ClawHub

Meeting Transcriber

v1.0.0

基于FunASR的中文实时语音转录，支持麦克风录音、自动标点、智能VAD及转录文件管理与环境检测。

⭐ 0· 39·1 current·1 all-time
by@chinapjs
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (FunASR-based meeting transcription) match the provided scripts: environment checks, conda setup, an OpenClaw wrapper, and a transcriber controller. Declared requirements in _meta.json (python, conda, audioProject env, main script) align with the code and functionality.
ℹ
Instruction Scope
SKILL.md and the scripts instruct the agent to run local environment checks, launch transcription processes, create startup scripts, and read/write local paths (e.g., D:\dev\python\voiceFunAsr, C:\Users\pengjschina\.cache, ~/.openclaw). This is expected for a local transcriber, but the skill will access many filesystem locations and spawn subprocesses — users should confirm those local paths and target scripts (vocie_mic_fixed_gbk.py) are trusted.
✓
Install Mechanism
No remote download/install spec in the registry entry; installation appears instruction-only plus included Python scripts. There are no external archive downloads or third‑party install URLs in the provided files.
✓
Credentials
The skill requests no secrets or external credentials. It expects Conda and Python and checks for audio/model caches; these are proportional to a local ASR transcription tool. No unrelated environment variables or keys are requested.
ℹ
Persistence & Privilege
always:false (no forced persistence). The scripts create local artifacts (batch scripts, start_with_conda.bat, a config file under ~/.openclaw) and may patch SKILL.md or other local skill files to add Conda metadata — this is within the skill's scope but means it will modify files on disk, so review what will be written.
Assessment
This skill appears to do what it says, but it is tailored to a specific Windows/Conda setup and uses hard-coded paths (e.g., D:\dev\python\voiceFunAsr, D:\ProgramData\Miniconda3\envs\audioProject, C:\Users\pengjschina\.cache). Before installing or running: 1) inspect vocie_mic_fixed_gbk.py and any referenced scripts in the D: path — those are the actual transcription engine and could contain arbitrary code; 2) be aware the skill will create startup scripts and a config file under your home (~/.openclaw) and may modify SKILL.md; 3) it will spawn subprocesses (conda, python) and may download ASR models at first run — ensure network/download behavior is acceptable; 4) if you do not have a matching Windows/Conda environment, the skill will likely fail or attempt to modify files to adapt; 5) no secrets are requested by the skill, but only proceed if you trust the source of the included transcriber scripts.

Like a lobster shell, security has layers — review code before you run it.

latestvk976yp8828xxnw4sfdwatvzky1843tsw

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments