List and analyze WaveCap audio recordings with metadata and quality checks.
npx skills add https://github.com/TobiasWooldridge/WaveCap --skill wavecap-audio
Please help me install this Agent Skill. Skill: wavecap-audio Source: https://github.com/TobiasWooldridge/WaveCap/tree/main/.claude/skills/wavecap-audio Command: npx skills add https://github.com/TobiasWooldridge/WaveCap --skill wavecap-audio
This Skill helps users analyze and manage audio recordings generated by WaveCap transcription sessions, allowing for inspection, quality checks, and organization of audio files.
Use the wavecap-audio skill to list all recordings in the state directory.
High-intent search queries and answers about installing and using this skill.
To check audio recording quality, you can analyze files to identify very short or large recordings, extract duration metadata, and review disk usage. This helps ensure your transcription session files are sufficient for analysis.
You can list audio files from a WaveCap state directory by retrieving available recordings, sorting them by date, and counting them. This allows you to quickly organize and inspect your recorded audio sessions.
You may need external tools like ffprobe or sox for detailed audio analysis. While basic file information is accessible directly, extracting detailed audio properties like sample rate and channels often requires these external dependencies.
The best way to find audio recordings missing transcriptions is to run a quality analysis on your audio files. This process scans the state directory to identify any recordings that lack corresponding transcription data.
Yes, you can retrieve basic file information without external tools. The skill provides basic metadata extraction directly, though detailed audio properties such as sample rate and channels require tools like ffprobe or sox.
Jaydpatel01Extract frames, audio, and metadata from video files using ffmpeg and Whisper.
tedtv1007-ctrlTranscribe audio files into text using the OpenAI Whisper API.
kaivyyTranscribe audio files with OpenAI Whisper and synthesize speech from text.
antgroupSearch, analyze, and batch-process files using Unix command-line utilities.
