How do I install the Video Url Transcriber skill?

Run npx skillmds@latest add tomevault-io/video-url-transcriber in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Video Url Transcriber safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Video Url Transcriber?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Video Url Transcriber free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Video Url Transcriber?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Video Url Transcriber by tomevault-io

Name: Video Url Transcriber
Author: tomevault-io

Video Url Transcriber

Transcribe a video/audio URL into timestamped JSON using yt-dlp + ffmpeg + faster-whisper. Use when an agent needs platform-agnostic URL-to-transcript ingestion for downstream analysis. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Video URL Transcriber Skill

Use this skill when a user asks for transcript extraction from a public media URL (YouTube, X, and any site supported by yt-dlp).

Preconditions

Install system deps:

brew install ffmpeg yt-dlp

Install Python deps from repo root:

pip install -r requirements.txt

Minimal workflow

Run dependency check:

python3 skill/video-url-transcriber/scripts/transcribe_url.py --doctor

Run one-shot URL transcription:

python3 skill/video-url-transcriber/scripts/transcribe_url.py "https://www.youtube.com/watch?v=..." --model-size small

Return JSON output with:

source_url
platform
title
duration_sec
language
transcript
segments[] with timestamps and optional words

API mode (agent workers)

Start API service:

python3 skill/video-url-transcriber/scripts/run_api.py

Transcribe request:

curl -s http://127.0.0.1:8099/transcribe \
  -H 'content-type: application/json' \
  -d '{
    "url": "https://www.youtube.com/watch?v=...",
    "language": null,
    "model_size": "small",
    "word_timestamps": true,
    "persist_media": false
  }'

Optional auth-gated media

Default policy: do not use browser cookies for public URLs.

If and only if the user explicitly approves personal browser/session usage, pass browser cookies with explicit opt-in:

python3 skill/video-url-transcriber/scripts/transcribe_url.py "<url>" --cookies-from-browser chrome --allow-personal-cookies

Execution rules

Always normalize audio to mono 16k WAV before ASR.
Never use browser cookies/keychain data unless user explicitly asks for it.
Default model_size is small; raise to medium/large-v3 only when user asks for higher quality.
Prefer persist_media=false unless user explicitly wants artifacts retained.
If transcription fails, return exact failing stage: fetch, ffmpeg normalize, or asr.

Source: nativ3ai/universal-video-transcriber — distributed by TomeVault.

---name: video-url-transcriberdescription: Transcribe a video/audio URL into timestamped JSON using yt-dlp + ffmpeg + faster-whisper. Use when an agent needs platform-agnostic URL-to-transcript ingestion for downstream analysis. Use when this capability is needed.---# Video URL Transcriber SkillUse this skill when a user asks for transcript extraction from a public media URL (YouTube, X, and any site supported by yt-dlp).## PreconditionsInstall system deps:```bashbrew install ffmpeg yt-dlp```Install Python deps from repo root:```bashpip install -r requirements.txt```## Minimal workflow1. Run dependency check:```bashpython3 skill/video-url-transcriber/scripts/transcribe_url.py --doctor```2. Run one-shot URL transcription:```bashpython3 skill/video-url-transcriber/scripts/transcribe_url.py "https://www.youtube.com/watch?v=..." --model-size small```3. Return JSON output with:- `source_url`- `platform`- `title`- `duration_sec`- `language`- `transcript`- `segments[]` with timestamps and optional words## API mode (agent workers)Start API service:```bashpython3 skill/video-url-transcriber/scripts/run_api.py```Transcribe request:```bashcurl -s http://127.0.0.1:8099/transcribe \ -H 'content-type: application/json' \ -d '{ "url": "https://www.youtube.com/watch?v=...", "language": null, "model_size": "small", "word_timestamps": true, "persist_media": false }'```## Optional auth-gated mediaDefault policy: do **not** use browser cookies for public URLs.If and only if the user explicitly approves personal browser/session usage, pass browser cookies with explicit opt-in:```bashpython3 skill/video-url-transcriber/scripts/transcribe_url.py "<url>" --cookies-from-browser chrome --allow-personal-cookies```## Execution rules- Always normalize audio to mono 16k WAV before ASR.- Never use browser cookies/keychain data unless user explicitly asks for it.- Default `model_size` is `small`; raise to `medium`/`large-v3` only when user asks for higher quality.- Prefer `persist_media=false` unless user explicitly wants artifacts retained.- If transcription fails, return exact failing stage: `fetch`, `ffmpeg normalize`, or `asr`.---> Source: [nativ3ai/universal-video-transcriber](https://github.com/nativ3ai/universal-video-transcriber) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions