stt + llm + tts

Speak, transcribe, generate, and listen — all in your browser.
No server, no API key. Nothing leaves your machine.

stt:
llm:
tts:


stt
llm
tts

STT: Quantized Kyutai STT model (Mimi audio codec + text decoder), custom Rust inference compiled to WebAssembly, GPU acceleration via WebGPU.
LLM: SmolLM2 (1.7B), multi-turn chat via WebGPU with WebLLM.
TTS: Quantized Kyutai Pocket-TTS model, custom Rust inference compiled to WebAssembly.


← trucs.ai