YouTube Transcript Cleaner for RAG
Pricing
Pay per usage
Go to Apify Store

YouTube Transcript Cleaner for RAG
Extracts clean YouTube transcripts (no timestamps) ready for LLMs and RAG pipelines.
Pricing
Pay per usage
Rating
0.0
(0)
Developer
GapDiscover Studio
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
6 days ago
Last modified
Categories
Features
Limited permissions
Share
YouTube Transcript Cleaner for RAG & LLMs
Extract clean, ready-to-use transcripts from YouTube videos. No timestamps, no noise — just pure text optimized for RAG pipelines, LLM training, and content analysis.
Why use this Actor?
- Clean Output: Removes timestamps, newlines, and extra spaces.
- LLM-Ready: Perfect for feeding into ChatGPT, Claude, or any RAG system.
- Bulk Support: Process multiple videos in one run.
- Error Handling: If a video has no subtitles, it returns a clear error message without failing the entire run.
How it works
- Paste a list of YouTube video URLs into the input field.
- Run the Actor.
- Get a dataset with clean transcripts, character counts, and status for each video.
Use Cases
- RAG Pipelines: Feed clean transcripts into your vector database.
- Content Analysis: Analyze competitor videos without manual copy-pasting.
- Research: Extract text from educational or documentary videos for study.
Input Example
{"videoUrls": ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"]}## Output Example{"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ","transcript": "We're no strangers to love...","charCount": 1234,"status": "success"}## PricingThis Actor uses Pay-per-event pricing. You only pay for successfully processed transcripts ($0.005 per video).