Audio/Video to Text

Extract text from an audio/video file

Converting audio or video files to text can save time and streamline processes, especially when dealing with information-heavy content. Transcribing these files makes it easier to apply text processing tools like summarization, quote extraction, and topic identification. It also eliminates the need to repeatedly listen to the file for specific information.

This page introduces the steps to convert audio and video files to text using available tools.

Note: Relevance focuses on text analysis, so the supported upload size for audio and video files is limited. For large video files, consider using tools like QuickTime to extract the audio and upload the audio file instead.

How to Use the Convert Audio/Video to Text Step

Available Converters

1. OpenAI Audio-to-Text Converter: Only supports audio input and requires your API key.

Add the Component

1. Navigate to the Workflow page.

2. Click on + Create Workflow or select an existing workflow.

3. Click on + Add Action.

4. Select the desired audio/video-to-text converter step from the list of action components.

File URL

All converters require a file as an input. If your file is publicly accessible on the web (i.e., no authentication or sign-up required), provide the URL directly or as a text input. Otherwise, you will need to add a File-to-URL input. In either case, use the {{variable_name}} to provide the data to the converter.

Access the Step Output

The output structure varies based on the audio/video processing tool used. Below are examples of accessing the output in a JavaScript code step for each converter:

Common Errors

Unsupported File Format

If the provided input file is not in a supported format, you might see an error like:

"err_code": "Unsupported Media Type", "err_msg": "..."

Solution: Use an audio/video editor to export your file to common audio/video formats and try again.

File Size

For files larger than 60 MB, you might encounter an error:

"Request body larger than maxBodyLength limit"

Solution: For large video files, use video editing tools like QuickTime to extract the audio and upload the audio file instead.