How to extract YouTube transcripts in bulk - text, SRT and VTT, any language, pay only for delivered transcripts
Feeding a YouTube video to an AI, a research doc or a subtitle editor starts with the same boring step: getting the transcript out. YouTube has no transcript API for other people's videos, the manual copy-paste from the
Feeding a YouTube video to an AI, a research doc or a subtitle editor starts with the
same boring step: getting the transcript out. YouTube has no transcript API for other
people's videos, the manual copy-paste from the player loses the timestamps, and most
extractors charge you per attempt - including the videos that fail.
So I built an extractor that works the way I would want to buy it:
- Give it a single video, a whole playlist or an entire channel (up to 500 videos per run).
- Pick your languages - English, Spanish, or any other caption language the video actually has. Manual subtitles are preferred; auto-generated captions are used when they are the only option, and always flagged.
- Get back, per video: the clean full text, timed segments, and ready-to-use SRT and WebVTT files, plus title, channel, publish date, duration and view count.
Try it with zero setup - this ready-to-run task pulls the transcripts of 10 recent
TED talks, in English and Spanish:
TED Talks Playlist - Transcripts in English and Spanish
Real numbers from that exact run: 10 videos attempted, 9 transcripts delivered in
about 3.5 minutes. One video refused every session - and that is the point of the
pricing: you pay only for transcripts actually delivered, $4.50 per 1,000.
Failed videos are never charged. Comparable extractors on the store charge $5 to
$10 per 1,000, some of them per attempt.
Spanish is a first-class citizen here, not an afterthought: ask for "es" and you get
the real Spanish caption track, not a machine translation of the English one.
It is also callable from code and from AI agents: full API access, and it works as a
tool through Apify's MCP server, so Claude, Cursor or your own agent can fetch
transcripts directly.
Honest limits: a video needs captions (manual or auto-generated) to have a
transcript at all, and YouTube fights automated access, so an occasional stubborn
video will fail. When it does, you are not charged for it - retry it later and it
usually lands.
I am a solo dev and this just launched. If you try the TED task, the thing that
helps most is an honest review on the Actor page - the first reviews are what get a
tool like this discovered.
Originally published by Dev.to AI. Aggregated on AIWithGhost for educational purposes β full credit and traffic to the original publisher.