Video Transcriber - Any Video URL to Text with Timestamps

Paste any video URL — YouTube, Facebook, Vimeo, Rumble, Twitch VODs, SoundCloud, podcast episodes, or a direct MP4/MP3 link — and get back an accurate, timestamped transcript. Works across 1000+ sites, with automatic language detection for dozens of languages.

What you get

• Full transcript of the spoken audio as a single clean string
• Timestamped segments (MM:SS / H:MM:SS + text) for subtitles, quotes, and chapter notes
• Automatic language detection, or pass a language hint
• Video metadata: title, uploader/channel, source site, duration, and video ID
• Handles videos up to 3 hours long
• Export to JSON, CSV, or Google Sheets directly from the Apify console

Supported sources

YouTube (videos, Shorts, live VODs), Facebook videos and reels, Vimeo, Rumble, Twitch VODs and clips, Dailymotion, SoundCloud, Streamable, news sites, podcast feeds, direct .mp4/.mp3/.m4a links, and 1000+ other platforms.

Use cases

• AI & LLM pipelines — turn spoken content into text for RAG systems, summarizers, and agents
• Content repurposing — convert webinars, podcasts, and videos into blog posts and newsletters
• Research & journalism — quote and search long interviews without scrubbing through video
• Meeting & lecture notes — transcribe recorded sessions hosted anywhere
• Subtitles & accessibility — generate caption text for videos that have none

How to use

1. Paste one or more URLs into Video URLs
2. (Optional) Set Spoken language if you know it (e.g. en, es); leave on auto otherwise
3. Run the actor — one record per video appears in the Dataset tab

If a site blocks the download, the actor automatically retries through Apify proxies (configurable via the Proxy option).

Output format

Each dataset record:

{
  "inputUrl": "https://www.youtube.com/watch?v=jNQXAC9IVRw",
  "videoId": "jNQXAC9IVRw",
  "title": "Me at the zoo",
  "uploader": "jawed",
  "sourceSite": "Youtube",
  "durationSeconds": 19,
  "language": "en",
  "transcript": "All right, so here we are in front of the elephants...",
  "segments": [
    { "start": "00:00", "text": "All right, so here we are in front of the elephants." }
  ]
}

Videos with no speech return an empty transcript.

Notes

• Billing scales with video length: a small base fee per video plus a per-minute transcription fee (rounded up to the next minute).
• Failed URLs (deleted videos, region locks, unsupported sites) produce an error record and are not charged.
• Videos longer than 3 hours are skipped.