Whisper Transcribe

Transcribe audio files to text using OpenAI Whisper. Supports speech-to-text with auto language detection, multiple output formats (txt, srt, vtt, json), batch processing, and model selection (tiny to large). Use when transcribing audio recordings, podcasts, voice messages, lectures, meetings, or any audio/video file to text. Handles mp3, wav, m4a, ogg, flac, webm, opus, aac formats.

This skill appears to do what it claims: wrap the local 'whisper' CLI to transcribe audio. Before installing/using it: (1) ensure you trust the 'openai-whisper' pip package source and install it in a virtualenv to limit install-time risks, (2) install ffmpeg separately (the script assumes it exists), (3) be aware models are downloaded at first run and may be large and require network access and disk space, and (4) avoid running the tool on sensitive audio in untrusted environments. If you want extra assurance, inspect the pip package source before installing or run the transcription inside a container/VM.

Type: OpenClaw Skill Name: whisper-transcribe Version: 1.0.0 The skill bundle is benign. The `SKILL.md` provides clear, non-malicious instructions for transcribing audio using the `whisper` CLI. The `scripts/transcribe.sh` script is a well-structured shell wrapper that safely executes the `whisper` command by constructing arguments in an array (`"${args[@]}"`), mitigating shell injection risks. It performs necessary file system operations (creating output directories and writing transcription files) directly aligned with its stated purpose and does not exhibit any signs of data exfiltration, persistence, unauthorized network activity, or prompt injection attempts against the agent.