Loading video...

Video Failed to Load

Go Home

New tutorial: Build a real-time AI yoga instructor in Python 🧘 Combining voice, video, pose detection, and LLM feedback, your instructor sees your pose, analyzes your form, and gives corrections. Let's break it down ↓

getstream_io's profile picture

Stream

12,274 subscribers

55,986 views • 9 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

real-time vision in your browser 🔥 try out YOLO26 for pose estimation and detection built on WebGPU ⚡️
0:21

real-time vision in your browser 🔥 try out YOLO26 for pose estimation and detection built on WebGPU ⚡️

merve

46,395 views • 7 months ago

NEW: BodyPark launched a pocket-sized AI camera that coaches your workouts. BodyPark ATOM watches your form, counts your reps, gives real-time voice feedback, and builds workout plans around your goals and equipment. -34-point skeletal tracking maps your movement -Auto-counts reps so you can stay in the set -Voice cues correct your form in real time -160° ultra-wide camera captures full-body exercises -SmartPath tracks bar path, center of gravity, range of motion, and power -AI creates workouts for strength, HIIT, Pilates, mobility, and recovery -MagMount design clips onto racks, tripods, desks, or gym setups Pricing is $219.
0:52

NEW: BodyPark launched a pocket-sized AI camera that coaches your workouts. BodyPark ATOM watches your form, counts your reps, gives real-time voice feedback, and builds workout plans around your goals and equipment. -34-point skeletal tracking maps your movement -Auto-counts reps so you can stay in the set -Voice cues correct your form in real time -160° ultra-wide camera captures full-body exercises -SmartPath tracks bar path, center of gravity, range of motion, and power -AI creates workouts for strength, HIIT, Pilates, mobility, and recovery -MagMount design clips onto racks, tripods, desks, or gym setups Pricing is $219.

Ritwik Pavan

889,169 views • 1 month ago

What's the real moat in AI? It's not your model. It's not your inference. It's your HUMANS. Human engagement. Human feedback. I break it down in this video🍿
1:36

What's the real moat in AI? It's not your model. It's not your inference. It's your HUMANS. Human engagement. Human feedback. I break it down in this video🍿

Zeb Evans

415,320 views • 5 months ago

Today we're launching Paxel: a free tool that analyzes your Claude, Codex, and Cursor coding sessions and gives you a profile of how you build with AI. It runs locally inside Docker, and your code never leaves your machine. Try it at
2:03

Today we're launching Paxel: a free tool that analyzes your Claude, Codex, and Cursor coding sessions and gives you a profile of how you build with AI. It runs locally inside Docker, and your code never leaves your machine. Try it at

Y Combinator

586,432 views • 3 months ago

Want to add AI POWER to your setup? ⚡ The Google Coral USB Accelerator is a compact plug-in device that brings rapid machine learning right to your computer. It speeds up tasks like real-time video inference and object detection, all without bogging down your CPU
0:41

Want to add AI POWER to your setup? ⚡ The Google Coral USB Accelerator is a compact plug-in device that brings rapid machine learning right to your computer. It speeds up tasks like real-time video inference and object detection, all without bogging down your CPU

NetworkChuck

17,048 views • 18 days ago

GROK 4 SEES, TALKS, AND THINKS OUT LOUD It doesn’t just chat - it watches, analyzes, and answers in real time. Grok 4’s voice mode is scary good now: more human, less robot, and yes - it speaks Spanish, French, Japanese, and even rambles like it’s got thoughts of its own. You can literally point your phone at anything mid-chat - docs, random objects, full scenes - and it’ll break it down like an overachieving tour guide. The future’s multitasking - and it’s judging your coffee order. Welcome to your pocket-sized, opinionated genius. Source: tetsuo
0:50

GROK 4 SEES, TALKS, AND THINKS OUT LOUD It doesn’t just chat - it watches, analyzes, and answers in real time. Grok 4’s voice mode is scary good now: more human, less robot, and yes - it speaks Spanish, French, Japanese, and even rambles like it’s got thoughts of its own. You can literally point your phone at anything mid-chat - docs, random objects, full scenes - and it’ll break it down like an overachieving tour guide. The future’s multitasking - and it’s judging your coffee order. Welcome to your pocket-sized, opinionated genius. Source: tetsuo

Mario Nawfal

5,083,699 views • 1 year ago

#Mentalhealthmatters Let's break the silence and talk about it. Your voice matters, and so do your feelings. Speak up, reach out, and let's support each other. Recorded this video for a project, thought I'd share it with you all! 😊🙏🏻
0:53

#Mentalhealthmatters Let's break the silence and talk about it. Your voice matters, and so do your feelings. Speak up, reach out, and let's support each other. Recorded this video for a project, thought I'd share it with you all! 😊🙏🏻

Shivam

13,351 views • 10 months ago

built ai interview glasses that clones your voice and delivers perfect answers in real time
0:31

built ai interview glasses that clones your voice and delivers perfect answers in real time

Eddy Xu

630,533 views • 1 year ago

Clicky is an amazing tool so I forked it and added "proactive tutor mode": It watches your screen and teaches you *without you asking anything*. Every time you stop using your keyboard or your cursor, it gives you instructions/feedback. Watch it teach me Figma in real time. Two additional changes in my fork: - auto copy the llm response to clipboard, when it helps you with writing (it helped me write this tweet) - it only takes a screenshot of the window you are focused on, reducing llm confusion
1:19

Clicky is an amazing tool so I forked it and added "proactive tutor mode": It watches your screen and teaches you *without you asking anything*. Every time you stop using your keyboard or your cursor, it gives you instructions/feedback. Watch it teach me Figma in real time. Two additional changes in my fork: - auto copy the llm response to clipboard, when it helps you with writing (it helped me write this tweet) - it only takes a screenshot of the window you are focused on, reducing llm confusion

Dan Peguine

126,441 views • 5 months ago

You live in Dubai and got a feedback on the quality of public facilities, infrastructure, roads, and public spaces? Here’s “Madinati” an AI-powered app taking and implementing your feedback in real time.
1:03

You live in Dubai and got a feedback on the quality of public facilities, infrastructure, roads, and public spaces? Here’s “Madinati” an AI-powered app taking and implementing your feedback in real time.

🇦🇪 HGS

22,191 views • 6 months ago

Meet Discovery Insure’s new Advanced Driving Instructor, a personalised AI driving coach, which aims to make every journey smarter by analysing your driving habits and giving personalised tips and goals.
0:34

Meet Discovery Insure’s new Advanced Driving Instructor, a personalised AI driving coach, which aims to make every journey smarter by analysing your driving habits and giving personalised tips and goals.

@Discovery_SA

167,000 views • 7 months ago

Playing around with KREA AI real-time video ✨ Stream from your webcam and it diffuses in real-time based on your video + a text prompt. I turned my Philz cup into a magic potion!
0:22

Playing around with KREA AI real-time video ✨ Stream from your webcam and it diffuses in real-time based on your video + a text prompt. I turned my Philz cup into a magic potion!

Justine Moore

28,574 views • 11 months ago

Gemini 3 in AI Mode analyzes your hardest questions and builds a custom layout specific to your query — whether that’s an interactive tool or a simulation coded in real-time. Watch it visualize a complex question about the physics of photography ↓
0:33

Gemini 3 in AI Mode analyzes your hardest questions and builds a custom layout specific to your query — whether that’s an interactive tool or a simulation coded in real-time. Watch it visualize a complex question about the physics of photography ↓

Google

119,900 views • 7 months ago

🚨 BREAKING: Someone just open-sourced software that sees you through walls using only WIFI signals. it’s called WiFi-DensePose. It maps your exact body pose in real-time. no cameras. no sensors. just your living room router. 100% Open Source.
0:36

🚨 BREAKING: Someone just open-sourced software that sees you through walls using only WIFI signals. it’s called WiFi-DensePose. It maps your exact body pose in real-time. no cameras. no sensors. just your living room router. 100% Open Source.

Oliver Prompts

7,895,826 views • 6 months ago

This is wild: DraGAN: Interactive point-based manipulation of images using AI. This gives you controllability of the pose, shape, expression, and layout of the objects in your images.
1:02

This is wild: DraGAN: Interactive point-based manipulation of images using AI. This gives you controllability of the pose, shape, expression, and layout of the objects in your images.

AI Breakfast

1,101,324 views • 3 years ago

Meet the new No-Code Agent Builder: Pick, combine, and deploy agents in seconds. Agents are composed of tools (APIs, smart contracts, on-chain logic). We break down your tools and let others build agents by combining them. Try it now 🔗👇
0:58

Meet the new No-Code Agent Builder: Pick, combine, and deploy agents in seconds. Agents are composed of tools (APIs, smart contracts, on-chain logic). We break down your tools and let others build agents by combining them. Try it now 🔗👇

Amadeus Protocol

99,837 views • 1 year ago

Building real-time voice AI just got a lot easier 🤖✨ Introducing our new Python AI SDK for building real-time AI integrations directly into Stream Video. With out-of-the-box integrations with , Deepgram, , OpenAI, Moonshine AI, and more, developers can mix and match between real-time Voice AI, TTS or STT models. Get started 👇
0:49

Building real-time voice AI just got a lot easier 🤖✨ Introducing our new Python AI SDK for building real-time AI integrations directly into Stream Video. With out-of-the-box integrations with , Deepgram, , OpenAI, Moonshine AI, and more, developers can mix and match between real-time Voice AI, TTS or STT models. Get started 👇

Stream

224,788 views • 1 year ago

Snap photos remotely on your #GalaxyZFlip5 with the #GalaxyWatch6. Zoom in and out, or switch from photo to video, all from your wrist. Just strike a pose and tap on your Watch. #SamsungUnpacked
0:24

Snap photos remotely on your #GalaxyZFlip5 with the #GalaxyWatch6. Zoom in and out, or switch from photo to video, all from your wrist. Just strike a pose and tap on your Watch. #SamsungUnpacked

Samsung Malaysia

19,847 views • 3 years ago

ACE Studio Video Composer doesn’t just generate tracks. It analyzes your scenes, cuts, and motion to create synced music & SFX on a full timeline. It’s like an AI audio assistant that builds your soundtrack and gives you fully editable clips. Download: 🚀
1:39

ACE Studio Video Composer doesn’t just generate tracks. It analyzes your scenes, cuts, and motion to create synced music & SFX on a full timeline. It’s like an AI audio assistant that builds your soundtrack and gives you fully editable clips. Download: 🚀

ACE Studio

69,877 views • 5 months ago