knoopx/transcribe-audio
agent/skills/tools/transcribe-audio/SKILL.md
Transcribes audio files to text using whisper-cpp (local, offline). Use when converting speech to text, transcribing podcasts, lectures, meetings, or any audio content.
$ install --global
skillsauthnpx skillsauth add knoopx/pi transcribe-audioInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 18, 2026, 6:46 AM187.7s1 file scanned
SKILL.md
- name:
- transcribe-audio
- description:
- Transcribes audio files to text using whisper-cpp (local, offline). Use when converting speech to text, transcribing podcasts, lectures, meetings, or any audio content.
- token_cost:
- 75
transcribe-audio
Transcribes audio files to text using whisper-cpp locally and offline. No API keys or network required.
Basic Transcription
transcribe-audio input.mp3 # Transcribe with default settings
transcribe-audio input.wav --language en # Specify language
transcribe-audio input.flac --model medium # Use a larger model for better accuracy
Options
--language <code>— specify source language (auto-detect by default)--model <size>— choose model size:tiny,base,small,medium,large--output <format>— output format:txt,srt,vtt(default:txt)--timestamp— include timestamps in output
Supported Formats
MP3, WAV, FLAC, OGG, M4A, and any format whisper-cpp supports. For best results, use uncompressed WAV or FLAC.
Tips
- Larger models (
medium,large) are more accurate but slower - Auto-detect language works well for common languages; specify explicitly for mixed-language audio
- Output with timestamps is useful for subtitles:
transcribe-audio file.mp4 --output vtt - All processing is local — no data leaves your machine
Related Skills
knoopx/notify
tools
VerifiedTrustedCommunity
Inform the user what is happening — skip passive lookups
52SKILL.mdUpdated May 20, 2026
knoopx/markdown-rendering
development
VerifiedTrustedCommunity
Renders markdown to self-contained HTML with a custom dark stylesheet and opens in browser. Use when previewing markdown documents, generating styled HTML from README or report files.
52SKILL.mdUpdated May 20, 2026
knoopx/jj-hunk
testing
VerifiedTrustedCommunity
Programmatic hunk selection for Jujutsu — split, commit, or squash specific hunks without interactive prompts. Use when making partial commits or selective squashes.
52SKILL.mdUpdated May 18, 2026
knoopx/jj-core
content-media
VerifiedTrustedCommunity
Manage version control with Jujutsu (jj) — no staging area, immediate changes, smart rebasing. Use when navigating history, squashing, or pushing to Git remotes.
52SKILL.mdUpdated May 18, 2026