← All skills
audio-voice-recovery
80 / 100 · Low risk
Fine to try.
By pproenca/dot-skills (GitHub) · media · 226 stars · scanned at commit cf93c57
Audio forensics and voice recovery guidelines for CSI-level audio analysis. This skill should be used when recovering voice from low-quality or low-volume audio, enhancing degraded recordings, performing forensic audio analysis, or transcribing difficult audio. Triggers on tasks involving audio enhancement, noise reduction, voice isolation, forensic authentication, or audio transcription.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this.
Found in 126 places.
Show 17 more
- skills/.experimental/audio-voice-recovery/AGENTS.md, line 2488
pip install pyrubberband - skills/.experimental/audio-voice-recovery/AGENTS.md, line 2604
pip install speechbrain - skills/.experimental/audio-voice-recovery/AGENTS.md, line 2628
print("speechbrain not installed. Install with: pip install speechbrain") - skills/.experimental/audio-voice-recovery/AGENTS.md, line 2789
pip install noisereduce - skills/.experimental/audio-voice-recovery/AGENTS.md, line 2838
pip install noisereduce torch torchaudio - skills/.experimental/audio-voice-recovery/AGENTS.md, line 2902
pip install demucs - skills/.experimental/audio-voice-recovery/AGENTS.md, line 2923
pip install asteroid - skills/.experimental/audio-voice-recovery/AGENTS.md, line 3006
pip install demucs - skills/.experimental/audio-voice-recovery/AGENTS.md, line 3009
pip install spleeter - skills/.experimental/audio-voice-recovery/AGENTS.md, line 3012
pip install asteroid-filterbanks asteroid - skills/.experimental/audio-voice-recovery/AGENTS.md, line 3225
pip install torch torchaudio - skills/.experimental/audio-voice-recovery/AGENTS.md, line 4225
brew install rubberband - skills/.experimental/audio-voice-recovery/AGENTS.md, line 5378
pip install openai-whisper - skills/.experimental/audio-voice-recovery/AGENTS.md, line 5381
pip install faster-whisper - skills/.experimental/audio-voice-recovery/AGENTS.md, line 6243
pip install mutagen - skills/.experimental/audio-voice-recovery/AGENTS.md, line 6247
brew install exiftool - skills/.experimental/audio-voice-recovery/AGENTS.md, line 6250
apt-get install libimage-exiftool-perl
and 106 more places
Runs commands on your computer
The author does not mention this.
Found in 17 places.
Show 14 more
- skills/.experimental/audio-voice-recovery/AGENTS.md, line 6047
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/AGENTS.md, line 6085
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/AGENTS.md, line 6874
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/AGENTS.md, line 7537
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/SKILL.md, line 127
python3 skills/.experimental/audio-voice-recovery/scripts/preflight_audio.py evidence.wav --out preflight.json - skills/.experimental/audio-voice-recovery/SKILL.md, line 186
python3 skills/.experimental/audio-voice-recovery/scripts/preflight_audio.py evidence.wav --out preflight.json - skills/.experimental/audio-voice-recovery/references/forensic-chain-custody.md, line 226
subprocess.run([ - skills/.experimental/audio-voice-recovery/references/forensic-metadata.md, line 69
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/references/forensic-metadata.md, line 107
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/references/tool-batch-automation.md, line 118
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/references/tool-install-guide.md, line 238
result = subprocess.run(cmd, capture_output=True, text=True) - skills/.experimental/audio-voice-recovery/references/voice-formant-preserve.md, line 142
subprocess.run(cmd, check=True) - skills/.experimental/audio-voice-recovery/references/voice-rnnoise.md, line 68
subprocess.run([rnnoise_path, str(input_path), str(output_path)], - skills/.experimental/audio-voice-recovery/scripts/preflight_lib.py, line 33
proc = subprocess.run(cmd, capture_output=True, text=True)
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'audio-voice-recovery' ] || [ -L ~/.agents/skills/'audio-voice-recovery' ]; then echo 'A skill folder named audio-voice-recovery already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/pproenca/dot-skills' "$d" && git -C "$d" checkout --quiet 'cf93c57cac89d6fc3e4194686000411567f5caf3' -- 'skills/.experimental/audio-voice-recovery' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/.experimental/audio-voice-recovery' ~/.agents/skills/'audio-voice-recovery' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'audio-voice-recovery' ~/.claude/skills/'audio-voice-recovery' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for pproenca/dot-skills shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/pproenca/dot-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-07 | cf93c57 | 85 |