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.

🚀 The team at Google DeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and state-of-the-art semantic quality. 👩‍💻 We built a demo showing how to integrate it across the LlamaIndex ecosystem, from LlamaParse to LlamaAgents: 𝗮𝘂𝗱𝗶𝗼-𝗸𝗯, a knowledge base for your audio notes. With... audio-kb, you can: 🔹 Upload an MP3 or record directly from your terminal 🔹 LlamaParse extracts the transcript from the audio 🔹 Gemini Embedding 2 generates embeddings 🔹 Metadata + vectors are stored in SurrealDB and indexed with HNSW 🔍 Once ingested, you can search all your audio notes directly from the terminal. 🎙️ Perfect for turning voice memos, meetings, or lectures into a searchable knowledge base. 📖 Full blog: 💻 GitHub: ⚡ Try LlamaParse:show more

LlamaIndex 🦙

114,259 subscribers

34,765 views • 3 months ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚀 The team at Google just released the Agents API, a service for building and running custom agents inside a sandboxed Linux environment, and we built a template that gives these agents access to LlamaParse / LiteParse, enabling them to process unstructured documents automatically 📄⚡ Here’s how it works: 🔹 Configure a Git repository where data and outputs will be stored 🔹 Clone the repository into the agent sandbox 🔹 Install the LiteParse CLI, the LlamaParse SDK, and agent skills to use both 🔹 Prompt the agent with a task and watch it process documents autonomously 🤖 The result? An agent that can work directly with messy, real-world documents using LlamaParse and LiteParse within Google’s new agent runtime. Check out the GitHub repository: Get started with LlamaParse:

🚀 The team at Google just released the Agents API, a service for building and running custom agents inside a sandboxed Linux environment, and we built a template that gives these agents access to LlamaParse / LiteParse, enabling them to process unstructured documents automatically 📄⚡ Here’s how it works: 🔹 Configure a Git repository where data and outputs will be stored 🔹 Clone the repository into the agent sandbox 🔹 Install the LiteParse CLI, the LlamaParse SDK, and agent skills to use both 🔹 Prompt the agent with a task and watch it process documents autonomously 🤖 The result? An agent that can work directly with messy, real-world documents using LlamaParse and LiteParse within Google’s new agent runtime. Check out the GitHub repository: Get started with LlamaParse:

LlamaIndex 🦙

21,975 views • 1 month ago

🚀 The Google DeepMind team just added Gemini 3.1 to the Live API, so we built a small demo showing how Gemini voice agents can plug directly into the document processing ecosystem powered by LlamaIndex. 🔥 In this example, we integrate LiteParse to enable fast, fully-local document parsing. With our TUI-based voice assistant, you can literally talk to your terminal: - Speak commands - Trigger live document parsing via tool calls - Hear the agent read back results in real time 🔊 The assistant can extract content from single files or entire folders, leveraging the lightning-fast local parsing that LiteParse provides ⚡ Take a look at the demo👇 👩‍💻 GitHub repo 📚 LiteParse docs

🚀 The Google DeepMind team just added Gemini 3.1 to the Live API, so we built a small demo showing how Gemini voice agents can plug directly into the document processing ecosystem powered by LlamaIndex. 🔥 In this example, we integrate LiteParse to enable fast, fully-local document parsing. With our TUI-based voice assistant, you can literally talk to your terminal: - Speak commands - Trigger live document parsing via tool calls - Hear the agent read back results in real time 🔊 The assistant can extract content from single files or entire folders, leveraging the lightning-fast local parsing that LiteParse provides ⚡ Take a look at the demo👇 👩‍💻 GitHub repo 📚 LiteParse docs

LlamaIndex 🦙

14,766 views • 3 months ago

If you try nothing else today, give the demo at a go - it lets you stream video and audio directly to Gemini 2.0 Flash and get audio back, so you can have a real-time audio conversation about what you can see with the model Feels like science fiction!

If you try nothing else today, give the demo at a go - it lets you stream video and audio directly to Gemini 2.0 Flash and get audio back, so you can have a real-time audio conversation about what you can see with the model Feels like science fiction!

Simon Willison

208,965 views • 1 year ago

Meet Veo 3.1 👋 With Veo 3.1, you can generate videos with richer audio, better narrative control, and enhanced realism. This new update also comes with a suite of additional features built for creative control. Including the ability to: — Extend your videos to make them longer (with audio) — Set the first and last frame of your video to control your output (with audio) — Upload multiple ingredient images to craft your scene (with audio) — Add or remove objects directly in your video These features are available in Flow by Google, the Gemini API, and Google Cloud Vertex AI. Veo 3.1 is also available in the Google Gemini. We’re so excited to see what you create!

Meet Veo 3.1 👋 With Veo 3.1, you can generate videos with richer audio, better narrative control, and enhanced realism. This new update also comes with a suite of additional features built for creative control. Including the ability to: — Extend your videos to make them longer (with audio) — Set the first and last frame of your video to control your output (with audio) — Upload multiple ingredient images to craft your scene (with audio) — Add or remove objects directly in your video These features are available in Flow by Google, the Gemini API, and Google Cloud Vertex AI. Veo 3.1 is also available in the Google Gemini. We’re so excited to see what you create!

Google AI

71,238 views • 8 months ago

Dump all the images, videos, text, and audio data that you have into Supabase (storage + database), and make them searchable using the new Gemini Embedding 2 model! I know we all miss him a lot!

Dump all the images, videos, text, and audio data that you have into Supabase (storage + database), and make them searchable using the new Gemini Embedding 2 model! I know we all miss him a lot!

Tyler Shukert

11,446 views • 3 months ago

Guardians of the Wild Sky is a new survival-crafting game like Pokémon and Palworld 🔹The world is inhabited by creatures called "Guardians" that you can capture and bond with using capture crystals 🔹Guardians help with exploration via flying, surfing, and gliding 🔹Also used in combat, and automating base tasks such as farming, crafting, and resource harvesting 🔹Fight alongside your Guardians, issue commands, or SHAPESHIFT into them to wield their powers directly. 🔹Build bases - you can even construct flying castles to move your entire base to new locations 🔹Use airships for faster travel and exploration. You can build crafting stations, cook, and farm directly on your ship 🔹Team up with friends to crew ships, man cannons, and execute coordinated assaults on enemies from both air and ground 🔹Discover towns, trade with merchants, and uncover ancient mysteries 🔹Demo available during Steam Next Fest

Guardians of the Wild Sky is a new survival-crafting game like Pokémon and Palworld 🔹The world is inhabited by creatures called "Guardians" that you can capture and bond with using capture crystals 🔹Guardians help with exploration via flying, surfing, and gliding 🔹Also used in combat, and automating base tasks such as farming, crafting, and resource harvesting 🔹Fight alongside your Guardians, issue commands, or SHAPESHIFT into them to wield their powers directly. 🔹Build bases - you can even construct flying castles to move your entire base to new locations 🔹Use airships for faster travel and exploration. You can build crafting stations, cook, and farm directly on your ship 🔹Team up with friends to crew ships, man cannons, and execute coordinated assaults on enemies from both air and ground 🔹Discover towns, trade with merchants, and uncover ancient mysteries 🔹Demo available during Steam Next Fest

Game Hunter

246,706 views • 4 months ago

🧑‍💼⚡ Transcribe your meetings into actionable notes! Last summer, we launched AI Transcribe to turn audio and video files—or even links—into editable, searchable text. Now we’ve taken it a step further. Here’s what the AI Meeting Note-taker does: ✅ Transcribes conversations from your mic or browser tab 🧠 Identifies different speakers with automatic voice recognition 📝 Summarizes key points so you can catch up quickly 🗄️ Saves everything directly to your Evernote account for safe keeping Try it out at your next meeting or brainstorm and let us know what you think, link in the thread!

🧑‍💼⚡ Transcribe your meetings into actionable notes! Last summer, we launched AI Transcribe to turn audio and video files—or even links—into editable, searchable text. Now we’ve taken it a step further. Here’s what the AI Meeting Note-taker does: ✅ Transcribes conversations from your mic or browser tab 🧠 Identifies different speakers with automatic voice recognition 📝 Summarizes key points so you can catch up quickly 🗄️ Saves everything directly to your Evernote account for safe keeping Try it out at your next meeting or brainstorm and let us know what you think, link in the thread!

Evernote

11,096 views • 11 months ago

🔥 Distance From The Ball 🔥 If you suffer from not knowing how far to stand from the ball with your irons, watch this video below 🔹Imagine you are giving someone a “thumbs up” 🔹Place your fist up against your belt buckle and rest the golf club on the tip of your thumb 🔹This will give you the perfect distance from the golf ball when using your irons Give it a try and see how it feels 👊🏼

🔥 Distance From The Ball 🔥 If you suffer from not knowing how far to stand from the ball with your irons, watch this video below 🔹Imagine you are giving someone a “thumbs up” 🔹Place your fist up against your belt buckle and rest the golf club on the tip of your thumb 🔹This will give you the perfect distance from the golf ball when using your irons Give it a try and see how it feels 👊🏼

Ryan Mouque

78,425 views • 2 years ago

Matryoshka dolls 🪆 = the key to AI efficiency. Gemini Embedding 2 leverages Matryoshka Representation Learning (MRL) so you can: 🔹 Dynamically truncate vectors for high-speed candidate matching without losing precision 🔹Slash database costs by choosing a smaller storage footprint without re-indexing 🔹 Adapt to any latency budget or accuracy requirement 📈💸 Learn how this helps build more efficient RAG, semantic search, and more:

Matryoshka dolls 🪆 = the key to AI efficiency. Gemini Embedding 2 leverages Matryoshka Representation Learning (MRL) so you can: 🔹 Dynamically truncate vectors for high-speed candidate matching without losing precision 🔹Slash database costs by choosing a smaller storage footprint without re-indexing 🔹 Adapt to any latency budget or accuracy requirement 📈💸 Learn how this helps build more efficient RAG, semantic search, and more:

Google for Developers

10,746 views • 1 month ago

NEW: Google releases EmbeddingGemma, a state-of-the-art multilingual embedding model perfect for on-device use cases! At only 308M params, the model can run 100% locally in your browser! 🤯 Explore your documents in an interactive 3D universe with our demo: "The Semantic Galaxy"

NEW: Google releases EmbeddingGemma, a state-of-the-art multilingual embedding model perfect for on-device use cases! At only 308M params, the model can run 100% locally in your browser! 🤯 Explore your documents in an interactive 3D universe with our demo: "The Semantic Galaxy"

Xenova

23,338 views • 9 months ago

The hardest part of learning? Finding your own blind spots 📚 Upload an audio file of you explaining a topic to Gemini 3 Flash in the Google Gemini, and It can pinpoint the info you missed and even create a quiz to help you fill the gaps.

The hardest part of learning? Finding your own blind spots 📚 Upload an audio file of you explaining a topic to Gemini 3 Flash in the Google Gemini, and It can pinpoint the info you missed and even create a quiz to help you fill the gaps.

Google

73,314 views • 6 months ago

🎙️ How to go Live with Search: Open the Google app on Android or iOS and tap the Live icon under the Search bar. From there, you can ask your question out loud to get a helpful audio response, then continue the conversation with follow-up questions or dive deeper with helpful web links.

🎙️ How to go Live with Search: Open the Google app on Android or iOS and tap the Live icon under the Search bar. From there, you can ask your question out loud to get a helpful audio response, then continue the conversation with follow-up questions or dive deeper with helpful web links.

Google

42,076 views • 3 months ago

The AI video content being made with the Google Gemini is blowing our minds¹ 🤯 With our latest #PixelDrop, you can now upload images directly from your camera roll, enter a prompt to describe a scene, and let Gemini bring it all to life:²

The AI video content being made with the Google Gemini is blowing our minds¹ 🤯 With our latest #PixelDrop, you can now upload images directly from your camera roll, enter a prompt to describe a scene, and let Gemini bring it all to life:²

Made by Google

44,512 views • 11 months ago

Imagine integrating instant video dubbing into your app. With the Gemini API, now you can. Watch Gemini 3.5 Live Translate process speech-to-speech in near real-time, streaming translated audio directly from a video source - going from English to Hindi in seconds! 🔥 📺 Full video:

Imagine integrating instant video dubbing into your app. With the Gemini API, now you can. Watch Gemini 3.5 Live Translate process speech-to-speech in near real-time, streaming translated audio directly from a video source - going from English to Hindi in seconds! 🔥 📺 Full video:

Google for Developers

12,730 views • 14 days ago

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

AshutoshShrivastava

122,990 views • 1 year ago

Having fun playing with new native audio capabilities in Gemini 1.5 Pro! ♊ Here’s a demo using audio from the #GoogleIO keynote with examples you can try: transcription, word-level timecodes, and searching audio by drawing. (🔊Video has sound)

Having fun playing with new native audio capabilities in Gemini 1.5 Pro! ♊ Here’s a demo using audio from the #GoogleIO keynote with examples you can try: transcription, word-level timecodes, and searching audio by drawing. (🔊Video has sound)

Alexander Chen

77,091 views • 2 years ago

Today we’re announcing a set of updates, starting with a new experimental feature for paid subscribers, audio uploads. You can upload an audio clip of your choice, and extend this clip either forward or backward by 32 seconds using up to 2 minutes of context. Audio uploads greatly enrich your prompting vocabulary. You can use audio to set tempo and mood, and explore from there. Maybe you’ve got a great intro but don’t know where to go next, or a full mix that’s missing the perfect bridge–in both cases, Udio can provide inspiration. Check out the video below for some examples (we’ve had a lot of fun with this).

Today we’re announcing a set of updates, starting with a new experimental feature for paid subscribers, audio uploads. You can upload an audio clip of your choice, and extend this clip either forward or backward by 32 seconds using up to 2 minutes of context. Audio uploads greatly enrich your prompting vocabulary. You can use audio to set tempo and mood, and explore from there. Maybe you’ve got a great intro but don’t know where to go next, or a full mix that’s missing the perfect bridge–in both cases, Udio can provide inspiration. Check out the video below for some examples (we’ve had a lot of fun with this).

udio

130,827 views • 2 years ago

Highguard is being called a "PvP Raid Shooter" 🔹Each team has a base to defend 🔹Goal is to secure the "Shieldbreaker" and use it to raid the enemy base before they destroy yours 🔹Matches can last between 8 to 30 minutes, spanning 1 to 4 raid cycles 🔹Wardens on launch: Atticus, Una, Slade, Mara, Redmane, Scarlet, Condor, Kai 🔹Teams vote on one of four unique bases 🔹Matches start with one minute to plan defenses 🔹Players select their Warden and loadout(Primary, Secondary, and Raid Tool) 🔹Use 5 "wall reinforcements" to armor up specific parts of your base 🔹Teams mount up and ride out into the open map to explore POIs 🔹Loot upgraded guns, armor, saddles, magical amulets 🔹Loot upgrades globally as the match progresses 🔹Vesper is a resource mined, gained from kills, or earned from raids that is used to purchase better gear from "Trader Flynn" 🔹Shieldbreaker spawns randomly inside a storm at one of three locations, it allows a team to start a raid on the enemy base, but can be dropped and stolen 🔹Siege Tower is summoned when a raid begins to break the enemy's outer shield and serves as the attacker's spawn point 🔹The goal is to reduce the enemy base's health to zero by destroying generators or the anchor stone, or by successfully defending your base 🔹Year worth of post launch content prepared

Highguard is being called a "PvP Raid Shooter" 🔹Each team has a base to defend 🔹Goal is to secure the "Shieldbreaker" and use it to raid the enemy base before they destroy yours 🔹Matches can last between 8 to 30 minutes, spanning 1 to 4 raid cycles 🔹Wardens on launch: Atticus, Una, Slade, Mara, Redmane, Scarlet, Condor, Kai 🔹Teams vote on one of four unique bases 🔹Matches start with one minute to plan defenses 🔹Players select their Warden and loadout(Primary, Secondary, and Raid Tool) 🔹Use 5 "wall reinforcements" to armor up specific parts of your base 🔹Teams mount up and ride out into the open map to explore POIs 🔹Loot upgraded guns, armor, saddles, magical amulets 🔹Loot upgrades globally as the match progresses 🔹Vesper is a resource mined, gained from kills, or earned from raids that is used to purchase better gear from "Trader Flynn" 🔹Shieldbreaker spawns randomly inside a storm at one of three locations, it allows a team to start a raid on the enemy base, but can be dropped and stolen 🔹Siege Tower is summoned when a raid begins to break the enemy's outer shield and serves as the attacker's spawn point 🔹The goal is to reduce the enemy base's health to zero by destroying generators or the anchor stone, or by successfully defending your base 🔹Year worth of post launch content prepared

Hunter

34,133 views • 4 months ago

Google just released its own MCP (Model Control Plane) server for Stitch, turning LLM coding agents into UI-savvy collaborators. The new Stitch MCP Server pipes designs directly into your IDE. 🔹 Generate new screens 🔹 Fetch code from any design 🔹 Give your agent full visual context

Google just released its own MCP (Model Control Plane) server for Stitch, turning LLM coding agents into UI-savvy collaborators. The new Stitch MCP Server pipes designs directly into your IDE. 🔹 Generate new screens 🔹 Fetch code from any design 🔹 Give your agent full visual context

Wes Roth

138,465 views • 5 months ago