Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Xenova 
posted an update 4 days ago
Post
2245
NEW: Real-time conversational AI models can now run 100% locally in your browser! 🤯

🔐 Privacy by design (no data leaves your device)
💰 Completely free... forever
📦 Zero installation required, just visit a website
⚡️ Blazingly-fast WebGPU-accelerated inference

Try it out: webml-community/conversational-webgpu

For those interested, here's how it works:
- Silero VAD for voice activity detection
- Whisper for speech recognition
- SmolLM2-1.7B for text generation
- Kokoro for text to speech

Powered by Transformers.js and ONNX Runtime Web! 🤗 I hope you like it!

this works way better than i expected! wow great! So then the next obvious step is avatar animation...somehow. For browser it seems we need gltf avatars with threejs and some kind of phoeneme animation

In a way I wonder if there’s a connection to the latest elevenlabs release one day after 🤔🤓