🎙️ Video Transcriber (Speech-to-Text). Turn Any Video Into Text You Can Use

Transform social videos into actionable text in seconds. This Apify actor converts Instagram, Facebook, X/Twitter, and TikTok videos into clean, timestamped transcripts that are perfect for RAG, search, summarization, and content workflows.

Powered by the speech‑to‑text engine from VidNavigator, it’s fast, accurate, and production‑ready.

This actor bridges the gap for videos without embedded subtitle tracks. If you need caption-based extraction (when subtitles exist), check our companion actor: Video Transcript Scraper.

---

✨ Why teams love this actor

• Speech-to-text, not subtitles: Captures speech even when videos don’t have captions.
• Multi-platform support: Instagram, Facebook, X/Twitter, TikTok.
• Developer-friendly output: Rich video metadata plus detailed segments with timestamps.
• Drop‑in API: One POST call. Get JSON back. Perfect for RAG, search, and analytics.

---

📈 What you get

A comprehensive data set that’s perfect for various use cases:

• Video Metadata: Instantly access video titles, descriptions, thumbnails and other metadata to help you contextualize the content.
• Timestamped Transcripts: Get every word with precise timestamps, ideal for indexing and AI models.
• LLM-Ready Data: Tailor-made for Large Language Models (LLMs) and AI applications, this data is pre-cleaned and ready to use. Ideal for NLP, sentiment analysis, or any ML workflow.

🚀 Key advantages

• 🌐 Compatible with multiple platforms: Instagram, Facebook, X, Tiktok
• 🤖 AI-Ready Output: Designed for quick integration into ML and AI applications.
• 📊 Rich Metadata: Get all the essential video details in one place.

---

🔗 Supported platforms

This video transcript scraper has been extensively tested on the following platforms:

• Instagram
• X (ex Twitter) (just copy the tweet video link)
• TikTok
• Facebook (public videos)

The tool may also work on other platforms not listed here, like media websites, though they have not been as thoroughly tested.

---

🚀 Simple inputs, powerful results

Using this actor couldn’t be easier! Just enter:

• URL: Link to the video (e.g., from Instagram, X, Facebook, etc.).

Sample input

{
  "video_url": "https://www.instagram.com/reel/C_L9MBOvb3q",
}

---

📦 Output

{
  "status": "success",
  "data": {
    "video_info": {
      "title": "A Reel Interesting Video",
      "description": "An example description for the video.",
      "thumbnail": "https://example.com/thumbnail.jpg",
      "url": "https://www.instagram.com/reel/C_L9MBOvb3q",
      "channel": "Example Creator",
      "duration": 58.5,
      "views": 123456,
      "likes": 7890,
      "published_date": "2024-07-01",
      "keywords": ["example", "social media", "video"],
      "category": "Entertainment"
    }
    "transcript": [
      {
        "text": "Hello, world!",
        "start": 0.0,
        "end": 1.5
      },
      {
        "text": "Welcome to our channel.",
        "start": 1.5,
        "end": 3.0
      }
    ]
  }
}

---

🚀 Quickstart

cURL

curl -X POST "https://api.apify.com/v2/acts/invideoiq~video-transcriber/run-sync?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"video_url": "https://www.instagram.com/reel/C_L9MBOvb3q"}'

Python

import requests, json

url = "https://api.apify.com/v2/acts/invideoiq~video-transcriber/run-sync?token=YOUR_TOKEN"
data = {"video_url": "https://www.instagram.com/reel/C_L9MBOvb3q"}
res = requests.post(url, json=data)
print(json.dumps(res.json(), indent=2, ensure_ascii=False))

JavaScript

fetch("https://api.apify.com/v2/acts/invideoiq~video-transcriber/run-sync?token=YOUR_TOKEN", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ video_url: "https://www.instagram.com/reel/C_L9MBOvb3q" })
})
  .then(r => r.json())
  .then(console.log)
  .catch(console.error);

---

⚙️ How it works

1. You provide a public video URL.
2. The actor calls VidNavigator’s speech‑to‑text API.
3. You receive clean JSON: rich metadataand timestamped transcript.

---

🧪 Best practices

• Prefer direct public video links. If content is private or geo‑restricted, transcription may fail.

---

❓ Troubleshooting

• "Video URL is required": Add a video_url string to the input.
• Ensure the URL is public and accessible without login.
• Empty or short transcripts: Some videos have minimal or no speech.

Need help or want a custom workflow? Report your issue in the issue tab and we’ll try and tailor it to your use case.