Getting Started

Welcome

This CatDV Worker Node plugin integrates seamlessly with OpenAI's Whisper, providing advanced transcription and translation capabilities directly within your CatDV library. Whether you’re a media production company, an educational institution, or a legal team managing multimedia content, this integration simplifies and enhances your transcription workflows.

By leveraging Whisper’s powerful speech recognition, the plugin enables you to extract valuable metadata from audio and video assets quickly and accurately. This streamlined process improves content organization and frees your team to focus on higher-value activities, boosting productivity and maximizing the efficiency of your CatDV environment.

For more information on OpenAI’s Whisper model, visit here: https://github.com/openai/whisper/blob/main/model-card.md

Release Notes

1.0.0 - April 2025 - Initial public release

Requirements

CatDV Pegasus Server 10.7.1 or later

CatDV Enterprise or Pegasus Worker 9.2.10 or later

CatDV Whisper Plugin 1.0.0 or later

Installation

There are three different plugin files for Whisper, (1) WhisperAI_Mac.catdv, (2) WhisperAI_Win_CPU.catdv, and (3) WhisperAI_Win_GPU. Please install the appropriate .catdv file by dragging and dropping it into the Worker application based on your operating system.

The Windows installer is designed for x64 systems, and the macOS version is optimized for Apple Silicon (M-series chips).

Currently, a Linux version of this worker plugin is not available.