Skip to content
cccskills
FreePublished on GitHub

tiktok-transcribe

TikTok 视频 → 下载 → 转录 → 存为 Markdown。支持 vm.tiktok.com / vt.tiktok.com 短链和完整链接,无需登录。

The English summary is being prepared. Showing the original description.

Works withTikTok
See how to install

Files included (3)

  • SKILL.md2.9 KB
  • requirements.txt64 B
  • scripts/transcribe.py3.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

TikTok 视频转录 Skill

将 TikTok 视频下载音频,用 SenseVoice-Small 转录为文字,存为带 frontmatter 的 Markdown 文件。内容中英混杂时自动检测语言。

环境要求

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

# 依赖
pip install funasr modelscope torch torchaudio

# 系统依赖
# macOS: brew install ffmpeg yt-dlp
# Ubuntu: sudo apt install ffmpeg && pip install yt-dlp

使用方法

# 完整链接
python scripts/transcribe.py "https://www.tiktok.com/@user/video/1234567890"

# 短链(自动跟随跳转)
python scripts/transcribe.py "https://vm.tiktok.com/xxxxx"
python scripts/transcribe.py "https://vt.tiktok.com/xxxxx"

# 指定输出目录
python scripts/transcribe.py "https://vm.tiktok.com/xxxxx" -o ./output

流程

Step 1: yt-dlp 下载音频

TikTok 有地区限制,脚本默认加 --geo-bypass。短链由 yt-dlp 自动跟随跳转,无需手动处理。

yt-dlp --extract-audio --audio-format mp3 --audio-quality 128K \
  --geo-bypass \
  "https://vm.tiktok.com/xxxxx"

Step 2: SenseVoice-Small 转录

from funasr import AutoModel

model = AutoModel(
    model="iic/SenseVoiceSmall",
    trust_remote_code=True,
    vad_model="fsmn-vad",
    vad_kwargs={"max_single_segment_time": 30000},
    device="cpu",
)

result = model.generate(
    input=audio_path,
    language="auto",   # TikTok 中英混杂,自动检测
    use_itn=True,
    batch_size_s=60,
)

Step 3: 生成 Markdown

脚本自动创建带 frontmatter 的 Markdown 文件,包含来源链接、作者、语言和转录文本。

已知限制

  • 地区限制:部分地区或网络环境下 TikTok 内容可能无法访问,--geo-bypass 可缓解但不保证解决
  • 反爬:频繁请求可能触发限流;脚本内置重试,仍建议控制频率
  • 语言混合:language=auto 对中英混杂内容可用,但长英文段落质量不如专用英文模型
  • 登录态:私密账号内容需要登录,当前脚本不携带登录态
  • 模型大小:SenseVoice-Small 首次下载约 893MB

致谢

⚖️ 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。

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

哔哩哔哩视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持 BV 号和完整链接,无需登录。

The English summary is being prepared. Showing the original description.

chubbyguan/chubbyskills1.3KUpdated Oct 14, 2026

内容加工:给任意采集产物(转录稿 / 文章 / 笔记)自动补「摘要 + 要点 + 标签 + 价值判断」, 写进 frontmatter 并在正文顶部插入摘要块。是「加工层」通用能力,惠及仓库所有采集 skill。

The English summary is being prepared. Showing the original description.

chubbyguan/chubbyskills1.3KUpdated Oct 14, 2026

抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持短链接和完整链接;优先无 cookie 直采,被风控时回退 yt-dlp + 浏览器 cookie(无需登录)。

The English summary is being prepared. Showing the original description.

chubbyguan/chubbyskills1.3KUpdated Oct 14, 2026

行业情报雷达:多源扫描(X/即刻/V2EX/HN) → 关键词过滤 → 趋势检测 → 每日情报简报。触发词:行业情报、竞品监控、热点扫描、情报雷达

The English summary is being prepared. Showing the original description.

chubbyguan/chubbyskills1.3KUpdated Oct 14, 2026

管理本地 Markdown/Obsidian 知识库:素材入库、健康检查、增量索引、关键词与 semantic-lite 检索、逐字原文资料包、归档和 MCP 连接。用于搜索知识库、整理资料及为 Agent 准备可定位的引用。

The English summary is being prepared. Showing the original description.

chubbyguan/chubbyskills1.3KUpdated Oct 14, 2026

学习笔记自动化:视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词:学习笔记、闪卡、Anki、知识提取、视频学习

The English summary is being prepared. Showing the original description.

chubbyguan/chubbyskills1.3KUpdated Oct 14, 2026

See all skills by chubbyguan

Report a problem with this skill