# 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. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.relay.app/ai/audio-transcription.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.