Skip to Content
Documents🏁 Getting Started

Getting Started

1. Download & Install

Visit the homepage to download the installer for your platform:

  • macOS: Download .dmg, drag to Applications
  • Windows: Download .exe installer, follow the wizard

Requirements: macOS 11+ / Windows 10+, 8GB+ RAM recommended.

2. First Launch & Model Download

On first launch, if no transcription model is detected, you’ll be guided to download one:

  1. Choose an ASR engine:
    • Whisper: strong multilingual support; we recommend base for beginners
    • Qwen3-ASR: better for Chinese, dialects, and Chinese-English mixing; we recommend 0.6B for beginners
  2. Choose a default model
  3. Click download — the model will be saved locally
  4. You will land in the library when the download finishes

You can also import custom models via Deep Link:

subwright://download/?url=<model_url>

3. Complete Your First Transcription

Method 1: Local File

  1. Drag an audio/video file onto the library, or use All media → Open…
  2. The Watch page opens with the player and the inspector
  3. In the Script stage of the inspector, click “Transcribe”
  4. Wait for completion — the transcript streams in on the right, synced to playback

Method 2: Recording

  1. Open Record (/record) from the sidebar
  2. Choose the input device (microphone / system audio)
  3. Click “Start Recording” and stop when done
  4. The recording is saved, transcribed, and opened in the Watch page
  1. Paste a YouTube, Bilibili or other video link into the library link box
  2. Install yt-dlp on first use (guided)
  3. It downloads, transcribes, and opens in the Watch page

4. Export Results

After transcription, open the Script stage of the inspector and click Export:

  • TXT: Plain text, good for reading
  • SRT/VTT: Subtitle files for video production
  • JSON: Full data with timestamps
  • DOCX/Markdown: Rich format documents

5. Explore More

Need help? Check FAQs or email contact@once.work

Last updated
🚀 IntroductionTranscription