When should I use transcript vs transcribe?

Try the transcript endpoint first—it's faster and scales up to as low as $0.000025/transcript. If no captions exist, use transcribe (scales up to $0.0041/min).

How fast is the transcription?

Blazing fast. We transcribe 1 hour of video in under 30 seconds. Short Facebook videos are processed almost instantly.

What languages are supported?

We support 99+ languages with high accuracy. The engine automatically detects the spoken language.

What about private Facebook videos?

No. The API only works with publicly accessible Facebook video content.

Are Facebook Reels supported?

Yes. Facebook Reels can be transcribed using the same endpoints as regular Facebook videos.

Back to solutions

API Solution

Facebook Video Transcription API with Captions and Speech-to-Text

Get transcripts from Facebook videos using caption retrieval when available, or speech-to-text for videos without captions. Timestamped JSON output for LLMs and search.

What is the Facebook Video Transcription API?

The Facebook Video Transcription API provides two methods to get text from Facebook videos. Use the Transcript API to retrieve native captions when they exist (faster and lower cost), or use the Transcribe API for speech-to-text when captions are not available. Both return the same consistent JSON format with timestamps and metadata.

Two methods for Facebook videos

Recommended first

Caption retrieval

Fast extraction of native captions when available. Lower cost per request.

POST /v1/transcript

Fallback

Speech-to-text

Generate transcripts from audio when no captions exist. Works on any video.

POST /v1/transcribe

What data is returned?

Full transcript with timestamps (start/end times)
Video metadata: title, description, thumbnail URL
Page/profile information: name, URL
Video statistics: views, likes, shares, duration
Structured segments for easy integration
Video URL and upload timestamp
Consistent schema across both methods

Supported URL formats

facebook.com/watch/?v=123456789
Facebook Watch video URLs
facebook.com/page/videos/123456789
Page video URLs
fb.watch/abc123
Facebook short URLs

Example use cases

Media Monitoring

Track brand mentions in Facebook video content by transcribing and analyzing at scale.

Content Archives

Build searchable archives of Facebook video content for research or compliance purposes.

Social Analytics

Analyze video content from Facebook pages for competitive intelligence and trend tracking.

API workflow

1.Try /v1/transcript with Facebook URL
2.If captions exist, receive transcript
3.If 404, call /v1/transcribe instead
4.Response returns transcript + metadata

Code examples

Try transcript first for speed, fall back to transcribe when needed.

Transcript API docs (caption retrieval) →Transcribe API docs (speech-to-text) →

bash

Response structure

{
  "status": "success",
  "data": {
    "video_info": {
      "title": "Facebook video by Page Name",
      "description": "Check out our latest update! Learn more...",
      "thumbnail": "https://scontent.xx.fbcdn.net/v/...",
      "url": "https://www.facebook.com/watch/?v=1234567890",
      "channel": "Page Name",
      "channel_url": "https://www.facebook.com/pagename",
      "duration": 180.5,
      "views": 50000,
      "likes": 2500
    },
    "transcript": [
      { "start": 0.0, "end": 4.2, "text": "Welcome to our channel!" },
      { "start": 4.2, "end": 9.8, "text": "Today we're going to show you something exciting." },
      { "start": 9.8, "end": 15.1, "text": "Let's get started with the tutorial." }
    ]
  }
}

Why use VidNavigator for Facebook videos?

Blazing fast transcription

Our speech-to-text engine transcribes 1 hour of video in under 30 seconds.

99+ languages supported

Transcribe Facebook videos in over 99 languages with high accuracy.

Cost-effective at scale

Scale up to as low as $0.000025/transcript or $0.0041/min for speech-to-text. Even cheaper for Enterprise.

Flexible approach

Caption retrieval when available, speech-to-text as fallback. Best of both methods.

Pricing

Start free. Caption retrieval scales up to as low as $0.000025 per transcript. Speech-to-text scales up to as low as $0.0041 per minute. Enterprise plans available at even lower rates.

View pricing Get API key