Transcribe a YouTube video to text with SRT subtitles
Fast transcription plus a ready SRT file.
{
"urls": [
"https://www.youtube.com/watch?v=jNQXAC9IVRw"
],
"quality": "fast",
"subtitleFormat": "srt"
}AI & transcription
Speech to text for YouTube, TikTok and any media URL
Paste a YouTube, TikTok, Instagram, X, Vimeo or SoundCloud link, or any audio or video file, and get the transcript with timecodes, timed segments and the detected language. Export SRT or WebVTT subtitles in 90+ languages, add speaker labels, or split the text into chunks for RAG.
★ 5.0 rating · 2 reviews24 users97.1% successful runs (30 days)
What data you get
transcript | Full transcript text |
segments | Timed passages with start and duration |
timecodes | Timecodes for each segment |
language | Detected or set spoken language |
srt / vtt | Ready-made subtitle files |
speakers | Speaker labels (optional add-on) |
chunks | RAG chunks with start timecodes |
How it works
- Open the scraper on Apify and sign up (free).
- Enter routes, dates and options in the form.
- Click Start and download results as JSON, CSV or Excel, or call the API.
Pricing
$2.00 per 1,000 rows
Pay per event: you are charged only for what the run returns — minutes of audio transcribed, files processed, video links resolved, the optional speaker-label add-on per minute. There is no monthly subscription; caps in the input keep each run's cost predictable.
Apify gives $5 free credits every month — enough to test this scraper at no cost.
Example tasks
Ready-made inputs. Copy one into the scraper form or send it through the API.
Transcribe an interview audio file with speaker labels
Accurate mode, two speakers, English.
{
"urls": [
"https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-1min.m4a"
],
"quality": "accurate",
"diarize": true,
"speakerCount": 2,
"language": "en"
}Translate a YouTube video transcript to English and chunk for RAG
English transcript split into retrieval chunks.
{
"urls": [
"https://www.youtube.com/watch?v=jNQXAC9IVRw"
],
"translateToEnglish": true,
"chunkForRag": true,
"chunkSize": 1000
}Use cases
- Content creators: get subtitles and captions for videos in minutes.
- Researchers and journalists: transcribe interviews with speaker labels.
- AI developers: feed video transcripts into RAG pipelines and chatbots.
- Marketers: repurpose podcasts and videos into articles and posts.
FAQ
Which links and files are supported?
Links from YouTube, TikTok, Instagram, Facebook, X, Vimeo, SoundCloud, Twitch, Dailymotion, VK, Rutube and Bilibili, plus direct audio and video file URLs or an uploaded file.
Which languages does it support?
90+ languages, detected automatically or set with a two-letter code; it can also translate the transcript to English.
Is it legal to scrape YouTube and TikTok?
The scraper reads publicly available YouTube and TikTok data without logging in. Scraping public data is generally allowed, but you are responsible for complying with local laws and the site's terms, and for not collecting or misusing personal data.
What is the difference between fast and accurate?
Fast is the everyday choice. Accurate makes fewer mistakes on accents, noise and technical vocabulary, and costs more.
How do I get the data into my app or spreadsheet?
Call it through the Apify API, use the Python or JavaScript client, or connect it to Make, n8n, Zapier or Google Sheets. Results export to JSON, CSV or Excel, and runs can be scheduled.