YouTube Video Summarizer – AI + Transcript

sfoln/youtube-transcript-summary · AI, Videos, Automation On request

Summarize YouTube videos with AI from their captions: a summary in your style, about 8 timestamped chapters, key takeaways, quotes and topics, plus the transcript. $5 per 1,000 transcripts + $8 per 1,000 AI summaries; videos without captions are free.

Request access Run it$5 / 1,000 youtube transcript, more below

About

What it does

YouTube Video Summarizer – AI + Transcript turns YouTube links into a ready-to-read summary of each video: a summary in the style you choose (brief, detailed or bullet points), ≈8 timestamped chapters with titles and one-line summaries, key takeaways, up to five verbatim quotes with timestamps, and topic labels. Summaries are generated from the video's own captions, in the language you ask for. Built for researchers, marketers, students, newsletter writers and AI agents that need the gist of long videos without watching them.

Price

Price per delivered record

Event	Price	Per 1,000	Charged for
YouTube transcript `youtube-transcript-retrieved`	$0.005	$5 / 1,000	Charged once per video for which a caption transcript was returned. Videos without captions, missing or blocked videos and failed requests are not charged.
Video summary `youtube-summary`	$0.008	$8 / 1,000	Charged once per video for which the AI summary (summary, chapters, takeaways, quotes, topics) was generated.

Apify free plan: up to 10 items per run. Paid plans have no per-run cap; set maxTotalChargeUsd to cap spend.

Run

Call it from code, an agent or the Console

This API is private on Apify for now. Email us and we will publish it for you, usually within two working days. The calls below work once it is public. contact@sfoln.com

curl · synchronous run, rows in the response

curl -X POST "https://api.apify.com/v2/actors/sfoln~youtube-transcript-summary/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"videos":["https://www.youtube.com/watch?v=jNQXAC9IVRw"]}'

mcp.json · hosted Apify MCP server

{
  "mcpServers": {
    "apify": {
      "type": "http",
      "url": "https://mcp.apify.com?tools=sfoln/youtube-transcript-summary"
    }
  }
}

asynchronous run · for large batches

POST https://api.apify.com/v2/actors/sfoln~youtube-transcript-summary/runs?maxTotalChargeUsd=1
GET  https://api.apify.com/v2/actor-runs/{runId}            # until status is SUCCEEDED
GET  https://api.apify.com/v2/datasets/{defaultDatasetId}/items?format=json

Authenticate with an Apify API token. MCP clients can instead sign in with OAuth when prompted. Example prompt for an agent: Summarize https://www.youtube.com/watch?v=jNQXAC9IVRw in bullet points with timestamped chapters and the key takeaways.

Input

Input fields

List YouTube videos. Each video produces one dataset record with its transcript-based summary.

Field	Type	Default	Meaning
`videos` *	`array`	required	Videos YouTube video / Shorts URLs or 11-character video IDs, one per line. Accounts on the Apify free plan can process up to 10 videos per run.
`style`	`string`	`"brief"`	Summary style brief: one short paragraph and 3–5 takeaways; detailed: 200–300 words and 5–10 takeaways; bullet: summary as 5–8 bullet points. One of `"brief"`, `"detailed"`, `"bullet"`.
`summaryLanguage`	`string`	—	Summary language Language for the summary, chapters and takeaways, e.g. "English" or "es". Empty = the transcript's language.
`transcriptLanguage`	`string`	—	Caption language Caption track to read, e.g. "en". Empty = the video's original (or auto-generated) track.
`includeTranscript`	`boolean`	`false`	Include transcript text Also return the full transcript as plain text.
`summarize`	`boolean`	`true`	Summarize with AI Turn off to return only transcript statistics (and the transcript with includeTranscript) without the AI summary.
`maxVideos`	`integer`	`500`	Max videos Safety cap on how many videos are processed in this run. Range 1–5000.
`concurrency`	`integer`	`4`	Concurrency Videos processed in parallel (1–8). Range 1–8.

Example input

{
  "videos": [
    "https://www.youtube.com/watch?v=jNQXAC9IVRw"
  ]
}

Output

One record per input item

Records land in the run's dataset; a synchronous call returns them directly. Each has a status (ok is charged; everything else is free) and a charged flag. The run's OUTPUT record totals items and charges.

Field	Type	Meaning
`input`	`string \| object`	Input The input item this record corresponds to.
`status`	`string`	Status ok \| not_found \| error \| skipped_invalid \| skipped_budget \| skipped_free_plan
`charged`	`boolean`	Charged Whether the record's main event was charged.
`chargedEvent`	`string \| null`	Charged event Event charged by the runner for this record, if any.
`source`	`string`	Source Upstream data source.
`fetchedAt`	`string`	Fetched at ISO timestamp.
`warnings`	`array \| null`	Warnings Non-fatal problems (pages not reachable, truncation, budget limits).
`error`	`object \| null`	Error { code, message, provider?, status? } when status is not ok.
`videoId`	`string \| null`	Video ID 11-character YouTube video ID.
`url`	`string \| null`	URL Canonical watch URL.
`language`	`string \| null`	Caption language Caption track language as named by YouTube (e.g. "English").
`transcriptWordCount`	`integer \| null`	Transcript words Words in the transcript.
`segmentCount`	`integer \| null`	Caption segments Number of timed caption segments.
`durationSecs`	`number \| null`	Duration (s, approx.) End of the last caption segment in seconds.
`style`	`string \| null`	Style brief \| detailed \| bullet.
`summary`	`string \| null`	Summary AI summary in the requested style.
`chapters`	`array \| null`	Chapters ≈8 time-based chapters: [{ startSecs, endSecs, title, summary }]; times come from the captions.
`keyTakeaways`	`array \| null`	Key takeaways Key takeaways (3–8 depending on style).
`quotes`	`array \| null`	Quotes Up to 5 verbatim quotes: [{ text, startSecs }].
`topics`	`array \| null`	Topics Up to 10 topic labels.
`summaryCharged`	`boolean \| null`	Summary charged true when youtube-summary was charged for this video.
`transcriptTruncated`	`boolean \| null`	Transcript truncated true when the transcript exceeded ≈10,000 tokens and each chapter was summarized from its opening part.
`tokensUsed`	`object \| null`	Tokens used { input, output } Mistral tokens for the summary.
`transcriptText`	`string \| null`	Transcript text Full transcript (only with includeTranscript).
`hasCaptions`	`boolean \| null`	Has captions false on not_found records without captions.

Example record

{
  "input": "https://youtu.be/bjVIDXPP7Uk",
  "videoId": "bjVIDXPP7Uk",
  "url": "https://www.youtube.com/watch?v=bjVIDXPP7Uk",
  "language": "English",
  "transcriptWordCount": 1840,
  "segmentCount": 214,
  "durationSecs": 412,
  "style": "brief",
  "summary": "The creator revisits backyard bike trails built two years ago, rebuilds the jumps and explains ...",
  "chapters": [
    {
      "startSecs": 0,
      "endSecs": 52,
      "title": "Back at the farm",
      "summary": "Introduction to the trails and the plan for the day."
    },
    {
      "startSecs": 52,
      "endSecs": 103,
      "title": "Rebuilding the first jump",
      "summary": "Digging and shaping the take-off."
    }
  ],
  "keyTakeaways": [
    "Pack the dirt in thin layers",
    "Test jumps at low speed first"
  ],
  "quotes": [
    {
      "text": "the secret is patience and practice",
      "startSecs": 90
    }
  ],
  "topics": [
    "mountain biking",
    "trail building"
  ],
  "summaryCharged": true,
  "transcriptTruncated": false,
  "tokensUsed": {
    "input": 3120,
    "output": 410
  },
  "status": "ok",
  "charged": true,
  "chargedEvent": "youtube-transcript-retrieved",
  "source": "scrapecreators+mistral",
  "fetchedAt": "2026-10-14T10:00:00.000Z"
}

Machine-readable

This page for agents

/actors/youtube-transcript-summary.json — this API as JSON
/actors/youtube-transcript-summary.md — this API as Markdown
/catalog.json — the whole catalogue