video-transcript
Skill1 starsChanged 27 days agoMITView on GitHub
把视频链接或音频文件转成带说话人区分的逐字稿。链路:下载→抽音频→faster-whisper 转写→ECAPA 声纹聚类分说话人→话轮合并。
- Installs packages
17 other projects use a version of this.
Adopted by
Most recently taken up by
- spongetimblin/claude-skill-librarytheir own version, first seen Nov 8, 2026
- thatjuan/agent-skillstheir own version, first seen Nov 8, 2026
- notque/vexjoy-agenttheir own version, first seen Nov 7, 2026
- Ntmib/jarvis-architecttheir own version, first seen Nov 1, 2026
- guipi888/workbuddy-video-transcripttheir own version, first seen Oct 25, 2026
- PerpperQAQ/video-transcripttheir own version, first seen Oct 13, 2026
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- ZeroPointRepo/youtube-skills★ 972same name
- notque/claude-code-toolkit★ 448same name
- notque/vexjoy-agent★ 448same name
- Backtthefuture/huangshu★ 274same name
- artemchuikin/youtube-skills★ 273same name
- bozhouDev/video-skills-toolkit★ 147same name
- Ntmib/jarvis-architect★ 4same name
- shalomb/agent-skills★ 3same name
- kuiilabs/claude-skills★ 2same name
- guipi888/workbuddy-video-transcript★ 1same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- ai-freebiesSkill
- ai-memory-managementSkill
- authorization-timingSkill
- booking-pitfall-checklistSkill
- deliverable-document-qaSkill
- email-triageSkill
- github-gitdb-pushSkill
- life-decision-guideSkill
- moments-displaySkill
- multi-channel-parallel-researchSkill
- openrouterSkill
- personal-goal-breakdownSkill
- table-data-verificationSkill
- task-acceptance-checklistSkill
- tencent-mapSkill
- volcengine-arkSkill
- x-post-fetchSkill
- zhizengzengSkill
- your-skill-nameSkill
The file
Files
视频转逐字稿(标准流程)
把录音或视频链接转成文字稿,统一按以下样式和流程处理。
一、固定输出样式
[00:00:00] 说话人A:同一人连续说的完整的一段话……
[00:00:05] 说话人B:另一人接的完整的一段话……规则:
- 每话轮只记一个开始时间戳(
[HH:MM:SS]),不逐句打时间戳; - 必须区分说话人(声纹聚类自动分,名字按内容推断后须经用户确认);
- 同一说话人连续说的内容合并为一段完整的话,不要碎成短句。
二、流程(按顺序执行)
1. 获取音频
- 本地音频/视频文件:直接用(推荐);
- 在线视频:请先用常规方式拿到本地文件后再处理(如 yt-dlp 下载公开视频,或在 App 里保存);平台要求登录验证的,请用户自行完成下载。
2. 抽音频(统一转 16kHz 单声道 wav)
ffmpeg -y -i 输入.mp4 -vn -ar 16000 -ac 1 -c:a pcm_s16le 音频.wav3. 转写 + 说话人分离 + 话轮合并(一键脚本)
python scripts/diarize_transcribe.py 音频.wav --speakers 2 --names "说话人1,说话人2" --out 逐字稿.txt--speakers:说话人数(访谈一般为 2);--names:可选,名字顺序对应聚类标签 0,1,…;不填则输出"说话人A/B";- 脚本逻辑:faster-whisper 转写 → 每个片段提 ECAPA 声纹 embedding → 余弦聚类分说话人 → 连续同说话人片段合并为话轮。
4. 质检后交付
- small 模型有少量谐音误识别(如"太干货"→"太干活"),正式用途换 medium/large 模型或人工校一遍;
- 说话人名字为内容推断时,必须在交付时说明"名字是推断的,对不上请纠正"。
三、环境准备
需要 Python 环境,安装:
pip install faster-whisper speechbrain scikit-learn scipy soundfile系统工具:ffmpeg、yt-dlp。
两个必记的坑
- PyAV 必须
<19:PyAV 19.0.0 删掉了av.open()的metadata_errors参数,faster-whisper 1.2.1 仍在传它,会报TypeError。固定安装av==18.1.0,不要升级。 - 模型下载时 httpx 报
Invalid port:如果本机no_proxy环境变量含[::1]方括号写法,huggingface_hub 解析不了。运行时覆盖:no_proxy="localhost,127.0.0.1" NO_PROXY="localhost,127.0.0.1" python scripts/diarize_transcribe.py ...
四、可选加速(云端 ASR)
本地转写吃 CPU/耗时较长时,可考虑云端 ASR 替代(按各自免费额度政策):
- 硅基流动 SenseVoiceSmall:免费、OpenAI 兼容接口、中文识别强,适合替换本地转写;
- 腾讯云语音识别:新用户有免费资源包额度。
接入时做好"额度用尽降级回本地 faster-whisper"的兜底。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

