​
What can you do with it?

The /transcription command enables you to convert audio files into text using AI-powered speech recognition. You can transcribe recordings, meetings, interviews, podcasts, and any audio content into readable text in various formats for further processing or documentation.

​
How to use it?

​
Basic Command Structure

/transcription [audio-file] [options]

​
Parameters

Required:

  • audio-file - The audio file to transcribe (URL or uploaded file)

Optional:

  • format - Output format: json, plaintext, markdown, or html (defaults to json)
  • language - Specify the audio language for better accuracy (auto-detected if not specified)
  • timestamps - Include timestamps in the transcript (true/false)

​
Response Format

The command returns:

{
  "output": "The transcribed text content",
  "duration": "audio duration in seconds",
  "language": "detected or specified language",
  "format": "output format used"
}

​
Examples

​
Basic Usage

/transcription
audio-file: meeting-recording.mp3

Transcribes an audio file into text with default JSON formatting.

​
Advanced Usage

/transcription
audio-file: interview.wav
format: markdown
language: English
timestamps: true

Transcribes an interview with timestamps included, formatted as markdown with specified language for accuracy.

​
Specific Use Case

/transcription
audio-file: podcast-episode.mp3
format: plaintext
language: Spanish

Transcribes a Spanish podcast episode into plain text format for easy reading and sharing.

​
Notes

Supported Audio Formats:

  • MP3 (.mp3)
  • WAV (.wav)
  • M4A (.m4a)
  • FLAC (.flac)
  • OGG (.ogg)

Language Support:

  • Automatic language detection
  • Over 50 languages supported