Skip to main content

Getting Started

Introduction​

Whisperly is a robust transcription system that converts complete audio files into text. The system processes your audio file and uses a polling mechanism to periodically check if the transcription result is ready. Once processing is complete, the full transcript is returned to you.

How It Works​

  1. Submit an Audio File:
    Upload your audio file (e.g., WAV, MP3) to the system for processing.
  2. Processing and Polling:
    The system processes the audio and continuously polls the server to check the status of the transcription.
  3. Receive the Transcript:
    When the transcription is complete, the system returns the full transcript.

Features​

  • Batch Processing:
    Efficiently handles complete audio files.
  • Polling Mechanism:
    Automatically checks for transcription completion.
  • Multi-Format Support:
    Supports various audio file formats.
  • Secure Access:
    Uses API key-based authentication to ensure secure operations. Every minute in audio is 1 credit.