TrevorS/voxtral-mini-realtime-rs
Streaming speech recognition running natively and in the browser. A pure Rust implementation of Mistral's Voxtral Mini 4B Realtime model using the Burn ML framework.
Supports both ASR and TTS with dual inference paths optimized for native (BF16/Q4 GGUF) and browser (WASM + WebGPU) execution, achieving real-time synthesis at 0.97 RTF on Q4 with custom WGSL kernels and fused operations. Solves five critical WASM constraints including 2GB allocation limits and 1.5GB embedding tables via sharded loading and GPU-resident quantized embeddings. Integrates with HuggingFace Hub for model distribution, Burn ML framework for compute, and cubecl-wgpu for WebGPU shader dispatch.
710 stars. Actively maintained with 25 commits in the last 30 days.
Stars
710
Forks
33
Language
Rust
License
Apache-2.0
Category
Last pushed
Feb 12, 2026
Commits (30d)
25
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/TrevorS/voxtral-mini-realtime-rs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
mrtozner/vox
Local voice AI framework for Rust. Whisper + LLM + TTS with no cloud dependencies.
darkautism/sensevoice-rs
A Rust-based, SenseVoiceSmall
izwi-ai/izwi
On-device AI engine for transcription, TTS, and voice workflows.
0xPD33/sonori
Sonori is a fully local STT app for Linux (Wayland).
go-restream/zipenhancer-rs
🚀 High-Performance Real-Time Audio Noise Reduction Library - Rust implementation based on ONNX...