---
title: Detect Video Text
slug: video-detect-text
url: https://apyverse.com/apyhub/service/video-detect-text
provider: ApyHub
categories: [Artificial Intelligence, Data Extraction]
auth: api_key
---

# Detect Video Text

Extract text from a video URL or uploaded file using Azure or Google OCR. Get provider response data for captions, labels, and on-screen text.

## Endpoints

| Method | Path | Description | Atoms |
| --- | --- | --- | --- |
| POST | `ai/video/detect/text/url` | What it does Detects text in a video provided by URL. You send the video URL and choose which OCR s… | 500 |
| POST | `ai/video/detect/text/file` | What it does Uploads a video file and runs text detection using either Azure or Google, depending o… | 500 |

## About

## What it does
Video Text Detection finds text in a video file or at a video URL and returns the detection results from the OCR provider you choose. Use it when you need to extract on-screen text from recorded footage, product demos, tutorials, or compliance recordings without building your own video OCR pipeline.

Send a `url` with `requested_service` set to `azure` or `google`, or upload a `file` with the same service choice. For Azure requests, the URL route accepts `azure.region`, `azure.account_id`, and `azure.access_token`; the file route accepts `azure_region`, `azure_account_id`, and `azure_access_token`. For Google requests, the URL route accepts `google.google_language` and `google.google_credential_json`; the file route accepts `google_language` and `google_credential_file`.

The response always includes a `data` object. Inside it, the `azure` or `google` property is present depending on the `requested_service` you sent. The service-specific object is returned as provided by the underlying OCR provider, so you can pass that output into your own processing, indexing, or review workflow.

This is a good fit for automatically capturing captions, signs, labels, UI text, or embedded annotations from video assets before storing them in a database or searchable archive.

## Usage

Authenticate with an ApyHub API key in the `apy-token` header.
Full docs and a live playground: https://apyverse.com/apyhub/service/video-detect-text