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.

We got a fully open source, end-to-end, conversational AI that you can run on a MacBook Air before Multi-modal GPT4o!

Vaibhav (VB) Srivastav

32,182 subscribers

209,098 views • 1 year ago •via X (Twitter)

Science & Technology Gaming Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Sean Austin1 year ago

That’s all using the open source s2s code?

MAULIK MANDALI1 year ago

GitHub or huggingface link

Lincoln 🇿🇦1 year ago

Wow.

Sentient1 year ago

Getting close where may be these models can run on high end phones

kiiwee1 year ago

whats the t2s latency

Cognevo1 year ago

This is groundbreaking!

Dhruv1 year ago

This is great.

Santiago1 year ago

Cool!

morgensol1 year ago

AI is what the internet was in the 1990s. A silent revolution. Og actually quite refreshing. I am python nerd where working with with machine learning and llms us second nature. There is no magic, though I well understand how an AU can be viewed as such.

James (Jake) Gearon1 year ago

plzzzz link plz plz

Related Videos

Physical AI just got a major data upgrade. NATIX joins The Autoware Foundation 🚗🚌🏎️ as a premium member 🌟 We will provide global multi-camera driving data for the open-source end-to-end autonomous driving model.

Physical AI just got a major data upgrade. NATIX joins The Autoware Foundation 🚗🚌🏎️ as a premium member 🌟 We will provide global multi-camera driving data for the open-source end-to-end autonomous driving model.

NATIX Network

11,492 views • 3 months ago

We shouldn’t lose context every time we switch AI tools. Introducing SharedContext ✨ - End-to-end encrypted - Portable across devices - Persistent across Claude, Cursor, Codex - Shareable by link - same exact context - Synced on the Blockchain Only you can decrypt it. Fully Open Source and free. "npm i -g ai-singlecontext" Give it a try.

We shouldn’t lose context every time we switch AI tools. Introducing SharedContext ✨ - End-to-end encrypted - Portable across devices - Persistent across Claude, Cursor, Codex - Shareable by link - same exact context - Synced on the Blockchain Only you can decrypt it. Fully Open Source and free. "npm i -g ai-singlecontext" Give it a try.

Vitto Rivabella

21,535 views • 5 months ago

🆕 Introducing JAT, the first open-source multi-modal, multi-task multi-domain agent! 🤖 A step toward open generalist agents! 🚀 📰 Blog:

🆕 Introducing JAT, the first open-source multi-modal, multi-task multi-domain agent! 🤖 A step toward open generalist agents! 🚀 📰 Blog:

Quentin Gallouédec

73,212 views • 2 years ago

You can now build AI Agents using a no-code drag and drop interface. Fully open-source.

You can now build AI Agents using a no-code drag and drop interface. Fully open-source.

Lior Alexander

87,456 views • 1 year ago

Build a conversational voice bot with 1 second voice-to-voice latency with Modal, Pipecat AI, and open models. Modal works seamlessly with WebRTC, WebSockets, and tunneling to squash latency to an absolute minimum.

Build a conversational voice bot with 1 second voice-to-voice latency with Modal, Pipecat AI, and open models. Modal works seamlessly with WebRTC, WebSockets, and tunneling to squash latency to an absolute minimum.

Modal

29,559 views • 8 months ago

If your AI needs a wire to work, it isn't yours. QVAC is the local-first engine designed to run anywhere, even where the internet can't reach. Fully autonomous. Fully open source. Fully sovereign. If you can dream it, you can build it. Even in another galaxy. Start building the future of edge AI:

If your AI needs a wire to work, it isn't yours. QVAC is the local-first engine designed to run anywhere, even where the internet can't reach. Fully autonomous. Fully open source. Fully sovereign. If you can dream it, you can build it. Even in another galaxy. Start building the future of edge AI:

QVAC

7,044,078 views • 2 months ago

✂️ Introducing: Shortest! Shortest is an open-source AI-powered testing framework that allows developers to write end-to-end tests in plain English, as simple as: shortest(“user can sign up and create a $5 product”) More tests = fewer regressions as AI writes and ships code.

✂️ Introducing: Shortest! Shortest is an open-source AI-powered testing framework that allows developers to write end-to-end tests in plain English, as simple as: shortest(“user can sign up and create a $5 product”) More tests = fewer regressions as AI writes and ships code.

Sahil Lavingia

722,543 views • 1 year ago

You can build an entire movie franchise on a MacBook Air. RAINBOW SUN.

You can build an entire movie franchise on a MacBook Air. RAINBOW SUN.

Ryan Lightbourn

45,563 views • 2 months ago

📧Mailmodo AI is an end-to-end conversational agent for email marketing. Now startups can plan, design, automate, and analyze entire email campaigns in one conversation.

📧Mailmodo AI is an end-to-end conversational agent for email marketing. Now startups can plan, design, automate, and analyze entire email campaigns in one conversation.

Y Combinator

16,012 views • 9 months ago

Agents can negotiate, pay, and execute - but none of it holds together. Today we are introducing Internet Court, which is the open skill that connects the entire agentic commerce stack into one flow, so any two agents can run a deal end to end. →

Agents can negotiate, pay, and execute - but none of it holds together. Today we are introducing Internet Court, which is the open skill that connects the entire agentic commerce stack into one flow, so any two agents can run a deal end to end. →

Internet Court

409,489 views • 17 days ago

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

You can run local AI models up to 120B without a $10,000 Mac Studio This phone-sized device is your own server for open-source models. 100% local and private. And you can use it to: - Power an agent like OpenClaw 24/7 - Completely replace a chatbot - Literally anything that requires an API It’s called Tiiny, and, once again, you can run the latest open-source models on it. Link below

Paul Couvert

41,185 views • 4 months ago

we built pookie it's a helper that lives inside Slack it can search messages, generate memes, run code, and connect to your tools (Linear, GitHub, Stripe, even my bank!) fully open source and self hostable

we built pookie it's a helper that lives inside Slack it can search messages, generate memes, run code, and connect to your tools (Linear, GitHub, Stripe, even my bank!) fully open source and self hostable

Aiden Bai

45,831 views • 2 months ago

Real-time video agents are here. Today, we’re sharing how we built Runway Characters, allowing you to turn one image into a fully expressive, conversational video agent streaming at 24 frames per second in HD. With just 1.75 seconds of end-to-end latency. Learn more below.

Real-time video agents are here. Today, we’re sharing how we built Runway Characters, allowing you to turn one image into a fully expressive, conversational video agent streaming at 24 frames per second in HD. With just 1.75 seconds of end-to-end latency. Learn more below.

Runway

148,315 views • 2 months ago

ICYMI - at Lens Fest we launched Project Jade, our Niantic Spatial 🌎 real-world embodied AI experience on @Spectacles. it’s the convergence of 4 simultaneous technological breakthroughs delivering magic: AR glasses, geospatial intelligence, multi-modal gen AI, & conversational AI.

ICYMI - at Lens Fest we launched Project Jade, our Niantic Spatial 🌎 real-world embodied AI experience on @Spectacles. it’s the convergence of 4 simultaneous technological breakthroughs delivering magic: AR glasses, geospatial intelligence, multi-modal gen AI, & conversational AI.

asim ᯅ

26,029 views • 9 months ago

We made it to Taco Bell! • without a disengagement • on a comma three • in a stock, production, car • using open source code • by the end of the year

We made it to Taco Bell! • without a disengagement • on a comma three • in a stock, production, car • using open source code • by the end of the year

comma

455,100 views • 3 years ago

This is a full end-to-end demo on how you can create your own product copilot using OpenCopilot: It's open source -> Chatting with products is truly an amazing experience instead of clicking around. Give it a try and let me know what you think!

This is a full end-to-end demo on how you can create your own product copilot using OpenCopilot: It's open source -> Chatting with products is truly an amazing experience instead of clicking around. Give it a try and let me know what you think!

Mo Gharabat 🦇

22,331 views • 2 years ago

Introducing local Reachy Mini conversations: free chats forever! So fast that we had to hardcode delays to stop it from interrupting you mid-sentence. We built an open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS Run it anywhere you run local LMs. Video shows DGX Spark and a 36GB M3 Pro MacBook. Blog:

Introducing local Reachy Mini conversations: free chats forever! So fast that we had to hardcode delays to stop it from interrupting you mid-sentence. We built an open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS Run it anywhere you run local LMs. Video shows DGX Spark and a 36GB M3 Pro MacBook. Blog:

Andi Marafioti

76,150 views • 2 months ago

Joshua Van on Alexandre Pantoja: A fight to end like that, I think we should run it back. #HelwaniShow

Joshua Van on Alexandre Pantoja: A fight to end like that, I think we should run it back. #HelwaniShow

Jed I. Goodman ©

14,243 views • 7 months ago

Today we’re releasing K2 Think V2, our most capable open-source reasoning model to date. This is a fully sovereign model: trained end-to-end on IFM-curated and synthesized data, with complete transparency from pre-training through final reasoning alignment.

Today we’re releasing K2 Think V2, our most capable open-source reasoning model to date. This is a fully sovereign model: trained end-to-end on IFM-curated and synthesized data, with complete transparency from pre-training through final reasoning alignment.

MBZUAI

287,725 views • 6 months ago

Open-source might have just caught up to NanoBanana dx8152 trained a Qwen Edit LoRA that nails multi-angle shots. Here’s a product video I made using it with Kling Start/End frames. Link to LoRA below 👇

Open-source might have just caught up to NanoBanana dx8152 trained a Qwen Edit LoRA that nails multi-angle shots. Here’s a product video I made using it with Kling Start/End frames. Link to LoRA below 👇

Miguel | AP

61,137 views • 8 months ago