audio-transcriber

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

执行命令写文件联网读环境变量（配置）严重 0 · 高危 18sickn33/agentic-awesome-skills

它会碰到什么

扫了多少8 个文本文件，68 KB

它会碰到什么执行命令写文件联网读环境变量（配置）

命中总数26 处

命中统计严重 0 · 高 18 · 中 5 · 低 0

关于「读环境变量（配置）」：这个技能会读 process.env 之类的环境变量，但读到的都是端口、目录、超时这类配置项，没有读取密钥类变量。扫描规则原本把「读环境变量」一律算作「读凭据」，本站按变量名做了细化区分，命中明细仍如实列在下面。

逐条看命中（18 条严重或高危）

高 examples/basic-transcription.sh:124cred-envread
```
audio_file = os.environ["AUDIO_FILE_ENV"]
```
高 examples/basic-transcription.sh:125cred-envread
```
model_name = os.environ["MODEL_ENV"]
```
高 examples/basic-transcription.sh:126cred-envread
```
transcriber = os.environ["TRANSCRIBER_ENV"]
```
高 examples/basic-transcription.sh:127cred-envread
```
temp_json = os.environ["TEMP_JSON_ENV"]
```

高 examples/basic-transcription.sh:183cred-envread

with open(os.environ["TEMP_JSON_ENV"], encoding="utf-8") as f:

高 examples/basic-transcription.sh:187cred-envread

filename = os.path.basename(os.environ["AUDIO_FILE_ENV"])

高 examples/basic-transcription.sh:188cred-envread
```
file_size = os.environ["FILE_SIZE_ENV"]
```
高 examples/basic-transcription.sh:189cred-envread
```
duration_hms = os.environ["DURATION_HMS_ENV"]
```
高 examples/basic-transcription.sh:193cred-envread
```
transcriber = os.environ["TRANSCRIBER_ENV"]
```
高 examples/basic-transcription.sh:194cred-envread
```
model_name = os.environ["MODEL_ENV"]
```

高 examples/basic-transcription.sh:237cred-envread

with open(os.environ["OUTPUT_FILE_ENV"], "w", encoding="utf-8") as f:

高 examples/basic-transcription.sh:240cred-envread

print(f"✅ Markdown report saved: {os.environ['OUTPUT_FILE_ENV']}")

高 scripts/transcribe.py:39exec-spawn

subprocess.run([sys.executable, "-m", "pip", "install", "--user", "rich"], check=False)

高 scripts/transcribe.py:51exec-spawn

subprocess.run([sys.executable, "-m", "pip", "install", "--user", "tqdm"], check=False)

高 scripts/transcribe.py:98exec-spawn

result = subprocess.run(['gh', 'copilot', '--version'],

高 scripts/transcribe.py:120exec-spawn
```
result = subprocess.run(
```
高 scripts/transcribe.py:302exec-spawn
```
result = subprocess.run(
```
高 scripts/transcribe.py:310exec-spawn
```
result = subprocess.run(
```

这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。

技能内容

Detailed Guide

Read [the detailed guide](references/detailed-guide.md) before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.

When to Use

Invoke this skill when:

User needs to transcribe audio/video files to text
User wants meeting minutes automatically generated from recordings
User requires speaker identification (diarization) in conversations
User needs subtitles/captions (SRT, VTT formats)
User wants executive summaries of long audio content
User asks variations of "transcribe this audio", "convert audio to text", "generate meeting notes from recording"
User has audio files in common formats (MP3, WAV, M4A, OGG, FLAC, WEBM)

Example Usage

Example 1: Basic Transcription

User Input:

copilot> transcribe audio to markdown: meeting-2026-02-02.mp3

Skill Output:

✅ Faster-Whisper detected (optimized)
✅ ffmpeg available (format conversion enabled)

📂 File: meeting-2026-02-02.mp3
📊 Size: 12.3 MB
⏱️  Duration: 00:45:32

🎙️  Processing...
[████████████████████] 100%

✅ Language detected: Portuguese (pt-BR)
👥 Speakers identified: 4
📝 Generating Markdown output...

✅ Transcription Complete!

📊 Results:
  File: meeting-2026-02-02.md
  Language: pt-BR
  Duration: 00:45:32
  Speakers: 4
  Words: 6,842
  Processing time: 127s

📝 Generated:
  - meeting-2026-02-02.md (Markdown report)

🎯 Next steps:
  1. Review meeting minutes and action items
  2. Share report with participants
  3. Track action items to completion

Example 3: Batch Processing

User Input:

copilot> transcreva estes áudios: recordings/*.mp3

Skill Output:

📦 Batch mode: 5 files found
  1. team-standup.mp3
  2. client-call.mp3
  3. brainstorm-session.mp3
  4. product-demo.mp3
  5. retrospective.mp3

🎙️  Processing batch...

[1/5] team-standup.mp3 ✅ (2m 34s)
[2/5] client-call.mp3 ✅ (15m 12s)
[3/5] brainstorm-session.mp3 ✅ (8m 47s)
[4/5] product-demo.mp3 ✅ (22m 03s)
[5/5] retrospective.mp3 ✅ (11m 28s)

✅ Batch Complete!
📝 Generated 5 Markdown reports
⏱️  Total processing time: 6m 15s

Example 5: Large File Warning

User Input:

copilot> transcribe audio to markdown: conference-keynote.mp3

Skill Output:

✅ Faster-Whisper detected (optimized)

📂 File: conference-keynote.mp3
📊 Size: 87.2 MB
⏱️  Duration: 02:15:47
⚠️  Large file (87.2 MB) - processing may take several minutes

Continue? [Y/n]:

User: Y

🎙️  Processing... (this may take 10-15 minutes)
[████░░░░░░░░░░░░░░░░] 20% - Estimated time remaining: 12m

This skill is platform-agnostic and works in any terminal context where GitHub Copilot CLI is available. It does not depend on specific project configurations or external APIs, following the zero-configuration philosophy.

Limitations

Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

想直接用这个技能？

本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。

去原始仓库

它属于哪个仓库

仓库sickn33/agentic-awesome-skills

星标★ 46,490

本站分层T1

该仓技能数6676

原文件路径plugins/agentic-awesome-skills/skills/audio-transcriber/SKILL.md

同一个仓库里的其他技能

看这个仓库的全部 6676 个技能

同名技能的其他版本

有 3 个不同仓库或目录里都有叫 audio-transcriber 的技能。它们内容并不相同，别混用：

sickn33/agentic-awesome-skills — Transform audio recordings into professional Markdown documentation with intelligent summa
sickn33/agentic-awesome-skills — Transform audio recordings into professional Markdown documentation with intelligent summa