MENU

Fun & Interesting

Building real-time conversational AI on ESP32 (using LiveKit and WebRTC)

Build With Binh 18,036 3 weeks ago
Video Not Working? Fix It Now

🧑‍💻 Project Description This is the first conversational ESP32 project to demonstrate real-time conversations using a custom speech pipeline (Silero for VAD, Whisper for STT, GPT4o for text-to-text and ElevenLabs for TTS). Demonstrated in the video, the device can talks to users direcly in Wheatley (Portal 2) voice and tone. It achieves this by interfacing directly with LiveKit real-time pipeline, which hosts a custom voice trained on ElevenLabs and a fine-tuned GPT4o. 💻 Github Repository The source and written tutorial of the project can be found here: https://github.com/pham-tuan-binh/wheatley-ai 🛒 SenseCap Watcher If you would like a SenseCap Watcher yourself, consider buying it from my affiliated link: https://www.seeedstudio.com/SenseCAP-Watcher-W1-A-p-5979.html?sensecap_affiliate=3gToNR2&referring_service=link This helps me a lot since I'm not yet in YouTube monetization program and making these videos cost me quite lot as a creator. Seeed Studio Coupon (applicable to most items on their shop): 5EB420ZS 👨‍💼 Collaboration The project is distributed under a copyleft license, details on Github. If you want to collaborate with me or commercialize this project, please write me an email at [email protected]. #esp32 #embedded #ai #livekit #elevenlabs 🎞️ Chapters 00:00 - Beginning 00:54 - Chapter 1 01:46 - Chapter 2 02:06 - Front end 03:21 - Back end 04:44 - Chapter 3 09:35 - Demo

Comment