# Audio Transcription

### Overview

Relay.app leverages **OpenAI Whisper** to provide a simple interface for transcribing audio files into text. Users can upload audio files, and the system processes them using Whisper's state-of-the-art transcription technology, delivering accurate text results.

### Supported File Types

Our transcription steps support the following file types, based on what OpenAI Whisper supports: **MP3, WAV, M4A, OGG, MPEG, MP4, MPGA**

> **Note**: Whisper's transcription quality may vary based on the clarity and quality of the input audio.

***

### File Size and Duration Guidelines

#### File Size Limit

* Maximum size: **25MB** per audio file.

#### Approximate Audio Length

The duration of audio that can be processed depends on the format and compression quality:

* **High-compression formats (e.g., MP3, OGG)**: Up to **30 minutes** of audio.
* **Low-compression formats (e.g., WAV)**: Shorter durations, typically **10–20 minutes**, due to larger file sizes.

***

### Best Practices

* Ensure the audio is clear and free from excessive background noise for optimal transcription quality.
* Use shorter clips for faster processing.
* Prefer MP3 or M4A formats for longer durations within the file size limit.
* For longer audio transcription needs, we recommend leveraging [Assembly AI](https://www.relay.app/apps/assemblyai/integrations) for transcription, which is offered as a separate integration in Relay.app

***

### Troubleshooting

#### Common Issues:

* **File exceeds 25MB**: Compress or trim the audio file using an audio editing tool before uploading.
* **Unsupported format**: Convert the file to one of the supported formats using free tools like Audacity or online converters.