Show HN: I built a free CharacterAI that runs locally(github.com)
github.com
Show HN: I built a free CharacterAI that runs locally
https://github.com/akdeb/open-toys/tree/main/resources
5 comments
also I'm not a hardware hacker - are there any ESP32 kits with the speaker / led / button / amp already wired or in a kit at least? (that you recommend for this)
Yeah I sell one here https://www.elatoai.com/products/ai-devkit
If you pre-order on the link I can ship you one at a discount
wow really cool, I browsed the repo but couldnt find what you used for the case on the ESP?
Thanks Boris! The case is made out of Resin but I started with PLA. Will post the open-sourced STEP files there
The voice pipeline currently supports MLX on any M1 through M5 chip. I used Whisper-Turbo for STT, Qwen3.5-9B-4bit for the LLM and Qwen3-TTS-0.6B-4bit for TTS.
The repo also has a Websocket Transport to add these voices to devices powered by the ESP32 via secure websockets.