---
name: youtube-transcripts
description: "Transcripts of YouTube videos with timestamps, chapters, language choice and video metadata. Use when the user wants to know what a YouTube video says: summarize, quote, search, translate or take notes from one or more videos, or needs captions with timestamps or chapters. Accepts watch, youtu.be, shorts, embed and live links or plain 11-character video IDs. Calls the Pullwire API with the key in PULLWIRE_API_KEY; costs 1 credit per transcript."
metadata:
  openclaw:
    requires:
      env:
        - PULLWIRE_API_KEY
      bins:
        - curl
    primaryEnv: PULLWIRE_API_KEY
    homepage: https://pullwire.dev/tools/youtube-transcripts
---

# YouTube Transcripts

Transcripts of YouTube videos with timestamps, chapters, language choice and video metadata. The data comes from the Pullwire API: you send the input as JSON and get structured JSON back. Only public data.

## Setup (once)

The API key must be in the environment variable `PULLWIRE_API_KEY`. Keys start with `af_live_`. Check it without printing it:

```bash
test -n "$PULLWIRE_API_KEY" && echo "key is set" || echo "PULLWIRE_API_KEY is missing"
```

If it is missing, stop and tell the user: sign up at https://pullwire.dev/login (new accounts get 2,000 free credits), create a key at https://pullwire.dev/app/keys, then run `export PULLWIRE_API_KEY="af_live_..."` in the shell the agent uses. Never print the key, write it into a file or repeat it in the chat.

## Run it

```bash
curl -sS -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}'
```

The request waits up to 25 seconds and answers with `{"run": {...}, "results": [...]}`. Check `run.status` (`succeeded` or `failed`) and `run.error`: when it is set, the run stopped early and `results` is partial (everything in it was charged). `run.creditsUsed` is what the run cost. For big answers add `-o result.json` and read only the fields you need.

Good to know:

- Pass several videos in one run instead of one run per video.
- For a summary or quotes, set `includeSegments` to `false`: `text` already holds the whole transcript and the answer stays small.
- Set `languages` (for example `["en"]`) when the user wants a specific language. If that language is missing, you get the default transcript and `languageMatched` is `false`; say so.
- A video without any transcript returns no result and costs nothing.

## Input

The JSON body is the tool input. Fields:

| Field | Type | Required | Default | What it does |
| --- | --- | --- | --- | --- |
| `videos` | string[] | yes |  | Videos: YouTube video URLs (watch, youtu.be, shorts, embed, live) or 11-character video IDs. |
| `languages` | string[] | no | `[]` | Preferred languages: 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. |
| `preferManual` | boolean | no | `true` | Prefer human-made captions: Use uploaded captions over auto-generated ones when both exist for a language. |
| `includeSegments` | boolean | no | `true` | Include timed segments: Adds the transcript split into segments with start and end time in seconds. |
| `includeMetadata` | boolean | no | `true` | Include video metadata: Adds title and channel. Views, duration, publish date and the language list are added when YouTube provides them. |
| `maxResults` | integer | no |  | Max results: Stop after this many transcripts. Empty: all videos. |

Without `maxResults` a run returns at most 20 results; the maximum is 200 per run. Credits for `maxResults` results are reserved before the run starts and the unused part is given back, so ask for what you need.

## Output

Each item in `results` has these fields:

| Field | Type | Always there |
| --- | --- | --- |
| `videoId` | string | yes |
| `url` | string | yes |
| `title` | string | no |
| `channelName` | string | no |
| `channelUrl` | string | no |
| `channelId` | string | no |
| `durationSeconds` | number | no |
| `viewCount` | number | no |
| `publishDate` | string | no |
| `description` | string | no |
| `language` | object \| null | yes |
| `languageMatched` | boolean | yes |
| `availableLanguages` | object[] | no |
| `text` | string | yes |
| `wordCount` | integer | yes |
| `segments` | object[] | no |
| `chapters` | object[] | no |
| `scrapedAt` | string | yes |

## Cost

1 credit per transcript. One transcript successfully extracted. Videos without a transcript are not charged. Check the balance with:

```bash
curl -sS "https://pullwire.dev/api/v1/me" -H "x-api-key: $PULLWIRE_API_KEY"
```

The answer has `balance` in credits. Tell the user what a run cost when it was more than a few credits.

## Bigger jobs

Add `?async=1` to the run URL to start a background run (up to 50 seconds). It answers `202` with `run.id` right away. Poll every few seconds until `status` is `succeeded` or `failed`, then fetch the results:

```bash
curl -sS "https://pullwire.dev/api/v1/runs/$RUN_ID" -H "x-api-key: $PULLWIRE_API_KEY"
curl -sS "https://pullwire.dev/api/v1/runs/$RUN_ID/results" -H "x-api-key: $PULLWIRE_API_KEY"
```

Add `?format=csv` to the results URL when the user wants a spreadsheet.

## Errors

Errors answer `{"error": {"code": "...", "message": "..."}}`.

| Status | Code | What to do |
| --- | --- | --- |
| 400 | `INVALID_INPUT` | The message names the field. Fix the input and retry; nothing was charged. |
| 401 | `UNAUTHORIZED` | The key is missing, wrong or revoked. Ask the user to set a valid key in `PULLWIRE_API_KEY`. |
| 402 | `INSUFFICIENT_CREDITS` | The balance cannot cover the reservation. Lower `maxResults` or tell the user the balance is too low. |
| 404 | `NOT_FOUND` | Unknown tool or run ID. |
| 429 | `RATE_LIMITED` | Used up its burst of 120 requests and its 60 per minute. Wait, then retry. |
| 500 | `INTERNAL_ERROR` | Retry later. If the body has `runId`, fetch the partial results with `GET /runs/{runId}/results`. |
| 503 | `TOOL_UNAVAILABLE` | Our latest automatic checks against this site failed, so its runs are paused. Nothing was reserved or charged. Tell the user and try again later. |
| 503 | `SERVICE_UNAVAILABLE` | Retry later. |

Docs: https://pullwire.dev/docs · Tool page: https://pullwire.dev/tools/youtube-transcripts