Transcribe Video

Add captions and transcriptions to videos

GET STARTED GitHub

Max file size: 250MB
Get the Source Code

Your transcribed video will play here.

Hold tight, processing may take a minute...

How do I transcribe video to text?

Step 1: Upload a video or paste a link/URL. All formats supported.

Step 2: Click the transcribe video button.

Step 3: Your VTT file will be available for download after processing.

Tips for accurate transcription

  • Keep clips short—trim silence/intros/outros before uploading for faster, cleaner results.
  • If your share link isn't a direct file URL, use Upload instead of From URL.
  • Record close to the mic and reduce background noise/echo (fans, music, traffic).
  • Avoid overlapping speech; let one person speak at a time.
  • Ensure the video actually has an audio track and a healthy volume.
  • After processing, preview and proof names, acronyms, and jargon before downloading VTT.

Privacy & security

Files are processed securely and deleted after conversion. Free demo supports smaller files but you can sign up to increase limits and unlock batch processing.

The open-source code for this project is available on GitHub. The project might inspire you to create your own subtitles or transcription project or act as the starting point for a new AI video project.

Build this into your app (when one-offs become a queue)

Adding subtitles to your video content will make it more accessible to a wider audience. If you just need a transcript now and then, this demo is perfect. If you're processing lots of files or need VTT/SRT at scale, Shotstack's APIs can automate it: queue jobs, get webhooks when they finish, and deliver files via CDN—without maintaining your own pipeline.

Get started with Shotstack's video editing API in two steps:

  1. Sign up for free to get your API key.
  2. Send an API request to create your video:
    curl --request POST 'https://api.shotstack.io/v1/render' \
--header 'x-api-key: YOUR_API_KEY' \
--data-raw '{
  "timeline": {
    "tracks": [
      {
        "clips": [
          {
            "asset": {
              "type": "video",
              "src": "https://shotstack-assets.s3.amazonaws.com/footage/beach-overhead.mp4"
            },
            "start": 0,
            "length": "auto"
          }
        ]
      }
    ]
  },
  "output": {
    "format": "mp4",
    "size": {
      "width": 1280,
      "height": 720
    }
  }
}'

Frequently asked questions (FAQs)

Yes—this demo uses automatic speech recognition (AI/ASR) behind the scenes to generate transcripts. If you need details (models/languages), see the API docs or contact support.

Yes. Download the meeting recording (MP4) and upload it here. If your share link isn't a direct file URL, use the upload option instead.

If your file is audio-only, upload it directly if supported; otherwise convert your video to MP3 first, then transcribe. (Tip: see the Video to MP3 demo to extract audio fast.)

Language support depends on the transcription backend. If a language selector isn't shown in the demo, check the Ingest API docs for the full list or set the language via API.

VTT provides time-stamped cues per caption line. For word-level timestamps or custom timing granularity, use the API and post-process the output.

Use a direct download URL. If the link requires login/cookies or expires quickly, download the file to your device and upload it to the demo.

Download your own video first, then upload it here. Many social links aren't direct file URLs, so "From URL" may not work without authentication.

Speaker labeling isn't guaranteed in the demo. If you need diarization, implement it in your app using the API and a backend that supports speaker separation.

The demo downloads VTT (and SRT via API). To get DOCX/PDF, copy the text and format it, or convert VTT/SRT in your app or a third-party tool.

Turnaround depends on clip length and audio quality. Short clips typically complete in minutes; you'll see progress in the UI. For queues and bulk jobs, use the API with webhooks.

More to do

Shotstack Edit - Video Generation and Editing API

Shotstack Studio - Online Video Editor

Pexels Slideshow Demo