months ago

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

New short course: Open Source Models with Hugging Face 🤗, taught by Maria Khalusova, Marc Sun, and Younes Belkada! Hugging Face has been a game changer by letting you quickly grab any of hundreds of thousands of already-trained open source models to assemble into new applications. This course teaches you best practices for building this way, including how to search and choose among models. You’ll learn to use the Transformers library and walk through multiple models for text, audio, and image processing, including zero-shot image segmentation, zero-shot audio classification, and speech recognition. You'll also learn to use multimodal models for visual question answering, image search, and image captioning. Finally, you’ll learn how to demo what you build locally, on the cloud, or via an API using Gradio and Hugging Face Spaces. You can sign up here:

Andrew Ng

224,699 views • 2 years ago

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

SwiftUI: You can chain free and open-source STT, TTS, and LLMs to build voice/vision apps with Core AI. Here is a demo I was experimenting with: - Whisper: Speech-to-text - Kokoro-82M: Text-to-speech - Qwen3-VL 2B: Vision I converted Pocket TTS and VibeVoice to Core AI models and tried with Gemma 4. All is working great.

Amos Gyamfi

80,976 views • 3 months ago

11k people are using the ElevenLabs MCP server in Claude. It connects to your ElevenLabs account and lets you generate speech, sound effects, and music directly in Claude. Generate audio with ElevenLabs without friction.

11k people are using the ElevenLabs MCP server in Claude. It connects to your ElevenLabs account and lets you generate speech, sound effects, and music directly in Claude. Generate audio with ElevenLabs without friction.

ElevenLabs Developers

28,663 views • 7 months ago

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:

New short course: Building Multimodal Search and RAG", by Weaviate AI Database's Sebastia(N_) Witalec ✊🏽✊🏾✊🏿. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This technique is also used to train multimodal embedding models that capture semantic similarity across different modalities like text, images, and audio. These multimodal embeddings can be used to build multimodal search and RAG systems. In this course, you'll learn how contrastive learning works, and how to add multimodality to RAG – so your models can draw on diverse, relevant context to answer questions. For example, a query about a financial report might synthesize information from text snippets, graphs, tables, and slides. You will also learn how visual instruction tuning lets you integrate image understanding into language models, and build a multi-vector recommender system using Weaviate’s open-source vector database. Please sign up here:

Andrew Ng

104,490 views • 2 years ago

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

Andrew Ng

107,967 views • 2 years ago

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Paul Couvert

727,356 views • 6 months ago

You can build Lovable apps from Slack directly. You can also build agents on Lovable and add those to Slack directly for your team to use! 🚀

You can build Lovable apps from Slack directly. You can also build agents on Lovable and add those to Slack directly for your team to use! 🚀

Suhem Parack

272,626 views • 1 month ago

Your app can now search the web for images. Web search in the Responses API now supports image results in addition to text results, so you can build apps that surface products, places, visual references, and source links for inspiration.

Your app can now search the web for images. Web search in the Responses API now supports image results in addition to text results, so you can build apps that surface products, places, visual references, and source links for inspiration.

OpenAI Developers

155,571 views • 4 months ago

Supabase is now listed as a ChatGPT app! It allows you to do anything that Supabase MCP allows, and you can just use it as a persisted storage layer, or you can combine it with other apps to build complex workflows! The possibilities are endless!

Supabase is now listed as a ChatGPT app! It allows you to do anything that Supabase MCP allows, and you can just use it as a persisted storage layer, or you can combine it with other apps to build complex workflows! The possibilities are endless!

Tyler Shukert

17,181 views • 6 months ago

Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with deepset, makers of Haystack, and taught by Tuana, who is the developer relations lead for Haystack at deepset. Generative AI technology is changing rapidly and it can be challenging to integrate APIs from different LLMs, vector databases, and various tools such as web search. In this course, you will learn how to use the Haystack framework to make your development process more modular, allowing you to manage complexity and focus more on building your application. In detail, you’ll: - Build a RAG pipeline using Haystack’s main building blocks – components, pipelines, and document stores. - Create custom components in your pipeline by building a Hacker News summarizer that extends your app’s ability to access APIs. - Use conditional routing to create a branching pipeline with a fallback to web search mechanism when the LLM does not have the necessary context to respond to the user's query. - Build a self-reflecting agent for named entity recognition that loops using an output validator custom component. - Create a chat agent using OpenAI's function-calling capabilities which allow you to provide Haystack pipelines as tools to the LLM, enhancing that agent's capabilities. By the end of this course, you will learn a high-level orchestration framework that can help make your applications flexible, extendible, and maintainable, even as the technology stack changes, new user needs arise, and you add new features to your application. Please sign up here:

Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with deepset, makers of Haystack, and taught by Tuana, who is the developer relations lead for Haystack at deepset. Generative AI technology is changing rapidly and it can be challenging to integrate APIs from different LLMs, vector databases, and various tools such as web search. In this course, you will learn how to use the Haystack framework to make your development process more modular, allowing you to manage complexity and focus more on building your application. In detail, you’ll: - Build a RAG pipeline using Haystack’s main building blocks – components, pipelines, and document stores. - Create custom components in your pipeline by building a Hacker News summarizer that extends your app’s ability to access APIs. - Use conditional routing to create a branching pipeline with a fallback to web search mechanism when the LLM does not have the necessary context to respond to the user's query. - Build a self-reflecting agent for named entity recognition that loops using an output validator custom component. - Create a chat agent using OpenAI's function-calling capabilities which allow you to provide Haystack pipelines as tools to the LLM, enhancing that agent's capabilities. By the end of this course, you will learn a high-level orchestration framework that can help make your applications flexible, extendible, and maintainable, even as the technology stack changes, new user needs arise, and you add new features to your application. Please sign up here:

Andrew Ng

53,887 views • 2 years ago

Want to build with AI for free? With local models in Workshop, you can build websites, dashboards, internal tools, workflows, prototypes, and more. That means: - Zero API costs - Offline access - Full privacy Try local models today in Workshop Desktop.

Want to build with AI for free? With local models in Workshop, you can build websites, dashboards, internal tools, workflows, prototypes, and more. That means: - Zero API costs - Offline access - Full privacy Try local models today in Workshop Desktop.

Workshop AI

923,614 views • 6 months ago