0xPD33/sonori
Sonori is a fully local STT app for Linux (Wayland).
Sonori helps you transcribe spoken audio into text right on your Linux computer, without sending any data to the cloud. You speak into your microphone, and the transcribed text appears on your screen as a transparent overlay or in your terminal. This tool is for anyone using Linux, especially those who need to quickly capture spoken notes, transcribe meetings, or get captions for audio content while keeping their data private.
Use this if you need a fast, private way to convert speech to text on your Linux system, either continuously or on-demand.
Not ideal if you are on Windows or macOS, or if you require cloud-based transcription with advanced features like speaker diarization.
Stars
17
Forks
1
Language
Rust
License
MIT
Category
Last pushed
Mar 14, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/0xPD33/sonori"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TrevorS/voxtral-mini-realtime-rs
Streaming speech recognition running natively and in the browser. A pure Rust implementation of...
darkautism/sensevoice-rs
A Rust-based, SenseVoiceSmall
mrtozner/vox
Local voice AI framework for Rust. Whisper + LLM + TTS with no cloud dependencies.
izwi-ai/izwi
On-device AI engine for transcription, TTS, and voice workflows.
CodersCreative/faster-whisper-rs
a rust crate for easily implementing faster-whisper stt into your rust programs.