Transcribe a YouTube video to SRT subtitles
Accurate transcript plus an SRT file.
{
"urls": [
"https://www.youtube.com/watch?v=jNQXAC9IVRw"
],
"quality": "accurate",
"subtitleFormat": "srt"
}AI transcription
Whisper Transcriber: video links and audio files to text with timecodes
Paste a YouTube, TikTok, Vimeo or SoundCloud link, or an MP3, WAV, M4A, FLAC, OGG, MP4 or MOV file, and get clean text with timecodes from Whisper large v3 in 90+ languages. Add speaker labels, English translation, SRT or VTT subtitles, or chunks ready for RAG.
★ 5.0 rating · 2 reviews27 users93.8% successful runs (30 days)
What data you get
text | Full transcript |
segments | Timed segments with start and end |
language | Detected or chosen spoken language |
speakers | Speaker labels (optional add-on) |
englishTranslation | Translation to English (optional) |
chunks | RAG-ready chunks (optional) |
subtitles | SRT or VTT subtitle file (optional) |
duration | Audio length processed |
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 pay per minute transcribed, per file processed and per video link resolved; speaker labels are an add-on billed per minute, and using your own Groq key lowers the per-minute charge.
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 with speaker labels
Two speakers, timed segments.
{
"urls": [
"https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-1min.m4a"
],
"diarize": true,
"speakerCount": 2,
"includeSegments": true
}Transcribe a Spanish TikTok and translate to English
Spoken Spanish turned into English text.
{
"urls": [
"https://www.tiktok.com/@nasa/video/7300000000000000000"
],
"language": "es",
"translateToEnglish": true
}Turn a YouTube video into RAG chunks
Fast transcription split into 1,500-character chunks.
{
"urls": [
"https://www.youtube.com/watch?v=jNQXAC9IVRw"
],
"chunkForRag": true,
"chunkSize": 1500,
"quality": "fast"
}Use cases
- Content creators: turn videos into subtitles, blog posts and show notes.
- Researchers: transcribe interviews with timecodes and speaker labels.
- Marketers: analyse what competitors say in their videos and podcasts.
- AI developers: feed spoken content into RAG pipelines as clean chunks.
FAQ
Do I need an OpenAI or Whisper API key?
No. Transcription works without your own key; you can optionally add a Groq key.
Which sources are supported?
Links from YouTube, TikTok, Instagram, Facebook, X, Vimeo, SoundCloud and more, plus MP3, WAV, M4A, FLAC, OGG, MP4 and MOV files.
Can I get subtitles?
Yes. Choose SRT or VTT and a subtitle file is created alongside the transcript.
Is it legal to transcribe YouTube or TikTok videos?
Transcribing public videos for research, accessibility or analysis is common, but rights belong to the creators. Respect copyright, platform terms and local law, get consent for private recordings, and avoid republishing transcripts without permission.
How do I get the data into my app?
Call it through the Apify API, use the Python or JavaScript client, or connect it to Make, n8n, Zapier or Google Sheets. Results export as JSON, CSV or Excel.