audio-transcriber
Transcribe Audio into Structured Markdown
Audio recordings are difficult to search and convert into reliable notes. This skill creates timestamped transcripts and optional LLM-generated summaries in Markdown.
This skill is part of a pack
Install the whole pack to get every skill the task needs, in one command.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "audio-transcriber" from https://skillstore.io/skills/sickn33-audio-transcriber.md and its manifest at https://skillstore.io/api/skills/sickn33-audio-transcriber/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "audio-transcriber". Transcribe team-standup.mp3 without external LLM processing.
Expected outcome:
A Markdown transcript with source metadata, detected language, processing date, and timestamped speech segments.
Using "audio-transcriber". Create meeting minutes from planning-session.wav after I approve Claude processing.
Expected outcome:
A raw timestamped transcript plus separate minutes covering topics, decisions, action items, and stated deadlines.
Using "audio-transcriber". Summarize research-interview.m4a by theme and retain timestamps.
Expected outcome:
A searchable transcript and a thematic summary that links notable statements to approximate recording times.
Security Audit
High RiskMost static hits are Markdown delimiters, diagnostic redirects, fixed command probes, placeholder credentials, or expected output writes. Seven external-command findings are confirmed because they install unpinned packages automatically or send prompt and transcript content to external LLM CLIs. No embedded audit-targeting prompt injection or shell command-injection path was found.
Confirmed security concerns (2)
Capability review items (7)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
โ๏ธ External commands (50)
๐ Filesystem access (37)
๐ Env variables (18)
๐ Network access (3)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/sickn33-audio-transcriber/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/sickn33-audio-transcriber?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/sickn33-audio-transcriber?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-audio-transcriber/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/sickn33-audio-transcriber.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA ยท BibTeX ยท CFF)
APA citation
sickn33. (2026). audio-transcriber security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-audio-transcriber/audits/5BibTeX citation
@techreport{sickn33-sickn33-audio-transcriber-2026,
author = {sickn33},
title = {audio-transcriber security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/sickn33-audio-transcriber/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "audio-transcriber security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "sickn33"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/sickn33-audio-transcriber/audits/5"
identifiers:
- type: other
value: "skillstore:sickn33-audio-transcriber:audit:5"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Document Team Meetings
Create a timestamped transcript and optional minutes with topics, decisions, and action items.
Prepare Interview Notes
Convert recorded interviews into searchable Markdown for review, quotation checks, and thematic analysis.
Produce Lecture Records
Turn lectures or training recordings into timestamped text with an optional structured summary.
Try These Prompts
Transcribe [audio file] with the base model. Save a timestamped Markdown transcript without LLM processing.
Transcribe [meeting file], then create concise minutes with topics, decisions, owners, and deadlines. Ask before sending content to an external LLM.
Transcribe [interview file]. Create a Markdown summary organized by themes, notable statements, and timestamps. Preserve uncertainty and do not invent speaker names.
Transcribe [audio file] with the [model] model. Apply this framework to the transcript: [framework]. Separate evidence, interpretations, decisions, and unresolved questions.
Best Practices
- Use clear recordings and review names, numbers, decisions, and deadlines against the audio.
- Choose local transcript-only mode for confidential recordings unless external processing is approved.
- Start with a small Whisper model, then increase model size when accuracy needs justify the added resources.
Avoid
- Do not assume generated summaries are exact records of decisions or commitments.
- Do not send confidential transcripts to Claude or GitHub Copilot without informed approval.
- Do not claim speaker identification, subtitles, or batch output when using the current main script.
Frequently Asked Questions
Does transcription work offline?
Which audio formats are supported?
Does the skill identify speakers?
Can it create subtitles?
How are summaries generated?
Where are output files saved?
Developer Details
Author
sickn33License
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
86d877f219e2131f05dd5b37c5e329c71c7b8ec4
Maintenance freshness
7/26/2026
Usage
67 downloads ยท 147 views
File structure
๐ CHANGELOG.md
๐ examples/
๐ README.md
๐ references/
๐ tools-comparison.md
๐ scripts/
๐ transcribe.py
๐ SKILL.md