Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pproenca/dot-skills --skill audio-voice-recoverygit clone --depth 1 https://github.com/pproenca/dot-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pproenca/dot-skills/audio-voice-recovery)<a href="https://agentmods.dev/skills/pproenca/dot-skills/audio-voice-recovery"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/audio-voice-recovery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pproenca/dot-skills/audio-voice-recovery"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/audio-voice-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.02963 |
| Opus 5 | $0.00036 | $0.01482 |
| Sonnet 5 | $0.00014 | $0.00593 |
| Haiku 4.5 | $0.00007 | $0.00296 |
Grade A, and why
audio-voice-recovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forensic Audio Research Audio Voice Recovery Best Practices
Comprehensive audio forensics and voice recovery guide providing CSI-level capabilities for recovering voice from low-quality, low-volume, or damaged audio recordings. Contains 45 rules across 8 categories, prioritized by impact to guide audio enhancement, forensic analysis, and transcription workflows.
When to Apply
Reference these guidelines when:
- Recovering voice from noisy or low-quality recordings
- Enhancing audio for transcription or legal evidence
- Performing forensic audio authentication
- Analyzing recordings for tampering or splices
- Building automated audio processing pipelines
- Transcribing difficult or degraded speech
Rule Categories by Priority
| Priority | Category | Impact | Prefix | Rules |
|---|---|---|---|---|
| 1 | Signal Preservation & Analysis | CRITICAL | signal- |
5 |
| 2 | Noise Profiling & Estimation | CRITICAL | noise- |
5 |
| 3 | Spectral Processing | HIGH | spectral- |
6 |
| 4 | Voice Isolation & Enhancement | HIGH | voice- |
7 |
| 5 | Temporal Processing | MEDIUM-HIGH | temporal- |
5 |
| 6 | Transcription & Recognition | MEDIUM | transcribe- |
5 |
| 7 | Forensic Authentication | MEDIUM | forensic- |
5 |
| 8 | Tool Integration & Automation | LOW-MEDIUM | tool- |
7 |
Quick Reference
1. Signal Preservation & Analysis (CRITICAL)
signal-preserve-original- Never modify original recordingsignal-lossless-format- Use lossless formats for processingsignal-sample-rate- Preserve native sample ratesignal-bit-depth- Use maximum bit depth for processingsignal-analyze-first- Analyze before processing
2. Noise Profiling & Estimation (CRITICAL)
noise-profile-silence- Extract noise profile from silent segmentsnoise-identify-type- Identify noise type before reductionnoise-adaptive-estimation- Use adaptive estimation for non-stationary noisenoise-snr-assessment- Measure SNR before and afternoise-avoid-overprocessing- Avoid over-processing and musical artifacts
What ships with it
53 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENTS.md 250 KB
- assets/templates/_template.md 1.1 KB
- metadata.json 1.4 KB
- references/_sections.md 2.1 KB
- references/forensic-chain-custody.md 8.1 KB
- references/forensic-enf-analysis.md 7.9 KB
- references/forensic-metadata.md 8.7 KB
- references/forensic-speaker-id.md 7.9 KB
- references/forensic-tampering.md 10 KB
- references/noise-adaptive-estimation.md 3.8 KB
- references/noise-avoid-overprocessing.md 4.6 KB
- references/noise-identify-type.md 4.0 KB
- references/noise-profile-silence.md 3.3 KB
- references/noise-snr-assessment.md 4.4 KB
- references/signal-analyze-first.md 3.9 KB
- references/signal-bit-depth.md 2.2 KB
- references/signal-lossless-format.md 1.6 KB
- references/signal-preserve-original.md 1.4 KB
- references/signal-sample-rate.md 1.9 KB
- references/spectral-band-limiting.md 4.3 KB
- references/spectral-declip.md 5.5 KB
- references/spectral-equalization.md 4.8 KB
- references/spectral-notch-filter.md 4.0 KB
- references/spectral-subtraction.md 3.7 KB
- references/spectral-wiener-filter.md 4.5 KB
- references/temporal-dynamic-range.md 6.4 KB
- references/temporal-noise-gate.md 5.9 KB
- references/temporal-silence-trim.md 5.8 KB
- references/temporal-time-stretch.md 5.2 KB
- references/temporal-transient-repair.md 6.2 KB
- references/tool-audacity-workflow.md 5.0 KB
- references/tool-batch-automation.md 7.7 KB
- references/tool-ffmpeg-essentials.md 5.0 KB
- references/tool-install-guide.md 6.3 KB
- references/tool-python-pipeline.md 8.5 KB
- references/tool-quality-assessment.md 7.8 KB
- references/tool-sox-commands.md 4.8 KB
- references/transcribe-confidence.md 6.7 KB
- references/transcribe-hallucination.md 7.1 KB
- references/transcribe-multipass.md 6.7 KB
- references/transcribe-segment.md 7.7 KB
- references/transcribe-whisper.md 5.9 KB
- references/voice-dereverb.md 5.4 KB
- references/voice-dialogue-isolate.md 4.8 KB
- references/voice-enhance-speech.md 5.5 KB
- references/voice-formant-preserve.md 5.4 KB
- references/voice-frequency-boost.md 6.0 KB
- references/voice-rnnoise.md 4.3 KB
- references/voice-vad-segment.md 5.8 KB
- scripts/compare_audio.py 3.7 KB runs code
- scripts/plan_from_preflight.py 4.2 KB runs code
- scripts/preflight_audio.py 1.8 KB runs code
- scripts/preflight_lib.py 12 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 230 lines · 71 tokens per session scan A 892c8fe5616e
audio-voice-recovery is a skill published in the GitHub repository pproenca/dot-skills (207 stars, last pushed 26d ago), licensed MIT. It adds 71 tokens to every session and 2,963 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
seedance-copyright
This skill should be used when a Seedance 2.0 prompt mentions named characters, franchises, studios, celebrities, public figures, private people, brand logos, copyrighted scenes, songs, voices, or real-person likeness workflows and needs an IP-safe rewrite.
voice-conversion-studio
A voice-conversion tool that changes a provided recording into an authorised target voice.
voice-clone-lab
A consent-controlled tool for creating a reusable synthetic voice from a local speaker recording.
c2pa-metadata
Embed a C2PA provenance manifest into an AI-generated marketing asset (PNG, JPG, WebP, GIF, TIFF, MP4, MOV, WebM, MP3, WAV, PDF) via scripts/embed-c2pa.py — produces a signed copy of the file carrying IPTC digital-source-type AI claims, an optional c2pa.ai-disclosure assertion for EU AI Act Article 50 (applicable 2…
suede-rights-passport
Suede Labs skill that turns messy creator materials into a local, offline rights-and-provenance transfer package: inventoried and hashed assets, a normalized suede-intake.json manifest, credits and splits, license notes, provenance, and a missing-information report, validated by a bundled stdlib script. Use when a…
suede-rights-audit
Suede Labs skill that finds and organizes the rights gaps in a creator project before packaging: ownership, contributors, splits, samples, licenses, provenance, metadata, licensing readiness, and royalty-routing readiness, each marked confirmed or unknown against an evidence trail. Use when a song, release, or…