How to Integrate VideoToTextAI APIs to Automatically Create VTT Files from Transcriptions

Video To Text AI

Sun Jul 20 2025

Learn how to automate subtitle generation from your videos using the VideoToTextAI API. Upload, transcribe, and export VTT files effortlessly.

Automate Subtitles with the VideoToTextAI API

Creating subtitles for your video content is essential for accessibility, engagement, and SEO. With Video To Text AI, you can automate the entire process using our API — no manual transcription required. In this guide, we'll walk you through how to integrate Video To Text AI’s API to upload a video/audio file, transcribe it, and generate a `.vtt` (WebVTT) subtitle file you can use across platforms.

Step 1: Get Your API Key

Before you start, log in to the Video To Text AI dashboard to generate your API key. You'll need this for all authenticated API requests.

Step 2: Upload a File for Transcription

Use the `/v2/upload/file` endpoint to send a video or audio file for transcription.

Endpoint:

POST https://videototextai.com/v2/upload/file

Required Headers:

`Content-Type: application/octet-stream`
`Content-Disposition: attachment; filename="yourfile.mp4"`
`x-api-key: <your-api-key>`

Optional header:

`X-user-content-language: en` (Override language detection)

Sample:

curl -X POST "https://videototextai.com/v2/upload/file?process_async=true" \
  -H "x-api-key: <your-api-key>" \
  -H "Content-Type: application/octet-stream" \
  -H "Content-Disposition: attachment; filename=\"movie.mp4\"" \
  --data-binary @"./movie.mp4"

You'll receive a JSON response with a unique `uuid_filename` identifier for your uploaded file.

Step 3: Export the VTT File

Once the transcription is complete(which you can check with the status endpoint), use the `uuid_filename` to export the VTT file.

Endpoint:

POST https://videototextai.com/user/transcriptions/{uuid_filename}/export/vtt

Replace `{uuid_filename}` with the identifier returned in the upload step.

Headers:

`x-api-key: <your-api-key>`

Sample `curl` Request:

curl -X POST "https://videototextai.com/user/transcriptions/123abc456def/export/vtt" \
  -H "x-api-key: <your-api-key>"

This returns a VTT file containing the transcribed subtitles.

Bonus: Use Your VTT File Anywhere

You can use the downloaded `.vtt` file in video players like VLC, embed it on your website, or upload it to YouTube for captioning.

Final Notes

File size limit: 10GB
Supported formats: flac, m4a, mp3, mp4, mpeg, mpga, oga, ogg, wav, webm
VTT export requires transcription to complete first. You can check status via the status api endpoint.
Be sure to generate your API key by logging into the Video To Text AI UI

Ready to Automate?

With just a few API calls, you can turn your media into accessible, searchable content — automatically. Visit Video To Text AI to get started!