YouTube Transcripts
Transcripts of YouTube videos with timestamps, chapters, language choice and video metadata.
- LIVE
- 1 credit per transcript
- Failed results are free
Try it live
Press “Run it live” and the real result shows up here, exactly what your agent gets back.
Example output
What your agent gets back.
Me at the zoo
- Channel
- jawed
- Word count
- 33
- Duration
- 0:21
- Language matched
- Yes
Also hier sind wir vor den Elefanten. Das Coole an den Typen ist dass sie sehr, sehr, sehr, lange Rüssel haben. Und das ist cool. Ansonsten gibt es nicht wirklich viel zu sagen.
View raw JSON
{
"videoId": "jNQXAC9IVRw",
"url": "https://www.youtube.com/watch?v=jNQXAC9IVRw",
"title": "Me at the zoo",
"channelName": "jawed",
"channelUrl": "https://www.youtube.com/@jawed",
"durationSeconds": 21,
"language": {
"code": "de",
"name": "de",
"isAutoGenerated": false
},
"languageMatched": true,
"text": "Also hier sind wir vor den Elefanten. Das Coole an den Typen ist dass sie sehr, sehr, sehr, lange Rüssel haben. Und das ist cool. Ansonsten gibt es nicht wirklich viel zu sagen.",
"wordCount": 33,
"segments": [
{
"start": 0,
"end": 5.067,
"text": "Also hier sind wir vor den Elefanten."
},
{
"start": 5,
"end": 12.467,
"text": "Das Coole an den Typen ist dass sie sehr, sehr, sehr, lange Rüssel haben."
},
{
"start": 12,
"end": 21,
"text": "Und das ist cool. Ansonsten gibt es nicht wirklich viel zu sagen."
}
],
"chapters": [
{
"title": "Chapter 1: Intro",
"start": 0
},
{
"title": "Chapter 2: Das coole Ding",
"start": 5
},
{
"title": "Chapter 3: Ende",
"start": 17
}
],
"scrapedAt": "2026-10-20T09:29:05.506Z"
}Use it from your agent
One key, any agent.
- 01Get your keySign up with your email. You start with 2,000 free credits.
- 02Call the toolSend the input as JSON. The answer comes back with the results and the credits used.
- 03Or plug in MCPAdd one block to Claude, Cursor or any MCP client and your agent finds “youtube-transcripts” by itself.
curl -X POST https://pullwire.dev/api/v1/tools/youtube-transcripts/runs \
-H "x-api-key: $PULLWIRE_API_KEY" \
-H "content-type: application/json" \
-d '{"videos":["https://www.youtube.com/watch?v=jNQXAC9IVRw"],"maxResults":3}'Waits up to 25 s for the results. Add ?async=1 to get a run id back right away.
Options
Everything you can set.
| Field | What it does | Type | Default |
|---|---|---|---|
| Videosrequiredvideos | YouTube video URLs (watch, youtu.be, shorts, embed, live) or 11-character video IDs. | list of text | – |
| Preferred languageslanguages | Language codes in order of preference, e.g. de, en, pt-BR. Empty: the original transcript. If none is available, the default transcript is returned with languageMatched = false. | list of text | – |
| Prefer human-made captionspreferManual | Use uploaded captions over auto-generated ones when both exist for a language. | yes / no | yes |
| Include timed segmentsincludeSegments | Adds the transcript split into segments with start and end time in seconds. | yes / no | yes |
| Include video metadataincludeMetadata | Adds title and channel. Views, duration, publish date and the language list are added when YouTube provides them. | yes / no | yes |
| Max resultsmaxResults | Stop after this many transcripts. Empty: all videos. | number | – |
Pricing
Pay for results, not requests.
1credit per transcript
One transcript successfully extracted. Videos without a transcript are not charged.
- Failed results are free
- One balance for every tool
- 2,000 free credits when you sign up
Use cases
What people do with it.
More tools
Same key, more sources.
[1706.03762] Attention Is All You Need
- Status code
- 200
- Format
- markdown
- Language
- en
- Content type
- text/html
Abstract page for arXiv paper 1706.03762: Attention Is All You Need
Web Scraper
LIVETurn any public web page into clean, LLM-ready Markdown, raw HTML or JSON fields picked with CSS selectors. Optional JavaScript rendering, screenshots and an automatic residential-proxy fallback when a site blocks.
Nike
- Start date
- Jun 20, 2025
- Platforms
- Facebook, Instagram
- Active
- Yes
- End date
- Aug 28, 2025
Get the gear that goes hard on and off the field.
Facebook Ads Library Scraper
LIVESearch the Facebook Ad Library by keyword or advertiser Page ID: ad text, images, videos, CTA, run dates and platforms. No login, no browser.
Software Engineer I, Fullstack (Search)
- Company
- Affirm
- Location
- Salt Lake City, UT
- Posted
- 4 days ago
- Apply badge
- Actively Hiring
At Affirm, we exist for the moments that matter—giving people a clear, predictable way to pay over time, with no hidden fees, no surprises, and no tradeoffs on what matters most. Search has become the default way consumers discover where to shop, compare options, and decide what…
LinkedIn Jobs Scraper
LIVESearch LinkedIn job postings by keyword, location, date posted, work type, experience level and job type: title, company, location, full description, seniority, employment type and applicant count. No login, no browser.