正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

An 8-year-old turned an $8 microcontroller into a fully offline, voice-controlled AI storyteller. No Wi-Fi. No cloud. No API. Using an ESP32-S3, INMP 441 mic, i2s speaker and Max 98357A amplifier, Laksh built a bot that generates stories, creates animations, reads them aloud and responds to voice commands: play,... show more

Capt Venkat 🇮🇳

6,332 subscribers

167,029 次观看 • 3 个月前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

49 条评论

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

your offline story-telling device is getting ready.

Slava S. 的头像

Slava S.3 个月前

Here is how it works under the hood

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

🚀🚀

Joe Bananas 的头像

Joe Bananas3 个月前

His daddy and mommy built it lol

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

🤣🤣🤣. Wish his father also knew how to build it.

Joe Bananas 的头像

Joe Bananas3 个月前

His daddy mommy put him on video after building it. 😀

Jimmy 的头像

Jimmy3 个月前

Super impressive build for an 8-year-old—getting local voice, animations, and LLM text generation playing nice together on an ESP32 is no small task! That said, calling it a complete storyteller is a bit generous given how harsh local TTS sounds on this hardware right now.

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

Agreed Jimmy. Tried eSpeak NG. Built his own lightweight English TTS. Same result. Interestingly, the ESP32 handles Chinese TTS much better. Pre-rendered speech sounds natural, but synthesized English speech is still poor. A high-quality offline English TTS for the ESP32 remains an open challenge.

ArT 的头像

ArT3 个月前

Yes that's laksh level.. Any 8 year old can assemble these tools now.. The real level is creating a tinystories llm or a home grown esp microcontroller.. This mindset is exactly why Indian IT is a service class and not an innovation class

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

That’s the next plan.

therealguru 的头像

therealguru3 个月前

WAIT OMDAYSSS 🤯🤯😎😎💪🏼💪🏼🇮🇳🇮🇳 👦🏻 👦🏻 ❤️❤️ GENIUS & WTF 😳 HE IS ONKY 8 DAMM

Harsha Bommana 的头像

Harsha Bommana3 个月前

Laksh is a legend!! 🔥🚀

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

Have to take some guidance and directions from you.

AI Mastery Guide 的头像

AI Mastery Guide3 个月前

An 8 year old outbuilding most adults with $8 in parts

DualShot66 的头像

DualShot663 个月前

for 8 year old thats a massive achievement. Good job, little buddy.

YFE Embedded 的头像

YFE Embedded3 个月前

@itzjustshiro Check this out

Stanislav Sorokin 的头像

Stanislav Sorokin3 个月前

If the bot stays offline, how do you stop a saved story becoming false precedent for the next prompt? Local storage improves privacy, but retrieval still needs a relevance gate and memory-off baseline. The test:

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

Good question. But, stories are not saved.

Pratima 的头像

Pratima3 个月前

Wow wow 👏👏👏

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

❤️

MelluPope: Monkey Bath 的头像

MelluPope: Monkey Bath3 个月前

👏👏👏

Debashis Roy 🙏 🇮🇳 的头像

Debashis Roy 🙏 🇮🇳3 个月前

Genuinely impressive for an 8-year-old — offline inference on an ESP32-S3 plus voice I/O and animation is no small feat. For the TTS issue: worth trying a lighter phoneme-based engine like eSpeak-NG ported for embedded — might improve clarity within the memory budget.

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

Thanks Debashis. He tried espeak-NG which yielded similar results. Tried making own english TTS that too same. It seems ESP32 has a good Chinese language TTS. Pre-rendered words sound natural, while synthesised words are bad. Needs a lot of work on this.

RITAV DAS 的头像

RITAV DAS3 个月前

Amazing Laksh !

Karmakar 的头像

Karmakar3 个月前

Extremely clean repo. Extremely clean and well-structured code. Extremely detailed commenting with "- - - /xyz - - -" styling. Definitely not at all generated by AI.

Second Order Equity 的头像

Second Order Equity3 个月前

How cool man. He's real life Dexter from Dexter's Laboratory🤣🤣

Rian Arz 的头像

Rian Arz3 个月前

This is the future of on-device AI. ESP32-S3 running local models with no cloud dependency shows how accessible edge computing has become. The voice + animation loop on a $8 board is impressive. What local model did Laksh use for story generation?

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

He forked an open source model from Git created by @slvDev.

Rahul Raj 的头像

Rahul Raj3 个月前

Amazing.

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

Thanks Rahul.

SimsINA Cafe ☕ (Belle) 的头像

SimsINA Cafe ☕ (Belle)3 个月前

I love tinker babies

Neel 的头像

Neel3 个月前

White pill of the day!

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

❤️

Just Jeff 的头像

Just Jeff3 个月前

🤯

Sanat K Mishra 🇮🇳🇳🇿🇮🇱 的头像

Sanat K Mishra 🇮🇳🇳🇿🇮🇱3 个月前

Well done Laksh, keep it up. You are the future of India. All the best.

SSKeyMoonshot 的头像

SSKeyMoonshot3 个月前

Founder is the Father .. son is co- founder…. Nice effort by the father …..

Abdulmuiz Adeyemo 的头像

Abdulmuiz Adeyemo3 个月前

Oh man

YaShR🅰️J 🔆 TRUMP 的头像

YaShR🅰️J 🔆 TRUMP3 个月前

future elon musk ur son

Aditya 的头像

Aditya3 个月前

prodigy in the making !

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

😊

Pankaj Malviya 的头像

Pankaj Malviya3 个月前

Good 👍

Dr Subroto Roy 的头像

Dr Subroto Roy3 个月前

Nice...at age 8 all we could do is crack open thick radio batteries and make a mess...

Capt Venkat 🇮🇳 的头像

Capt Venkat 🇮🇳3 个月前

And that did set the tone for future builders. 🙌

Rian Arz 的头像

Rian Arz3 个月前

This is the future of personal AI. Fully local, no cloud dependency, runs on cheap hardware. The 8-year-old just proved agents don't need big infra to be magical. What microcontroller project are you building next?

Rian Arz 的头像

Rian Arz3 个月前

This is the kind of project that makes hardware suddenly feel magical again. The offline constraint forces real creativity — no lazy API calls. Would love to see how he handled the story generation prompt on that tiny chip.

Nandish V Patel 的头像

Nandish V Patel3 个月前

👏🏻👏🏻👏🏻

gss 的头像

gss3 个月前

very smart boy, at his age I played minecraft

Cabinetofwhimsicalwisdom ! 的头像

Cabinetofwhimsicalwisdom !3 个月前

Congrats and wishing Laksh many more milestones

durgasprasad 的头像

durgasprasad3 个月前

Unbelievable.. 👌

相关视频

Want to add offline voice AI to your ESP32? Start with ESP-Skainet. It is an open-source speech AI framework for building always-on voice assistants that run entirely on ESP32 devices. It combines WakeNet for wake-word detection, MultiNet for offline speech commands, and an Audio Front End with echo cancellation, noise suppression, and voice activity detection. ESP32-S3 is the recommended platform, with the latest models also targeting ESP32-P4.

Want to add offline voice AI to your ESP32? Start with ESP-Skainet. It is an open-source speech AI framework for building always-on voice assistants that run entirely on ESP32 devices. It combines WakeNet for wake-word detection, MultiNet for offline speech commands, and an Audio Front End with echo cancellation, noise suppression, and voice activity detection. ESP32-S3 is the recommended platform, with the latest models also targeting ESP32-P4.

Praveen Kumar Verma

15,209 次观看 • 3 个月前

btw this robot runs on a fully open source AI framework called Xiaozhi it turns a $8 ESP32 chip into a fully autonomous voice assistant NO expensive cloud servers or high latency wake-word detection and audio streaming happen locally on the chip: > requires only an ESP32-S3, a microphone, and a basic speaker > supports real-time conversational voice interaction > completely open-source and customizable for any DIY robotics project anyone can now build a personal AI companion for the price of a cup of coffee. (github link in the replies)

btw this robot runs on a fully open source AI framework called Xiaozhi it turns a $8 ESP32 chip into a fully autonomous voice assistant NO expensive cloud servers or high latency wake-word detection and audio streaming happen locally on the chip: > requires only an ESP32-S3, a microphone, and a basic speaker > supports real-time conversational voice interaction > completely open-source and customizable for any DIY robotics project anyone can now build a personal AI companion for the price of a cup of coffee. (github link in the replies)

ard

42,210 次观看 • 2 个月前

This guy fit a barista AI inside an $8 ESP32. Ask it an espresso question over USB. It answers on a tiny OLED. Fully local. No cloud. No GPU. Tiny specialized AI is getting interesting. Repo below.

This guy fit a barista AI inside an $8 ESP32. Ask it an espresso question over USB. It answers on a tiny OLED. Fully local. No cloud. No GPU. Tiny specialized AI is getting interesting. Repo below.

Min Choi

51,718 次观看 • 2 个月前

What If Your ESP32-S3 Became an AI Robot With Personality? Meet StackChan, a community-created, open-source AI desktop robot built around the M5Stack CoreS3 and ESP32-S3. Inside is a 240 MHz dual-core processor with 16 MB Flash and 8 MB PSRAM, plus a touchscreen, camera, dual microphones, speaker, 9-axis IMU, proximity sensor, NFC, RGB LEDs, and two feedback servos. It can talk, react, move its head, show expressions, work as an AI agent, and connect to smart-home or IoT projects. The best part? You can program and customize it using Arduino, PlatformIO, ESP-IDF, or UiFlow2.

What If Your ESP32-S3 Became an AI Robot With Personality? Meet StackChan, a community-created, open-source AI desktop robot built around the M5Stack CoreS3 and ESP32-S3. Inside is a 240 MHz dual-core processor with 16 MB Flash and 8 MB PSRAM, plus a touchscreen, camera, dual microphones, speaker, 9-axis IMU, proximity sensor, NFC, RGB LEDs, and two feedback servos. It can talk, react, move its head, show expressions, work as an AI agent, and connect to smart-home or IoT projects. The best part? You can program and customize it using Arduino, PlatformIO, ESP-IDF, or UiFlow2.

Praveen Kumar Verma

16,179 次观看 • 1 个月前

Turned 8 today. Laksh gifted himself a successful build on his birthday, an ESP32-CAM with object identification. More experiments to follow. Hardware x Ai. 🚀 AML

Turned 8 today. Laksh gifted himself a successful build on his birthday, an ESP32-CAM with object identification. More experiments to follow. Hardware x Ai. 🚀 AML

Capt Venkat 🇮🇳

28,048 次观看 • 11 个月前

Building a robot dog? This ESP32 board was made for it. Petoi Biboard is an ESP32-based development board designed for multi-joint robots, with up to 12 PWM servo outputs built right in. It also includes an onboard IMU for balance and motion sensing, wireless connectivity, expansion interfaces and audio features. The BiBoard V1 adds features such as a voice command module, speaker and Raspberry Pi support. What makes it especially interesting is the software ecosystem. The board works with Petoi's open-source OpenCat framework, giving developers a solid starting point for building quadruped robots instead of creating everything from scratch. An ESP32, 12 servos and open-source robotics software. That's a pretty good starting point for building your own robot dog.

Building a robot dog? This ESP32 board was made for it. Petoi Biboard is an ESP32-based development board designed for multi-joint robots, with up to 12 PWM servo outputs built right in. It also includes an onboard IMU for balance and motion sensing, wireless connectivity, expansion interfaces and audio features. The BiBoard V1 adds features such as a voice command module, speaker and Raspberry Pi support. What makes it especially interesting is the software ecosystem. The board works with Petoi's open-source OpenCat framework, giving developers a solid starting point for building quadruped robots instead of creating everything from scratch. An ESP32, 12 servos and open-source robotics software. That's a pretty good starting point for building your own robot dog.

Praveen Kumar Verma

77,546 次观看 • 1 个月前

The touch bar has been turned into a standalone gadget, powered by an ESP32 microcontroller:

The touch bar has been turned into a standalone gadget, powered by an ESP32 microcontroller:

Wenting

657,749 次观看 • 1 年前

meet WALL-E no, not the one from the cartoon :) this is a fully 3D-printed, autonomous desk companion running on an ESP32. it uses a local AI voice assistant to process commands in real-time and control its own motors building intelligent robotics just dropped to zero cost...

meet WALL-E no, not the one from the cartoon :) this is a fully 3D-printed, autonomous desk companion running on an ESP32. it uses a local AI voice assistant to process commands in real-time and control its own motors building intelligent robotics just dropped to zero cost...

ard

65,781 次观看 • 2 个月前

I just deployed a token on Abstract using only my voice, using AI agents. I built an open-source Discord bot that controls a wallet, can perform on-chain actions, and replies to users in the voice chat. Here's a demo:

I just deployed a token on Abstract using only my voice, using AI agents. I built an open-source Discord bot that controls a wallet, can perform on-chain actions, and replies to users in the voice chat. Here's a demo:

Jarrod Watts

131,616 次观看 • 1 年前

Every time I think the ESP32-S3 has hit its limit, someone finds another gear. This open-source Jet renderer is now pushing the S3 even harder. Real-time screen-space reflections, water ripple distortion, lens flare and 8 ships on screen, all running on a tiny MCU. Performance dropped from around 60 FPS to 45–50 FPS, but that's still wild for an ESP32-S3. And the developer thinks there is more performance left to squeeze out. No GPU. No desktop CPU. Just an ESP32-S3 doing real-time 3D graphics.

Every time I think the ESP32-S3 has hit its limit, someone finds another gear. This open-source Jet renderer is now pushing the S3 even harder. Real-time screen-space reflections, water ripple distortion, lens flare and 8 ships on screen, all running on a tiny MCU. Performance dropped from around 60 FPS to 45–50 FPS, but that's still wild for an ESP32-S3. And the developer thinks there is more performance left to squeeze out. No GPU. No desktop CPU. Just an ESP32-S3 doing real-time 3D graphics.

Praveen Kumar Verma

15,924 次观看 • 2 个月前

another example: a developer used the exact same $8 ESP32-S3 chip and local AI setup to build a real-time object recognition camera the fact that this is running entirely offline, on an eight-dollar microcontroller, without any cloud API calls, is wild... it captures the video feed, processes it locally through the model, and identifies objects in real-time. we are entering an era where you can just glue intelligence onto any physical object for less than $10. the hardware barrier is completely shattered.

another example: a developer used the exact same $8 ESP32-S3 chip and local AI setup to build a real-time object recognition camera the fact that this is running entirely offline, on an eight-dollar microcontroller, without any cloud API calls, is wild... it captures the video feed, processes it locally through the model, and identifies objects in real-time. we are entering an era where you can just glue intelligence onto any physical object for less than $10. the hardware barrier is completely shattered.

ard

230,333 次观看 • 3 个月前

You can now put an entire LLM model on an ESP32 How is that possible and what would you do with it?

You can now put an entire LLM model on an ESP32 How is that possible and what would you do with it?

tech.explain

16,206 次观看 • 1 个月前

What If Your Weekend Project Could Balance on Two Wheels? The ES02 is an open-source bipedal wheeled robot built around an ESP32 by Navbot. It combines two-wheel balancing with leg movement, making it a fun platform for experimenting with robot control, simulation, motion planning and embedded programming. If you are getting into robotics, this is the kind of project that can teach you a lot by actually building and tuning it. Would you build one for your next weekend project?

What If Your Weekend Project Could Balance on Two Wheels? The ES02 is an open-source bipedal wheeled robot built around an ESP32 by Navbot. It combines two-wheel balancing with leg movement, making it a fun platform for experimenting with robot control, simulation, motion planning and embedded programming. If you are getting into robotics, this is the kind of project that can teach you a lot by actually building and tuning it. Would you build one for your next weekend project?

Praveen Kumar Verma

12,586 次观看 • 1 个月前

What if you could pick up an ESP32-S3 and play with it without touching the hardware? I made an interactive 3D ESP32-S3 simulator that runs directly in the browser. You can click GPIO pins to toggle them, lift the shield can, watch the board boot, switch camera angles and even export screenshots. Try it.

What if you could pick up an ESP32-S3 and play with it without touching the hardware? I made an interactive 3D ESP32-S3 simulator that runs directly in the browser. You can click GPIO pins to toggle them, lift the shield can, watch the board boot, switch camera angles and even export screenshots. Try it.

Praveen Kumar Verma

19,213 次观看 • 1 个月前

Imagine sitting in a cafe, opening your phone, tapping one button, and your home PC starts waking up. No port forwarding. No public IP. No complicated VPN setup. This ESP32 project turns a tiny microcontroller into a remote Wake-on-LAN bridge. The ESP32 stays connected to Wi-Fi and listens for a command over MQTT. When you send the command, it fires a Wake-on-LAN magic packet across your local network and wakes up your PC. The clever part is that the ESP32 makes the outbound connection, so you don't need to expose your home network to the internet. Developed by kreavx

Imagine sitting in a cafe, opening your phone, tapping one button, and your home PC starts waking up. No port forwarding. No public IP. No complicated VPN setup. This ESP32 project turns a tiny microcontroller into a remote Wake-on-LAN bridge. The ESP32 stays connected to Wi-Fi and listens for a command over MQTT. When you send the command, it fires a Wake-on-LAN magic packet across your local network and wakes up your PC. The clever part is that the ESP32 makes the outbound connection, so you don't need to expose your home network to the internet. Developed by kreavx

Praveen Kumar Verma

18,983 次观看 • 23 天前

Your ad blocker could fit behind your router. meet ESP32-C3 AdBlock, an open-source DIY DNS ad blocker by ZedAxis, built around a roughly $2 ESP32-C3 Super Mini board inside: 400 KB of RAM, 4 MB of flash, built-in Wi-Fi and a USB adapter, tucked into a printed case no subscription no browser extension no separate power brick plug it into your router’s USB port for power, connect over Wi-Fi and set it as your DNS server to block listed ad and tracker domains. compact 40-bit hashes save RAM. a web dashboard lets you check blocked requests and add domains, while open-source code and case files let you build your own. follow for more hardware you can see working

Your ad blocker could fit behind your router. meet ESP32-C3 AdBlock, an open-source DIY DNS ad blocker by ZedAxis, built around a roughly $2 ESP32-C3 Super Mini board inside: 400 KB of RAM, 4 MB of flash, built-in Wi-Fi and a USB adapter, tucked into a printed case no subscription no browser extension no separate power brick plug it into your router’s USB port for power, connect over Wi-Fi and set it as your DNS server to block listed ad and tracker domains. compact 40-bit hashes save RAM. a web dashboard lets you check blocked requests and add domains, while open-source code and case files let you build your own. follow for more hardware you can see working

Psalter

705,473 次观看 • 26 天前

Most AI products added voice by wrapping a chatbot in speech-to-text. Vellum built a real-time voice loop on top of a full agent. It browses the web, reads your files, runs code, and sends messages while you’re still talking. This is voice as a real surface for an agent. Not a voice chatbot.

Most AI products added voice by wrapping a chatbot in speech-to-text. Vellum built a real-time voice loop on top of a full agent. It browses the web, reads your files, runs code, and sends messages while you’re still talking. This is voice as a real surface for an agent. Not a voice chatbot.

Kyronis

112,849 次观看 • 3 个月前