YouTube AI Transcript Extractor — Video to Text, SRT & VTT 🚀

🎬 Turn ANY YouTube video into a clean transcript + 40+ data fields — long-form, Shorts & live replays

Built for content creators, SEO pros, researchers, and AI/RAG pipelines that need YouTube video-to-text at scale

---

📋 Overview

Paste a YouTube link, get the words. The YouTube AI Transcript Extractor converts any YouTube video into a clean, timestamped transcript — plus 40+ metadata fields — in one run. Single video or thousands, no login required.

What you get:

• ✅ Every YouTube video, not just Shorts: long-form, Shorts, live replays, watch?v=, youtu.be, embeds — even a bare video ID
• ⚡ Instant native captions: reads a video's own captions in seconds — and when a video has none, falls back to AI audio transcription so you still get a transcript
• 🎯 Ready-to-use formats: full plain text, timestamped segments, plus SRT & VTT subtitle files
• 💰 Fair, cost-aligned pricing: $0.01 per captioned video; per-minute AI transcription only when a video has no captions — start FREE, no credit card
• 💎 40+ metadata fields in the same run: views, likes, comments, channel analytics, keywords, thumbnails, categories, related videos
• ✨ Bulk-ready: drop in a list or upload a CSV/TXT of URLs and transcribe them all

✨ Features

• 🎬 Any URL format: watch?v=, youtu.be, /shorts/, /embed/, /live/, or a raw 11-character video ID
• 📝 Four transcript outputs: full text, timestamped segments, SRT, and VTT — copy-paste or drop straight into an editor
• 🌍 Auto language detection: captures the video's spoken language automatically
• 📊 40+ metadata fields: engagement metrics with calculated ratios, channel stats, keywords, thumbnails, category, publish dates
• 🔗 Related videos: discover connected content and trends in the same run
• 📁 Bulk + file upload: paste many URLs or upload a .csv/.txt — URL column auto-detected
• 🤖 AI/RAG friendly: clean structured JSON that drops straight into LLMs and vector stores
• 🆓 Free to try: full feature access on the free tier — no setup, no keys

🎞️ Quick Start

Paste a YouTube URL, click Start, and get your transcript + metadata seconds later. Use the bulk field for many videos at once.

curl -X POST "https://api.apify.com/v2/acts/sian.agency~youtube-ai-transcript-extractor/runs?token=YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"}'

🚀 Getting Started (3 Simple Steps)

Step 1: Add your video(s)

Paste a single YouTube URL in Video URL, or add many in the bulk URLs field (or upload a CSV/TXT).

Step 2: Click Start

The actor validates each URL, then extracts the transcript and metadata.

Step 3: Download your data

Export transcripts + metadata as JSON, CSV, or Excel — or grab the ready-made SRT/VTT caption files.

That's it! In under a minute, you'll have:

• A clean, timestamped transcript of every video
• SRT + VTT subtitle files ready for editing
• 40+ metadata fields per video for analysis

📥 Input Configuration

Field	Type	Required	Description
videoUrl	string	No	A single YouTube video URL (watch, youtu.be, Shorts, embed, live) or bare video ID
urls	array	No	Multiple YouTube URLs for bulk processing; supports CSV/TXT file upload
maxAiTranscriptionMinutes	integer	No	Cost cap, default 30. How long a caption-less video may be before AI audio transcription is used. 0 disables AI entirely. Captioned videos are unaffected — see Pricing.

Single video:

{ "videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" }

Bulk processing:

{
  "urls": [
    { "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" },
    { "url": "https://youtu.be/BoZuXYvGFu8" }
  ]
}

Free tier processes up to 5 URLs per run. Paid tier: unlimited URLs per run.

📤 Output

Each video is saved to the Apify dataset with 50 fields, including:

Field	Type	Description
fullTranscript	string	Complete plain-text transcript
segments	array	Timestamped segments (text, start, end, duration)
vtt	string	WebVTT subtitle file
srt	string	SRT subtitle file
totalWords	number	Word count of the transcript
title	string	Video title
channelTitle	string	Channel name
subscriberCount	number	Channel subscribers
viewCount	string	View count
likeCount	string	Like count
commentCount	number	Comment count
likesPerViewPercentage	string	Likes-to-views ratio
keywords	array	Video tags/keywords
category	string	Video category
publishDate	string	Publish date (ISO 8601)
relatedVideos	object	Connected/related videos

Example (trimmed):

{
  "videoId": "dQw4w9WgXcQ",
  "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
  "title": "Rick Astley - Never Gonna Give You Up (Official Video)",
  "channelTitle": "Rick Astley",
  "fullTranscript": "We're no strangers to love. You know the rules and so do I...",
  "totalWords": 291,
  "totalSegments": 52,
  "vtt": "WEBVTT\n\n1\n00:00:18.560 --> 00:00:22.399\n...",
  "srt": "1\n00:00:18,560 --> 00:00:22,399\n...",
  "viewCount": "1600000000",
  "likeCount": "18000000",
  "keywords": ["Rick Astley", "Never Gonna Give You Up"],
  "category": "Music",
  "publishDate": "2009-10-25"
}

💼 Use Cases & Examples

1. Content & SEO Research

Marketers and creators mining what actually drives views. Input: competitor or niche video URLs · Output: transcript + keywords + engagement · Use: find the hooks, topics, and phrasing behind top-performing videos.

2. AI, RAG & LLM Pipelines

Data teams turning video into machine-readable knowledge. Input: a channel's video URLs · Output: clean structured transcripts · Use: feed LLMs and vector databases to build summaries, search, and Q&A over video content.

3. Subtitles & Accessibility

Editors and publishers making video accessible. Input: any video URL · Output: SRT + VTT files · Use: caption videos, meet accessibility requirements, and translate from a clean base transcript.

4. Content Repurposing

Creators turning one video into ten assets. Input: a long-form upload · Output: full transcript + segments · Use: spin blog posts, newsletters, show notes, and social clips from a single video.

5. Market & Trend Analysis

Analysts tracking what's being said at scale. Input: trending or industry video URLs (bulk) · Output: transcripts + metadata · Use: monitor messaging, sentiment, and emerging topics across a niche.

6. Research & Journalism

Researchers and reporters quoting the record accurately. Input: interview, talk, or press-conference URLs · Output: timestamped transcript · Use: search, cite, and verify spoken content quickly.

🔗 Integration Examples

JavaScript / Node.js

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: 'YOUR_TOKEN' });

const run = await client.actor('sian.agency/youtube-ai-transcript-extractor').call({
  videoUrl: 'https://www.youtube.com/watch?v=dQw4w9WgXcQ'
});

const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].fullTranscript);

Python

from apify_client import ApifyClient
client = ApifyClient('YOUR_TOKEN')

run = client.actor('sian.agency/youtube-ai-transcript-extractor').call(
    run_input={'videoUrl': 'https://www.youtube.com/watch?v=dQw4w9WgXcQ'}
)

for item in client.dataset(run['defaultDatasetId']).iterate_items():
    print(item['fullTranscript'])

cURL

curl -X POST "https://api.apify.com/v2/acts/sian.agency~youtube-ai-transcript-extractor/runs?token=YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"}'

Automation Workflows (n8n / Zapier / Make)

1. Trigger: schedule or webhook
2. HTTP Request: call the actor API
3. Process: handle the JSON transcript + metadata
4. Action: save, notify, translate, or summarize

📊 Performance & Pricing

FREE Tier (Try It Now)

• 5 videos per run — full feature access, same quality
• No credit card required
• Perfect for testing and small projects

PAID Tier (Production Ready)

• Unlimited videos per run
• No processing delays
• $0.01 per video with captions (most videos) — flat, any length; per-minute AI billing only when a caption-less video needs audio transcription ($0.005 per run start)

💰 Cost-aligned pricing — a flat cent for caption-based transcripts, and you only pay by duration when AI actually transcribes the audio.

🛡️ Built-in cost cap. Because you can't tell in advance whether a video has captions, the AI transcription limit (minutes) input bounds what a caption-less video can cost you:

Setting	Behaviour	Worst case per video
30 (default)	AI only for caption-less videos up to 30 min	~$0.45
0	Never use AI — caption-less videos return metadata only	$0.00
600	Effectively unlimited, for podcasts and long-form	~$9.00

Videos that already have captions are never affected — they stay a flat $0.01 at any length. When a video is skipped by this limit you get its full metadata and are not charged for AI.

🔗 View current pricing

❓ Frequently Asked Questions

Q: Which YouTube URLs are supported? A: Standard watch?v=, youtu.be short links, /shorts/, /embed/, /live/, and bare 11-character video IDs.

Q: What if a video has no captions? A: The actor automatically falls back to AI audio transcription, so you still get a transcript.

Q: How many videos can I process? A: FREE tier: 5 per run. PAID tier: unlimited.

Q: What output formats do I get? A: Plain text, timestamped segments, SRT, and VTT — export the dataset as JSON, CSV, or Excel.

Q: Does it work with private or unlisted videos? A: No — only publicly accessible videos are supported.

Q: Can I transcribe a whole list at once? A: Yes — paste multiple URLs or upload a CSV/TXT file; the URL column is auto-detected.

🐛 Troubleshooting

"Invalid YouTube URL or video ID"

• Check the URL is a real, public YouTube video
• A bare 11-character video ID also works (e.g. dQw4w9WgXcQ)

Empty or missing transcript

• The video may have captions disabled and no usable audio — try another video
• Very new uploads may not have captions processed yet

Only 5 videos processed

• That's the FREE tier limit — upgrade your Apify plan for unlimited videos per run

⚖️ Is it legal to scrape data?

Our actors are ethical and do not extract any private user data, such as email addresses, gender, or location. They only extract what the user has chosen to share publicly. We therefore believe that our actors, when used for ethical purposes by Apify users, are safe.

However, you should be aware that your results could contain personal data. Personal data is protected by the GDPR in the European Union and by other regulations around the world. You should not scrape personal data unless you have a legitimate reason to do so. If you're unsure whether your reason is legitimate, consult your lawyers.

You can also read Apify's blog post on the legality of web scraping.

🤝 Support

Join our active support community

• For issues or questions, open an issue in the actor's repository
• Check the SIÁN Agency Store for more automation tools
• 📧 apify@sian-agency.online

---

Built by SIÁN Agency | More Tools