ReddRadar
Agent skill
wavecap-audio
Analyze recorded audio files from WaveCap. Use when the user wants to inspect audio recordings, check audio quality, list available recordings, or get audio file metadata.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/wavecap-audio
SKILL.md
WaveCap Audio Analysis Skill
Use this skill to analyze and inspect recorded audio files from WaveCap transcription sessions.
Recordings Location
Audio recordings are stored in the state directory:
STATE_DIR="/Users/thw/Projects/WaveCap/state"
RECORDINGS_DIR="$STATE_DIR/recordings"
Recordings are also accessible via HTTP at http://localhost:8000/recordings/
List Available Recordings
List all recordings
ls -la "$STATE_DIR/recordings/" | head -50
List recordings with sizes (sorted by date)
ls -lht "$STATE_DIR/recordings/" | head -30
Count total recordings
ls "$STATE_DIR/recordings/" 2>/dev/null | wc -l
Find recordings by date
# Today's recordings
find "$STATE_DIR/recordings" -name "*.wav" -mtime 0 -type f
# Last 7 days
find "$STATE_DIR/recordings" -name "*.wav" -mtime -7 -type f
Get Audio File Metadata
Basic file info
file "$STATE_DIR/recordings/FILENAME.wav"
Detailed audio properties (requires ffprobe/sox)
# Using ffprobe (if available)
ffprobe -v quiet -show_format -show_streams "$STATE_DIR/recordings/FILENAME.wav" 2>/dev/null | grep -E "duration|sample_rate|channels|bit_rate"
# Using soxi (if sox installed)
soxi "$STATE_DIR/recordings/FILENAME.wav" 2>/dev/null
Get duration of a recording
ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 "$STATE_DIR/recordings/FILENAME.wav" 2>/dev/null
Find Recordings for a Transcription
Get recording URL from transcription
curl -s "http://localhost:8000/api/streams/{STREAM_ID}/transcriptions?limit=10" | \
jq '.transcriptions[] | {id, timestamp, recordingUrl, text}'
Check if recording file exists
RECORDING_URL="recordings/abc123.wav"
FILENAME=$(basename "$RECORDING_URL")
ls -la "$STATE_DIR/recordings/$FILENAME" 2>/dev/null || echo "Recording not found"
Analyze Audio Quality
Check for very short recordings (likely noise/errors)
find "$STATE_DIR/recordings" -name "*.wav" -size -10k -type f | head -20
Check for large recordings (long transmissions)
find "$STATE_DIR/recordings" -name "*.wav" -size +500k -type f | head -20
Get total disk usage
du -sh "$STATE_DIR/recordings/"
List recordings without transcriptions
# Get all transcription recording URLs
TRANSCRIBED=$(curl -s http://localhost:8000/api/transcriptions/export | \
jq -r '.[].recordingUrl // empty' | xargs -I{} basename {} | sort | uniq)
# Compare with files on disk
ls "$STATE_DIR/recordings/" | sort > /tmp/all_recordings.txt
echo "$TRANSCRIBED" | sort > /tmp/transcribed.txt
comm -23 /tmp/all_recordings.txt /tmp/transcribed.txt | head -20
Stream Audio via API
Access recording via HTTP
# Recordings are served at /recordings/
curl -s -I "http://localhost:8000/recordings/FILENAME.wav"
# Download a recording
curl -o local_copy.wav "http://localhost:8000/recordings/FILENAME.wav"
Stream live audio (if stream supports it)
# Check if stream supports live audio
curl -s http://localhost:8000/api/streams | jq '.[] | select(.source == "audio" or .source == "remote") | {id, name, source}'
Clean Up Old Recordings
Find recordings older than 30 days
find "$STATE_DIR/recordings" -name "*.wav" -mtime +30 -type f | wc -l
Calculate space used by old recordings
find "$STATE_DIR/recordings" -name "*.wav" -mtime +30 -type f -exec du -ch {} + 2>/dev/null | tail -1
Tips
- Recording filenames typically include a UUID or timestamp
- Use
recordingUrlfrom transcription API responses to link audio to transcripts - The recordings directory may grow large over time - monitor disk usage
- Audio files are WAV format, typically 16kHz mono
- Very short recordings (< 1 second) may be noise or squelch breaks
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?