Video Transcriber Actor

This actor extracts transcripts and metadata from videos on social media and other platforms. Provide a public video URL, and it returns a structured JSON with the transcript, timestamps, and video details.

Overview

The actor takes a video URL, processes it, and returns a transcript broken into timestamped segments along with core video metadata. It works with Instagram, Twitter/X, Facebook, TikTok, Vimeo, Dropbox, Google Drive, and Loom. Transcription is automatic and includes language detection.

Key Features

• Multi-Platform: Works with Instagram, Twitter/X, Facebook, TikTok, Vimeo, Dropbox, Google Drive, and Loom.
• Structured Output: Returns a clean JSON object containing the full transcript, timestamped segments, and video metadata (title, description, duration, etc.).
• Automatic Language Support: Detects and transcribes multiple languages.
• Fast Processing: Efficient for videos of any length.

Input

Run the actor with a JSON input containing the video URL.

{
  "url": "https://www.instagram.com/watch?v=example"
}

• url (required): The publicly accessible URL of the video to transcribe.

Output

The actor outputs a single JSON object per video with the following structure:

{
  "url": "https://www.instagram.com/watch?v=example",
  "title": "Video Title",
  "description": "Video Description",
  "duration": "10:00",
  "viewCount": 1000,
  "uploadDate": "20240911",
  "language": "en",
  "transcript": "Full transcript text...",
  "segments": [
    {
      "start": 0.0,
      "end": 5.0,
      "text": "Transcribed text segment..."
    }
  ]
}

How to Use

Via Apify Console

1. Navigate to the actor's page on Apify.
2. Enter the target video URL in the input field.
3. Click Run.

Via Apify API

Use the Apify Client to run the actor programmatically.

from apify_client import ApifyClient

client = ApifyClient("YOUR_API_TOKEN")
run_input = { "url": "https://www.instagram.com/watch?v=example" }

run = client.actor("username/video-transcriber").call(run_input=run_input)
results = client.dataset(run["defaultDatasetId"]).list_items().items

Limitations

• Videos must be publicly accessible.
• Some source platforms may require authentication (e.g., private videos).
• Processing time is dependent on video length.

Built by Webscrap Team.