mcpbeat

Podcast Transcribe

chubbyguan/podcast-transcribe

> 播客/小宇宙 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持 RSS 批量下载、单集链接转录。

4k tokens
context cost
the whole folder, loaded on every use
4
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
588
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/chubbyguan/chubbyskills --skill podcast-transcribe

The instruction itself

5 sections, as written by the author

播客转录 Skill

将播客音频下载并转录为文字,存为 Markdown 文件。支持小宇宙、喜马拉雅等平台。

环境要求

# Python 3.9+
python -m venv .venv
source .venv/bin/activate

# 依赖
pip install faster-whisper

# 系统依赖
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg

使用方法

单集转录

python scripts/transcribe.py "https://www.xiaoyuzhoufm.com/episode/xxxxx"

批量转录(RSS)

python scripts/batch_transcribe.py --rss-url "http://www.ximalaya.com/album/xxxxx.xml" --count 10

流程

Step 1: 下载音频

支持多种来源:

  • 小宇宙单集链接(自动从页面提取音频 URL)
  • 喜马拉雅链接
  • 直接音频 URL(.mp3/.m4a/.wav)
  • RSS feed 中的音频链接

注意:小宇宙/喜马拉雅等平台会从页面 HTML 中自动解析 og:audio<audio> 标签或内嵌 JSON 获取真实音频地址,无需手动提取。

Step 2: faster-whisper 转录

from faster_whisper import WhisperModel

model = WhisperModel('small', device='cpu', compute_type='int8')
segments, info = model.transcribe(
    audio_path,
    language='zh',
    beam_size=5,
    vad_filter=True,
)

Step 3: 生成 Markdown

自动创建带 frontmatter 的 Markdown 文件。

性能数据

| 模型 | 速度 (CPU) | 中文准确率 |

|------|------|------|

| faster-whisper tiny | ~149s/1h | 一般 |

| faster-whisper small | ~10min/h | 良好 (~85-90%) |

| faster-whisper large-v3 | ~30-60min/h | 最佳 |

已知限制

  • CPU 推理较慢,长播客需要较长时间
  • 中文准确率约 85-90%,需要人工校对
  • 首次运行会下载模型(small: ~461MB)
  • 不支持说话人分离

参考项目

⚖️ 合规声明

仅供个人学习与研究使用。请遵守目标平台的服务条款(ToS)与 robots 规则,控制请求频率,不要用于批量抓取、商用爬取或侵犯他人权益的场景。下载内容的版权归原作者所有。

How to use it

Copy the folder

Take chubbyguan/podcast-transcribe from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference pip, brew. Without those the skill loads but fails at the first command.