sensevoice-rs and sensevoice-cli
These are ecosystem siblings where one provides a Rust library binding (darkautism/sensevoice-rs) and the other is a CLI wrapper tool (miuda-ai/sensevoice-cli) built on top of the same SenseVoice-small model, allowing users to choose between programmatic or command-line interfaces for the same underlying functionality.
About sensevoice-rs
darkautism/sensevoice-rs
A Rust-based, SenseVoiceSmall
SenseVoiceSmall is a speech recognition tool that takes audio files or live audio streams as input and converts spoken words into written text. It identifies the language, emotion, and any background events within the audio, making it useful for transcribing conversations or media. This tool is for developers who need to integrate high-performance speech-to-text capabilities into their Rust applications, especially those targeting Rockchip NPU hardware.
About sensevoice-cli
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.
Scores updated daily from GitHub, PyPI, and npm data. How scores work