100% Local
🔒
Privacy First
All AI inference happens locally. No data sent to servers.
Now running on Edge
AI that runs
where you are
Run Falcon-H1, Whisper, and Kokoro AI models directly in your browser. No servers. No data collection. Just privacy-first AI.
4 Models Active
~250MB Total Size100% Browser-BasedWorks Offline
⚡
Offline Capable
Models cached locally. Works without internet.
GPL 3.0
📦
Open Source
GPL 3.0 licensed. View, modify, distribute freely.
Edge Ready
🌐
Edge Ready
Runs on Cloudflare Workers, Vercel Edge, any edge runtime.
Powered by Open Models
All models sourced from HuggingFace, optimized for edge deployment.
Chat AI
Falcon-H1-Tiny-90M
90M
parameters
91MB
91MBHuggingFace
Speech Recognition
Whisper-Tiny
39M
parameters
31MB
31MBHuggingFace
Embeddings
all-MiniLM-L6-v2
22M
parameters
45MB
45MBHuggingFace
Text-to-Speech
Web Speech API
N/A
parameters
0MB
0MBHuggingFace
Ready to try it yourself?
Open the playground and chat with Falcon-H1 directly in your browser. No account required.
Start Chatting