# agdata YouTube Transcript API

> agdata YouTube Transcript API is a paid API for AI agents from agdata.shveik.dev, paid per call via x402, $0.032/call, status unknown (last checked 2026-10-10).

Fetches the full transcript of a YouTube video in your choice of format and language, returning structured metadata alongside the transcript segments.

## Facts

- Endpoint: POST https://agdata.shveik.dev/mpp/youtube-transcript?utm_source=zero.xyz
- Price: $0.032/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agdata-youtube-transcript-api-e22142f3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HvEfcxgfOh5hszmmzHfMB

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agdata-youtube-transcript-api-e22142f3 -d '<json body>'
```

Example prompt: Can you grab the full transcript of this YouTube video — https://www.youtube.com/watch?v=dQw4w9WgXcQ — in English and give it to me as plain text?

## When to prefer this

Choose this endpoint when you need structured, timed transcript data from a YouTube video without setting up a YouTube Data API key or managing proxies. It is especially useful for agents that need to summarize, translate, index, or analyze video content at scale, paying per call with no subscription. Supports multiple output formats (JSON, text, SRT, VTT) and multiple languages in one call.

## Known failure modes

- Video not found or invalid URL returns an error response
- No transcript available for the requested language — try 'any' for the first available language
- Video has disabled captions entirely — no transcript can be returned
- Private or age-restricted videos may be inaccessible
- Insufficient USDC balance for the $0.028 per-call fee causes payment failure
- Transcript truncated if video is very long (truncated field set to true)

## How this service works

Unblocking and fresh web data for AI agents. Social, maps, search, news, jobs and reviews as structured data, and unblocking for any other page, as Markdown or HTML. Pay per call in stablecoins over x402 or MPP, with no API key, no account and no proxy setup. (x402 on Base and Polygon (plus Solana on most routes) or MPP on Base)

## Output

Returns a JSON object containing the video's title, channel name, channel URL, view count, published date, duration in seconds, language of the transcript, subtitle type (auto-generated or user-generated), whether the transcript was truncated, the number of segments, a list of available languages, and an array of transcript segments. The transcript array contains timed caption entries.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "lang": {
   "enum": [
    "any",
    "en",
    "de",
    "es",
    "fr",
    "it",
    "ja",
    "ko",
    "nl",
    "pt",
    "ru"
   ],
   "type": "string"
  },
  "video": {
   "type": "string",
   "maxLength": 2048
  },
  "format": {
   "enum": [
    "json",
    "text",
    "srt",
    "vtt"
   ],
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://…",
  "title": "Rick Ast…",
  "format": "json",
  "videoId": "dQw4w9Wg…",
  "language": "en",
  "truncated": false,
  "viewCount": 1822672170,
  "channelUrl": "https://…",
  "transcript": [],
  "channelName": "Rick Ast…",
  "publishedAt": "2009-10-…",
  "segmentCount": 61,
  "subtitleType": "user_gen…",
  "durationSeconds": 213,
  "availableLanguages": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agdata-youtube-transcript-api-e22142f3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agdata.shveik.dev](https://www.zero.xyz/host/agdata.shveik.dev/llms.txt)