Agent skill

Video Transcribe

by wendy7756 in wendy7756/AI-Video-Transcriber

Transcribe and summarize a video or podcast from a URL (YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, 30+ platforms) or from a local media/.txt file.

Apache-2.0Auto-check: notesMedia & Creative

Install Video Transcribe

skills CLI

$ npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install wendy7756/AI-Video-Transcriber video-transcribe --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/wendy7756/AI-Video-Transcriber.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/video-transcribe .claude/skills/video-transcribe && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "video-transcribe" agent skill from https://github.com/wendy7756/AI-Video-Transcriber/tree/main/skills/video-transcribe into .claude/skills/video-transcribe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-transcribe", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/wendy7756/AI-Video-Transcriber/tree/main/skills/video-transcribe

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install wendy7756/AI-Video-Transcriber video-transcribe --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wendy7756/AI-Video-Transcriber.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/video-transcribe .agents/skills/video-transcribe && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "video-transcribe" agent skill from https://github.com/wendy7756/AI-Video-Transcriber/tree/main/skills/video-transcribe into .agents/skills/video-transcribe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-transcribe", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install wendy7756/AI-Video-Transcriber video-transcribe --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wendy7756/AI-Video-Transcriber.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/video-transcribe .cursor/skills/video-transcribe && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "video-transcribe" agent skill from https://github.com/wendy7756/AI-Video-Transcriber/tree/main/skills/video-transcribe into .cursor/skills/video-transcribe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-transcribe", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/wendy7756/AI-Video-Transcriber.git --path skills/video-transcribe

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install wendy7756/AI-Video-Transcriber video-transcribe --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wendy7756/AI-Video-Transcriber.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/video-transcribe .gemini/skills/video-transcribe && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "video-transcribe" agent skill from https://github.com/wendy7756/AI-Video-Transcriber/tree/main/skills/video-transcribe into .gemini/skills/video-transcribe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-transcribe", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install wendy7756/AI-Video-Transcriber video-transcribe

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/wendy7756/AI-Video-Transcriber.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/video-transcribe .github/skills/video-transcribe && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "video-transcribe" agent skill from https://github.com/wendy7756/AI-Video-Transcriber/tree/main/skills/video-transcribe into .github/skills/video-transcribe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-transcribe", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install wendy7756/AI-Video-Transcriber video-transcribe --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wendy7756/AI-Video-Transcriber.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/video-transcribe .opencode/skills/video-transcribe && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "video-transcribe" agent skill from https://github.com/wendy7756/AI-Video-Transcriber/tree/main/skills/video-transcribe into .opencode/skills/video-transcribe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "video-transcribe", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: video-transcribe
GitHub stars: 3.3k
Token cost: ~937 tokens
SKILL.md length: 397 words
Files: 1
Skills in repo: 1
Repo updated: Sep 15, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Transcribe and summarize a video or podcast from a URL (YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, 30+ platforms) or from a local media/.txt file.

The user shares a video/podcast link
SKILL.md covers Before running, Run it, Reading the result and Critical: no_speech, plus 1 more section
Calls python, python3 and pip; reaches openrouter.ai; needs OPENAI_API_KEY
Media file and wants a transcript

What it does

Video Transcribe is an agent skill from wendy7756/AI-Video-Transcriber. Transcribe and summarize a video or podcast from a URL (YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, 30+ platforms) or from a local media/.txt file. Use when the user shares a video/podcast link or media file and wants a transcript, summary, translation, or the original video downloaded. Triggers on "transcribe", "summarize this video", "what does this video say", "get the transcript", "转录", "视频摘要".

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Transcription and Podcasting. It works with TikTok, YouTube, Bilibili and OpenAI. The repository describes itself as: Transcribe and summarize videos and podcasts using AI. Open-source, multi-platform, and supports multiple languages. The licence is Apache-2.0.

When your agent uses it

The user shares a video/podcast link
Media file and wants a transcript
The original video downloaded
Summarize this video

Example prompts

“transcribe”
“summarize this video”
“what does this video say”
“/video-transcribe”

Requirements

Python 3
A credential in OPENAI_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 634e6a2. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- python
- python3
- pip
- brew
- apt
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- openrouter.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- OPENAI_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Video Transcribe loads about 937 tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 397 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~107
When it runs · the whole SKILL.md, loaded when a task matches: ~937

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteRuns commands with sudoSKILL.md:21

with `brew install ffmpeg` on macOS or `sudo apt install ffmpeg` on Debian/Ubuntu. Do not proceed without it; audio ext

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wendy7756/AI-Video-Transcriber at commit 634e6a2, republished under its Apache-2.0 licence (© wendy7756). 397 words, ~937 tokens.

Download SKILL.mdSave it as .claude/skills/video-transcribe/SKILL.md (or your agent's skills folder).

name: video-transcribe
description: Transcribe and summarize a video or podcast from a URL (YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, 30+ platforms) or from a local media/.txt file. Use when the user shares a video/podcast link or media file and wants a transcript, summary, translation, or the original video downloaded. Triggers on "transcribe", "summarize this video", "what does this video say", "get the transcript", "转录", "视频摘要".

Video Transcribe

Runs this repo's pipeline headlessly: platform subtitles when available (seconds), local Whisper as fallback, then optimize -> translate -> summarize.

Before running

The command must be run from the AI Video Transcriber repository root and needs the project virtualenv plus ffmpeg. Verify once per session:

bash

ls venv/bin/python && command -v ffmpeg

No venv: run ./install.sh, or python3 -m venv venv && venv/bin/pip install -r requirements.txt.
No ffmpeg: install it first with brew install ffmpeg on macOS or sudo apt install ffmpeg on Debian/Ubuntu. Do not proceed without it; audio extraction will fail.

Run it

bash

venv/bin/python transcribe.py "<URL or file path>" --json

Always pass --json: it puts machine-readable output on stdout and keeps progress chatter on stderr. Parse the JSON rather than scraping log lines.

Useful flags:

Flag	When to use
`-l, --summary-language <code>`	Summary language: `en`, `zh`, `es`, `fr`, `de`, `it`, `pt`, `ru`, `ja`, `ko`, `ar`. Default `en`
`--no-llm`	No API key is available, or the user only wants the raw transcript. Skips optimize/translate/summarize
`--no-video`	The user does not want the source video kept
`--whisper-model small`	Accuracy matters more than speed. `tiny` to `large`, default `base`
`-o <dir>`	Write the Markdown somewhere other than `./temp`

The LLM steps need an OpenAI-compatible key via OPENAI_API_KEY and optionally OPENAI_BASE_URL. Without one the pipeline still transcribes but falls back to basic formatting; prefer --no-llm when the user only needs the transcript.

Provider settings:

bash

export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="https://openrouter.ai/api/v1"
export OPENAI_TRANSLATION_MODEL="gpt-4o"  # optional

For a one-off run, transcribe.py also accepts --api-key, --base-url, and --model. Prefer environment variables when possible so API keys are not written to shell history.

Show full SKILL.md (156 more words)Show less

Reading the result

json

{
  "title": "...",
  "no_speech": false,
  "detected_language": "en",
  "files": { "raw": "...", "transcript": "...", "summary": "...", "translation": "..." },
  "media": { "path": "...", "kind": "video", "size_bytes": 2243691 }
}

Read the transcript and summary paths to get the content. translation is present only when the source language differs from the summary language.

Critical: `no_speech`

When "no_speech": true the source contains no speech. There is no transcript, summary, or translation. The pipeline deliberately skips the LLM so that nothing gets invented.

If you see this, tell the user the video has no speech. Do not guess at the content, infer it from the title, or describe what the video probably says.

Failure modes

Exit 2: bad input, such as a missing file, unsupported extension, or empty text file. Report the message and fix the argument.
Exit 1: download/transcode failure, usually an unreachable URL, region-blocked/private video, or missing ffmpeg. Report the actual error.
First run downloads Whisper weights, so it can look stalled for a minute.
Long videos are slow in Whisper mode. Warn the user before starting if no platform subtitles are available.

Files

Just SKILL.md in skills/video-transcribe of wendy7756/AI-Video-Transcriber.

Open the folder on GitHubat commit 634e6a2

Compare with similar skills

Video Transcribe next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Video Transcribe compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Video Transcribe this skillwendy7756/AI-Video-Transcriber	3.3k	—	~937	Automated safety check: Notes	Apache-2.0	26 days ago
BibiJimmyLv/BibiGPT-v1	6.2k	—	~885	Automated safety check: Pass	GPL-3.0	5 mo ago
Ffmpeg Skillkajisho5/ffmpeg-skill	1.9k	—	~7.4k	Automated safety check: Pass	MIT	yesterday
Video Clip Extractorlinzzzzzz/openclip	569	—	~2.8k	Automated safety check: Warn	MIT	1 mo ago
Watchmathiaschu/watch	142	—	~4k	Automated safety check: Warn	MIT	4 mo ago
VideoiBigQiang/feedgrab	614	—	~1.6k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Bibi
JimmyLv/BibiGPT-v1
BibiGPT CLI for summarizing videos, audio, and podcasts directly in the terminal.
6.2k GitHub stars~885 tokensUpdated 5 mo ago
Media & CreativeAuto-check passed
Ffmpeg Skill
kajisho5/ffmpeg-skill
Edit video and audio with local FFmpeg from natural-language requests: cut, trim, join, resize/reframe (9:16, 1:1), speed change, captions and subtitles (SRT/ASS, animated, karaoke), logos and text…
1.9k GitHub stars~7.4k tokensUpdated yesterday
Media & CreativeAuto-check passed
Video Clip Extractor
linzzzzzz/openclip
Processes videos to identify engaging moments, generate transcripts, and create highlight clips with artistic titles and custom cover images.
569 GitHub stars~2.8k tokensUpdated 1 mo ago
Media & CreativeAuto-check: warnings
Watch
mathiaschu/watch
Watch a video from YouTube, Instagram, X/Twitter, Vimeo, TikTok or any of ~1800 yt-dlp sites (or a local path).
142 GitHub stars~4k tokensUpdated 4 mo ago
Media & CreativeAuto-check: warnings
Video
iBigQiang/feedgrab
Video & Podcast Digest — send a video/podcast link, get full transcript + structured summary.
614 GitHub stars~1.6k tokensUpdated 1 mo ago
Media & CreativeAuto-check passed
Video Clipper
gooseworks-ai/goose-skills
Repurposes long-form video (podcasts, interviews, talks) into short-form vertical clips for Instagram Reels, TikTok, and YouTube Shorts.
1.2k GitHub starsUsed in 1 repo~3.1k tokens
Media & CreativeAuto-check: notes

Works with

Questions about Video Transcribe

What does Video Transcribe do?

Transcribe and summarize a video or podcast from a URL (YouTube, TikTok, Bilibili, Apple Podcasts, SoundCloud, 30+ platforms) or from a local media/.txt file. Video Transcribe is an agent skill from wendy7756/AI-Video-Transcriber.txt file.

When should I use Video Transcribe?

Video Transcribe fits situations like: the user shares a video/podcast link; media file and wants a transcript; the original video downloaded; summarize this video.

How do I install Video Transcribe in Claude Code?

Run `npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a claude-code`. Or copy the skill folder (skills/video-transcribe in wendy7756/AI-Video-Transcriber) into .claude/skills/video-transcribe in your project. Claude Code loads it when a task matches its description.

How do I install Video Transcribe in Codex?

Run `npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a codex`. Or copy the skill folder (skills/video-transcribe in wendy7756/AI-Video-Transcriber) into .agents/skills/video-transcribe in your project. Codex loads it when a task matches its description.

Can I use Video Transcribe in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wendy7756/AI-Video-Transcriber --skill video-transcribe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-transcribe, .gemini/skills/video-transcribe, .github/skills/video-transcribe and .opencode/skills/video-transcribe in your project.

What does Video Transcribe need to run?

Going by SKILL.md and its folder, Video Transcribe needs the command-line tools its instructions call (python, python3, pip, brew and apt) and credentials named OPENAI_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY.

Does Video Transcribe access the network?

SKILL.md names 1 domain. In commands or code: openrouter.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Video Transcribe safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Video Transcribe use?

Video Transcribe is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Video Transcribe use?

About 937 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Video Transcribe?

Skills that share tags, products or a category with Video Transcribe: Bibi (JimmyLv/BibiGPT-v1, 6.2k stars), Ffmpeg Skill (kajisho5/ffmpeg-skill, 1.9k stars), Video Clip Extractor (linzzzzzz/openclip, 569 stars) and Watch (mathiaschu/watch, 142 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Video Transcribe?

wendy7756 (a GitHub user) maintains it in wendy7756/AI-Video-Transcriber, which has 3,334 GitHub stars. The repository was last updated on September 15, 2026.

Source: wendy7756/AI-Video-Transcriber on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Video Transcribe

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Video Transcribe

Before running

Run it

Reading the result

Critical: no_speech

Failure modes

Files

Compare with similar skills

Similar skills

Bibi

Ffmpeg Skill

Video Clip Extractor

Watch

Video

Video Clipper

Related

Questions about Video Transcribe

Critical: `no_speech`