Function Details

Transcribe Media

Provided by

Logo

OpenAI

Media Transcription

This function transcribes audio from video or audio files into text. Simply provide a URL to your media file, and it will extract the audio and transcribe it using OpenAI's Whisper model.

Supported File Types

  • Video formats: MP4 and other common video formats

  • Audio formats: MP3, WAV, M4A, OGG, AAC, WMA, FLAC

Limitations

  • Maximum duration: 60 minutes

  • File must be accessible via a direct URL

  • File size should be reasonable (recommended under 100MB)