miuda-ai/sensevoice-cli
Tool for speech recognition using sensevoice-small
This tool transcribes spoken audio into written text. You provide an audio file (like WAV, MP3, or FLAC) and it outputs a JSON file containing the transcribed text, broken down by segments and channels. It's designed for anyone who needs to convert spoken recordings into text for analysis, documentation, or search.
Use this if you need a quick, command-line way to get accurate text transcripts from audio files in multiple languages, with options to customize how speech is detected and segmented.
Not ideal if you prefer a graphical user interface, need real-time transcription, or require advanced speaker diarization features (identifying who spoke when).
Stars
26
Forks
4
Language
Rust
License
—
Category
Last pushed
Nov 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/miuda-ai/sensevoice-cli"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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.
0xPD33/sonori
Sonori is a fully local STT app for Linux (Wayland).
izwi-ai/izwi
On-device AI engine for transcription, TTS, and voice workflows.