Provided by TikHub
YouTube video captions
Video captions from YouTube via TikHub. One request per call; TikHub bills the request whether or not data comes back, and an empty data envelope is reported as no result.
How to run it
Step 1Set up
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.md
Show me how to use the TikHub endpoint /api/v1/youtube/web_v2/get_video_captions on Glasser.glasser run -p tikhub -e '/api/v1/youtube/web_v2/get_video_captions' -i '{"video_id":"dQw4w9WgXcQ"}' --endpoint-version 1Uses endpoint version 1. Inspect the current price before running. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(uuidgen)Run it, and copy this same block to send it again:
curl -X POST https://api.glasser.ai/v1/runs \
-H "Authorization: Bearer gl_..." \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"tikhub","endpoint":"/api/v1/youtube/web_v2/get_video_captions","input":{"video_id":"dQw4w9WgXcQ"},"endpoint_version":1}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 1; inspect the current price before running.
Step 2Try a specific example task
When you need to prepare a research brief, you might find published posts about your topic and use them as source material.
Copy this prompt into your agent to find relevant posts for your research brief.
Use tikhub:/api/v1/youtube/web_v2/get_video_captions on Glasser.
Find published content about my topic in the returned posts for a research brief.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"format": {
"enum": [
"srt",
"xml",
"json3",
"txt"
],
"type": "string",
"description": "Caption format - srt: SubRip subtitle format (with timestamps) - xml: Raw XML format - json3: JSON format (YouTube raw structure) - txt: Plain text (no timestamps)"
},
"video_id": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "Video ID (recommended)"
},
"video_url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "Full video URL (optional)"
},
"language_code": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "Language code (e.g. en, zh-Hans, a.en), returns available caption list if empty"
}
},
"additionalProperties": false
}{
"video_id": "dQw4w9WgXcQ"
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How pricing works
| Data returned or no match | The same price with or without matching data. | $0.012 |
|---|---|---|
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The Run exceeded its time limit. | $0.00 |
| Internal failure | An internal error prevented completion. | $0.00 |