# ESP32-S3 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/esp32-s3
> Markdown URL: https://aitinkerers.org/technologies/esp32-s3.md
> Technology record last updated: 2026-02-25T07:41:08Z
> Generated: 2026-09-20T15:43:48Z

The ESP32-S3 is a dual-core Xtensa LX7 Wi-Fi/Bluetooth LE SoC, purpose-built for AIoT: featuring vector instructions for AI acceleration and robust hardware security.

This is a serious upgrade: the ESP32-S3 integrates a dual-core Xtensa LX7 processor clocked up to 240 MHz, paired with 2.4 GHz Wi-Fi (802.11 b/g/n) and Bluetooth 5 (LE) radio. Crucially, it includes vector instructions for hardware-accelerated AI and neural network computing, targeting demanding AIoT applications like voice and image recognition. You get 512 KB of SRAM, support for high-speed Octal SPI flash/PSRAM (up to 16 MB), and a rich peripheral set, including USB OTG and up to 45 programmable GPIOs. Security is locked down with AES-XTS flash encryption, Secure Boot, and the 'World Controller' for isolated execution environments.

- Official technology site: https://www.espressif.com/en/products/socs/esp32-s3
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Fully Customizable Voice AI with multi-modal open source LLMs and esp32 (clone your own voice too with simple tools)](https://tokyo.aitinkerers.org/talks/rsvp__c55AmItHW0)

A step‑by‑step guide to building a fully local voice AI using fully open source EchoKit, swapping ASR/TTS models, integrating open‑source LLMs, and deploying on ESP‑32. Walkthrough of how I run the open source EchoKit (https://github.com/second-state/echokit_server) voice AI stack to connect any LLM with speech-to-text, text-to-speech, and custom prompts—all running locally or in the cloud. I’ll start with a minimal working setup, then show how to swap in different ASR/TTS models (Whisper, VITS), integrate LLMs (GPT5, Kimi K2, DeepSeek), and add domain-specific knowledge bases. We’ll explore the full data flow, from audio capture to streamed responses, plus edge deployment with the open source runtime WasmEdge for low-latency inference.

- Event context: AI Tinkerers Tokyo Kickoff – October 10, 2025 — 2025-10-10 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp__c55AmItHW0

### [Winners Don't Settle](https://hong-kong.aitinkerers.org/talks/rsvp_QPd3cm59vT8)

This talk shares the journey of building Cresento, a sports tech startup transforming grassroots football through AI-powered wearables. I’ll explore how we engineered smart shin pads embedded with motion sensors and GPS, and trained AI models to deliver real-time coaching, performance feedback, and talent discovery tools—directly to amateur athletes. This is not just a hardware project—it’s an AI platform empowering the next generation of football talent through data-driven insights and automated training recommendations. Attendees will get a behind-the-scenes look at how we built the AI Coach system, turned raw sensor data into actionable insights, and created a feedback loop between athlete movement and skill improvement.

- Event context: AI Tinkerers - Hong Kong Meetup (April) - AI in Education and the HKUST Community — 2025-04-30 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_QPd3cm59vT8

## Related Technologies

- [Arduino](https://aitinkerers.org/technologies/arduino) ([Markdown](https://aitinkerers.org/technologies/arduino.md)) — 1 public demo
- [AWS Amplify](https://aitinkerers.org/technologies/aws-amplify) ([Markdown](https://aitinkerers.org/technologies/aws-amplify.md)) — 1 public demo
- [EchoKit](https://aitinkerers.org/technologies/echokit) ([Markdown](https://aitinkerers.org/technologies/echokit.md)) — 1 public demo
- [esp-idf-hal](https://aitinkerers.org/technologies/esp-idf-hal) ([Markdown](https://aitinkerers.org/technologies/esp-idf-hal.md)) — 1 public demo
- [LlamaEdge](https://aitinkerers.org/technologies/llamaedge) ([Markdown](https://aitinkerers.org/technologies/llamaedge.md)) — 1 public demo
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [SwiftUI](https://aitinkerers.org/technologies/swiftui) ([Markdown](https://aitinkerers.org/technologies/swiftui.md)) — 9 public demos