Video transcript

Use when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text, or extract information from video content.

How to use it

Claude Code
  1. Run the line below. It pulls the whole folder into ~/.claude/skills/video-transcript.
  2. Describe your job in plain words. Claude Code follows the skill from there.
Claude Code — installs the whole folder, not just SKILL.md
npx degit ZeroPointRepo/youtube-skills/skills/video-transcript#main ~/.claude/skills/video-transcript

For one project only, change the path to .claude/skills/video-transcript.

Claude (web or desktop app)
  1. On this page open ⋯ → Download .md.
  2. Save it as SKILL.md in a folder, zip the folder, then Customize → Skills → + → Create skill → Upload a skill.
  3. Pick the file and Save. Claude shows the name and description and runs a security scan.
  4. Check the skill is switched on.
  5. Start a new chat and describe your job in plain words. The AI follows the skill from there.
ChatGPT or another app
  1. ChatGPT: make a Project and paste it into Instructions.
  2. Neither? Paste it at the top of a new chat — it works for that chat.
Not working?
  • Check which app you pasted it into — the steps above name the right one.
  • Some skills need the paid tier of Claude or ChatGPT.
Step-by-step guide with screenshots · Ask in the forum

Paste into Claude, ChatGPT or Cursor.

Source of Video transcript

Show the full text103 lines
namedescriptionversionuser-invocablecompatibilityrequired_environment_variablesmetadata
video-transcriptUse when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text, or extract information from video content. Also use when a user shares a video URL without explanation and wants to know what it says. Not for uploads or account management.1.5.1trueRequires internet access to reach transcriptapi.com. No additional runtimes or dependencies needed. - name: TRANSCRIPT_API_KEY prompt: Your TranscriptAPI key (starts with sk_) help: Free account at https://transcriptapi.com — 100 credits, no card required. Or let the agent create one for you. required_for: all API requests{"openclaw":{"emoji":"▶️","requires":{"env":["TRANSCRIPT_API_KEY"]},"primaryEnv":"TRANSCRIPT_API_KEY","homepage":"https://transcriptapi.com"},"hermes":{"tags":["youtube","transcripts","video","captions","text-extraction","summarization"],"category":"media"}}

Video Transcript

Extract transcripts from videos via TranscriptAPI.com.

Setup

If $TRANSCRIPT_API_KEY is not set, read references/auth-setup.md and follow the instructions there to get and store the key.

Required Headers

Every request needs two headers:

  • Authorization: Bearer $TRANSCRIPT_API_KEY
  • User-Agent: your agent's name and version if known (e.g. HermesAgent/0.11.0, ClaudeCode/1.0). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request.

GET /api/v2/youtube/transcript

GET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_URL&format=text&include_timestamp=true&send_metadata=true
Authorization: Bearer $TRANSCRIPT_API_KEY
User-Agent: YourAgent/1.0
Param Required Default Values
video_url yes — YouTube URL or 11-char video ID
format no json json (structured), text (readable)
include_timestamp no true true, false
send_metadata no false true, false

Accepted URL formats:

  • https://www.youtube.com/watch?v=VIDEO_ID
  • https://youtu.be/VIDEO_ID
  • https://youtube.com/shorts/VIDEO_ID
  • Bare video ID: dQw4w9WgXcQ

Response (format=text&send_metadata=true):

{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": "[00:00:18] We're no strangers to love\n[00:00:21] You know the rules...",
  "metadata": {
    "title": "Rick Astley - Never Gonna Give You Up",
    "author_name": "Rick Astley",
    "author_url": "https://www.youtube.com/@RickAstley",
    "thumbnail_url": "https://i.ytimg.com/vi/dQw4w9WgXcQ/maxresdefault.jpg"
  }
}

Response (format=json):

{
  "video_id": "dQw4w9WgXcQ",
  "language": "en",
  "transcript": [
    { "text": "We're no strangers to love", "start": 18.0, "duration": 3.5 },
    { "text": "You know the rules and so do I", "start": 21.5, "duration": 2.8 }
  ]
}

Tips

  • Summarize long transcripts into key points first, offer full text on request.
  • Use format=json when you need precise timestamps for quoting specific moments.
  • Use send_metadata=true to get video title and channel for context.
  • Works with YouTube Shorts too.

Errors

Code Meaning Action
401 Bad API key Check key or re-setup
402 No credits Top up at transcriptapi.com/billing
403/1010 Cloudflare block Add or fix User-Agent header
404 No transcript Video may not have captions enabled
408 Timeout Retry once after 2s

1 credit per successful request. Errors don't consume credits. Free tier: 100 credits, 300 req/min.

Copy-paste examples

Every request in this file as a ready-to-run one-liner: references/curl-examples.md

1---
2name: video-transcript
3description: "Use when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text, or extract information from video content. Also use when a user shares a video URL without explanation and wants to know what it says. Not for uploads or account management."
4version: "1.5.1"
5user-invocable: true
6compatibility: Requires internet access to reach transcriptapi.com. No additional runtimes or dependencies needed.
7required_environment_variables:
8 - name: TRANSCRIPT_API_KEY
9 prompt: Your TranscriptAPI key (starts with sk_)
10 help: Free account at https://transcriptapi.com — 100 credits, no card required. Or let the agent create one for you.
11 required_for: all API requests
12metadata: {"openclaw":{"emoji":"▶️","requires":{"env":["TRANSCRIPT_API_KEY"]},"primaryEnv":"TRANSCRIPT_API_KEY","homepage":"https://transcriptapi.com"},"hermes":{"tags":["youtube","transcripts","video","captions","text-extraction","summarization"],"category":"media"}}
13---
14 
15# Video Transcript
16 
17Extract transcripts from videos via [TranscriptAPI.com](https://transcriptapi.com).
18 
19## Setup
20 
21If `$TRANSCRIPT_API_KEY` is not set, read [references/auth-setup.md](references/auth-setup.md) and follow the instructions there to get and store the key.
22 
23## Required Headers
24 
25Every request needs two headers:
26 
27- **Authorization:** `Bearer $TRANSCRIPT_API_KEY`
28- **User-Agent:** your agent's name and version if known (e.g. `HermesAgent/0.11.0`, `ClaudeCode/1.0`). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request.
29 
30## GET /api/v2/youtube/transcript
31 
32```http
33GET https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_URL&format=text&include_timestamp=true&send_metadata=true
34Authorization: Bearer $TRANSCRIPT_API_KEY
35User-Agent: YourAgent/1.0
36```
37 
38| Param | Required | Default | Values |
39| ------------------- | -------- | ------- | -------------------------------------- |
40| `video_url` | yes | — | YouTube URL or 11-char video ID |
41| `format` | no | `json` | `json` (structured), `text` (readable) |
42| `include_timestamp` | no | `true` | `true`, `false` |
43| `send_metadata` | no | `false` | `true`, `false` |
44 
45Accepted URL formats:
46 
47- `https://www.youtube.com/watch?v=VIDEO_ID`
48- `https://youtu.be/VIDEO_ID`
49- `https://youtube.com/shorts/VIDEO_ID`
50- Bare video ID: `dQw4w9WgXcQ`
51 
52**Response** (`format=text&send_metadata=true`):
53 
54```json
55{
56 "video_id": "dQw4w9WgXcQ",
57 "language": "en",
58 "transcript": "[00:00:18] We're no strangers to love\n[00:00:21] You know the rules...",
59 "metadata": {
60 "title": "Rick Astley - Never Gonna Give You Up",
61 "author_name": "Rick Astley",
62 "author_url": "https://www.youtube.com/@RickAstley",
63 "thumbnail_url": "https://i.ytimg.com/vi/dQw4w9WgXcQ/maxresdefault.jpg"
64 }
65}
66```
67 
68**Response** (`format=json`):
69 
70```json
71{
72 "video_id": "dQw4w9WgXcQ",
73 "language": "en",
74 "transcript": [
75 { "text": "We're no strangers to love", "start": 18.0, "duration": 3.5 },
76 { "text": "You know the rules and so do I", "start": 21.5, "duration": 2.8 }
77 ]
78}
79```
80 
81## Tips
82 
83- Summarize long transcripts into key points first, offer full text on request.
84- Use `format=json` when you need precise timestamps for quoting specific moments.
85- Use `send_metadata=true` to get video title and channel for context.
86- Works with YouTube Shorts too.
87 
88## Errors
89 
90| Code | Meaning | Action |
91| -------- | ---------------- | ---------------------------------------------- |
92| 401 | Bad API key | Check key or re-setup |
93| 402 | No credits | Top up at transcriptapi.com/billing |
94| 403/1010 | Cloudflare block | Add or fix User-Agent header |
95| 404 | No transcript | Video may not have captions enabled |
96| 408 | Timeout | Retry once after 2s |
97 
981 credit per successful request. Errors don't consume credits. Free tier: 100 credits, 300 req/min.
99 
100## Copy-paste examples
101 
102Every request in this file as a ready-to-run one-liner: [references/curl-examples.md](references/curl-examples.md)
103 

Discussion

Alternatives

Also in Captions & subsSee all 320 in Content creator →