# YouTube Transcript Fetcher

> YouTube Transcript Fetcher is a paid API for AI agents from api.agent-data.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-11-14).

Fetches the full transcript (manual or auto-generated subtitles) of a YouTube video as plain text, with optional timestamps, plus the video title and channel name.

## Facts

- Endpoint: GET https://api.agent-data.workers.dev/api/v1/youtube/transcript?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/youtube-transcript-fetcher-992697ea
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_XM6ern1FDXVz2GzDa2HBp

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 youtube-transcript-fetcher-992697ea
```

Example prompt: Can you grab the full transcript of this YouTube video — https://www.youtube.com/watch?v=jNQXAC9IVRw — in English, with timestamps, so I can summarize what was said?

## When to prefer this

Use this endpoint when you need the spoken content of a YouTube video as text — for summarization, quoting, translation, or analysis — without needing to download or process audio. Prefer this over audio transcription services when the video already has subtitles (manual or auto), as it is faster and cheaper. Best for agents that need to process video content programmatically without watching it.

## Known failure modes

- Video has no subtitles or captions available — returns an error indicating no transcript found
- Invalid or non-existent video URL/ID — returns a not found error
- Requested language not available for the video — may fall back to default or return an error
- Private or age-restricted videos may be inaccessible
- Network timeout when YouTube is slow to respond

## How this service works

Transcript of a YouTube video (manual or auto subtitles) as plain text, optional timestamps, with title and channel. Use to summarize or quote videos.

## Output

Returns a JSON object containing the full transcript as plain text, the video title, channel name, detected language code, video ID, total duration in seconds, and a boolean indicating whether the captions were auto-generated or manually created. Optionally includes per-segment timestamps if requested.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Video URL or id"
      },
      "lang": {
       "type": "string",
       "description": "Preferred languages, e.g. en,ru"
      },
      "timestamps": {
       "type": "boolean"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "All right, so here we are in front of the elephants...",
  "title": "Me at the zoo",
  "channel": "jawed",
  "language": "en",
  "video_id": "jNQXAC9IVRw",
  "duration_sec": 19,
  "is_generated": false
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/youtube-transcript-fetcher-992697ea/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agent-data.workers.dev](https://www.zero.xyz/host/api.agent-data.workers.dev/llms.txt)
