Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Create a verbatim transcript for a YouTube URL using Google Gemini (speaker labels, paragraph breaks; no time codes). Use when the user asks to transcribe a YouTube video or wants a clean transcript (
Imported from Demerzels-lab/elsamultiskillagent (public/skills/odrobnik/gemini-yt-video-transcript/SKILL.md). Install upstream with npx skills add Demerzels-lab/elsamultiskillagent --skill gemini-yt-video-transcript. Copyright stays with the author.
Gemini YouTube Video Transcript
Create a verbatim transcript for a YouTube URL using Google Gemini.
--out <path> Write transcript to a specific file (default: auto-named in the workspace out/ folder).
Delivery
When chatting: send the resulting transcript as a document/attachment.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "demerzels-lab-elsamultiskillagent-gemini-yt-video-transcript",
"kind": "skill",
"name": "gemini-yt-video-transcript",
"description": "Create a verbatim transcript for a YouTube URL using Google Gemini (speaker labels, paragraph breaks; no time codes). Use when the user asks to transcribe a YouTube video or wants a clean transcript (no timestamps).",
"publisher": "Demerzels-lab",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Create a verbatim transcript for a YouTube URL using Google Gemini (speaker labels, paragraph breaks; no time codes). Use when the user asks to transcribe a YouTube video or wants a clean transcript (no timestamps)."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/Demerzels-lab/elsamultiskillagent",
"path": "public/skills/odrobnik/gemini-yt-video-transcript/SKILL.md",
"ref": "f45fcb5e73f2335658ba629bf17887f5895c7ccf",
"url": "https://github.com/Demerzels-lab/elsamultiskillagent/blob/f45fcb5e73f2335658ba629bf17887f5895c7ccf/public/skills/odrobnik/gemini-yt-video-transcript/SKILL.md",
"key": "Demerzels-lab/elsamultiskillagent/public/skills/odrobnik/gemini-yt-video-transcript/SKILL.md"
}
},
"instructions": "# Gemini YouTube Video Transcript\n\nCreate a **verbatim transcript** for a YouTube URL using **Google Gemini**.\n\n**Output format**\n- First line: YouTube video title\n- Then transcript lines only in the form:\n\n```\nSpeaker: text\n```\n\n**Requirements**\n- No time codes\n- No extra headings / lists / commentary\n\n## Usage\n\n```bash\npython3 {baseDir}/scripts/youtube_transcript.py \"https://www.youtube.com/watch?v=...\"\n```\n\nOptions:\n- `--out <path>` Write transcript to a specific file (default: auto-named in the workspace `out/` folder).\n\n## Delivery\n\nWhen chatting: send the resulting transcript as a docume",
"cost": {
"context_tokens": 153
}
}
Fetch it by URL: GET /api/v1/registry/demerzels-lab-elsamultiskillagent-gemini-yt-video-transcript/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
