YouTube Transcript & AI Summary Extractor

Turn any YouTube video, Short, channel, or playlist into structured, timestamped transcript text and AI-generated summaries — one clean dataset row per video.

What it does

• Resolves watch URLs, Shorts URLs, and bare video IDs.
• Timestamped transcripts — every segment carries a startTime (HH:MM:SS) and text.
• Multi-language — request a preferred language; falls back to auto-generated captions and reports language + isAutoGenerated.
• Export formats — choose json (default), srt, vtt, csv, or txt. SRT/VTT/CSV/TXT are generated in spec-correct format and attached to the row.
• Channel / playlist input — pass a channel page (@handle, /channel/...), or a playlist (?list=) URL; it auto-expands to the video list (capped by maxVideos).
• Proxy-aware + anti-block — detects YouTube IP-bans / 429-style blocks, rotates the proxy, and retries with exponential backoff (maxRetries).
• AI summary — optional bullet summary with selectable summaryLength (short/medium/long) and an independent summaryLanguage.
• Chapter segmentation (stretch) — optional AI topic-based chapters with title + start/end times.
• One dataset row per processed video.

Inputs

Field	Type	Default	Notes
startUrls (required)	array[string]	—	Video, Short, video-ID, channel, or playlist URLs. Channels/playlists expand automatically.
mode	enum	auto	auto tries direct then browser title; direct; browser.
maxVideos	integer	1	Max videos to process across all URLs + expansions (1–200).
preferredLanguage	string	en	Preferred transcript language code. Auto-generated captions used as fallback.
languages (legacy)	array[string]	["en","en-US","en-GB","a.en"]	Kept for backward compatibility; used only when preferredLanguage is omitted.
languagesExtended	array[string]	= preferred	Extra fallback codes.
includeRawTranscript	boolean	true	Include timestamped segments + full text.
includeSummary	boolean	false	Generate an AI summary. Requires OPENAI_API_KEY + OPENAI_BASE_URL.
summaryModel	string	gpt-4o-mini	Model for summary + chapters.
summaryLength	enum	medium	short (3-5), medium (5-8), long (8-12) bullets.
summaryLanguage	string	""	Language for the summary, independent of transcript language.
enableChapters	boolean	false	AI topic-based chapter segmentation (needs includeSummary).
outputFormat	enum	json	json, srt, vtt, csv, txt.
maxRetries	integer	3	Exponential-backoff retries on YouTube blocks/IP-bans (proxy rotates each retry).
maxTranscriptLength	integer	15000	Truncate transcript after this many characters.
proxyConfiguration	object	{ "useApifyProxy": true, "apifyProxyGroups": ["RESIDENTIAL"] }	Defaults to Apify RESIDENTIAL proxies. YouTube blocks datacenter IPs (the Apify run node and the BUYPROXIES group are both blocked), so residential proxies are required for reliable channel/playlist/bulk runs. Override with your own proxyUrl or a different group if you have proxy access.

Backward compatibility: with no new inputs set, behavior matches the previous version (single video, en transcript, json output, optional summary). The old languages input is still honored when preferredLanguage is omitted.

Example 1 — single video, timestamped transcript (default)

{
  "startUrls": ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"],
  "mode": "auto",
  "maxVideos": 1,
  "preferredLanguage": "en",
  "includeRawTranscript": true,
  "includeSummary": false,
  "outputFormat": "json"
}

Example 2 — SRT export + AI summary (Spanish)

{
  "startUrls": ["https://www.youtube.com/watch?v=abc123"],
  "outputFormat": "srt",
  "includeSummary": true,
  "summaryLength": "short",
  "summaryLanguage": "es",
  "maxTranscriptLength": 8000
}

Example 3 — whole channel, auto-language fallback, chapters

{
  "startUrls": ["https://www.youtube.com/@someChannel"],
  "maxVideos": 20,
  "preferredLanguage": "en",
  "includeSummary": true,
  "enableChapters": true,
  "summaryLength": "long"
}

Example 4 — playlist with proxy + anti-block retries

{
  "startUrls": ["https://www.youtube.com/playlist?list=PLxxxxxxxxxxxx"],
  "maxVideos": 50,
  "proxyConfiguration": { "useApifyProxy": true, "groups": ["BUYPROXIES94952"] },
  "maxRetries": 5,
  "outputFormat": "vtt"
}

Output schema (per video row)

Field	Type	Description
videoUrl	string	Source URL.
videoId	string	11-char YouTube video ID.
title	string	Video title (when available).
language	string	Resolved transcript language code.
isAutoGenerated	boolean	true when auto-generated captions were used.
transcriptSegments	array	[{ startTime: "HH:MM:SS", startSeconds, text }].
fullText	string	Full concatenated transcript (when includeRawTranscript).
summary	object	{ model, summary, error? } when includeSummary.
exportFormat	string	The chosen export format.
srt / vtt / csv / txt	string	Present only for the matching outputFormat.
chapters	array	[{ title, startTime, endTime }] when enableChapters.
warnings	array[string]	Non-fatal issues (e.g. transcript-empty-or-quota-limited).

Example output row (outputFormat: json)

{
  "videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
  "videoId": "dQw4w9WgXcQ",
  "title": "Rick Astley - Never Gonna Give You Up",
  "language": "en",
  "isAutoGenerated": false,
  "transcriptSegments": [
    { "startTime": "00:00:01", "startSeconds": 1.36, "text": "[♪♪♪]" },
    { "startTime": "00:00:18", "startSeconds": 18.64, "text": "♪ We're no strangers to love ♪" }
  ],
  "fullText": "[♪♪♪] ♪ We're no strangers to love ♪ ...",
  "summary": { "model": "gpt-4o-mini", "summary": "- Iconic 80s song\n- ..." },
  "exportFormat": "json",
  "chapters": [
    { "title": "Intro", "startTime": "00:00:00", "endTime": "00:01:00" }
  ],
  "warnings": []
}

AI summary / chapters — setup

Set these environment variables on the Actor (Apify Console → Actor → Environment): OPENAI_API_KEY and OPENAI_BASE_URL (any OpenAI-compatible endpoint, e.g. OpenRouter). When unset, includeSummary / enableChapters produce an empty summary with an error field rather than failing the run.

Run costs

Pay-per-event pricing:

• per dataset row written
• per run

Actual cost depends on run + row counts. Check the Apify Console after a run.

Notes / limitations

• Proxy / IP bans: YouTube blocks datacenter IPs (including the Apify run node and the BUYPROXIES group). The actor therefore defaults to Apify RESIDENTIAL proxies, which reliably bypass the block. Without a working residential proxy, channel/playlist/bulk runs will fail with "YouTube is blocking requests from your IP." If you have your own residential proxy, set proxyConfiguration.proxyUrl.
• Channel/playlist expansion is best-effort and capped by maxVideos.
• Not all videos have captions; unavailable transcripts surface a warnings entry.
• isAutoGenerated reflects whether the served transcript was auto-generated.