Voice Recognition

Local speech-to-text with OpenAI Whisper CLI. Supports Chinese, English, 100+ languages with translation and summarization.

This skill appears to do what it says: a small Python wrapper that invokes the local OpenAI Whisper CLI and writes transcripts locally. Before installing/use: (1) install openai-whisper from a trusted source (Homebrew tap) so the 'whisper' binary on your PATH is legitimate; (2) be aware the first run will download model weights to ~/.cache/whisper (large download and disk usage); (3) update the SKILL.md usage examples to point to the script location on your system instead of the hard-coded /Users/liyi/... path, and only create the suggested alias if you trust the script location; (4) transcripts are written next to the input audio file — check permissions and disk location; (5) if you want to reduce risk, run the script in an isolated environment (container or VM) until you confirm behavior. No signs of credential exfiltration or remote endpoints were found in the included files.

Type: OpenClaw Skill Name: voice-recognition Version: 1.0.0 The skill bundle is designed for local speech-to-text using the OpenAI Whisper CLI. The `SKILL.md` provides clear usage instructions without any prompt injection attempts or malicious directives for the agent. The Python script `scripts/voice识别_升级版.py` uses `subprocess.run` to execute the `whisper` command, passing user-controlled audio file paths as distinct arguments, which is the recommended secure method to prevent shell injection. Output files are written locally to the same directory as the input audio, aligning with the skill's stated purpose. There is no evidence of data exfiltration, persistence mechanisms, or other malicious behaviors.