shaishaicookie/fcpx-auto-captions

🎬 Auto Captions for Final Cut Pro Powered by OpenAI's Whisper Model

What it solves

It automates the creation of captions for videos in Final Cut Pro X, removing the need for manual transcription of audio to text.

How it works

The application uses OpenAI's Whisper model to transcribe audio from video files and generates caption files that can be imported directly into Final Cut Pro X via fcpxml, or exported as .srt files for use in other editing software like Adobe Premiere Pro, DaVinci Resolve, and Sony Vegas.

Who it’s for

Video editors using Final Cut Pro X and other professional video editing software who need fast, accurate automated transcription.

Highlights

  • Accurate transcription supporting over 90 languages.
  • Direct integration with Final Cut Pro X via fcpxml.
  • Support for .srt file exports for compatibility with Premiere Pro, DaVinci Resolve, and Sony Vegas.
  • Real-time output and a progress bar for tracking transcription status.

Related

  • Project
    filippogiruzzi/voice_activity_detection

    A deep learning-based Voice Activity Detection system using a 1D-ResNet and MFCC features to classify audio signals as speech or noise.

  • Project
    funnyzak/tts-now

    tts‑now is a cross‑platform Electron desktop app that calls Alibaba Cloud and iFlytek TTS APIs to synthesize speech from text, supporting single and batch jobs, with pre‑built binaries for Windows, macOS and Linux.

  • Project
    licyk/qwen-tts-webui

    A web interface and OpenAI-compatible API for Qwen3-TTS, offering optimized text-to-speech generation, voice cloning, and voice design capabilities.

  • Project
    pretyflaco/millet

    A meeting transcription and summarization tool that captures system audio from any app and produces private, speaker-diarized transcripts and professional PDFs using local models or TEEs.