Transcription
OnceScribe’s core capability is converting audio or video into timestamped text. All processing happens locally on your device.
Supported Formats
- Audio: MP3, WAV, M4A, FLAC, OGG, AAC, WMA
- Video: MP4, MOV, AVI, MKV, WMV, FLV, WEBM
Start Transcribing
- Select the “File” tab on the workbench
- Drag & drop a file, or click “Select File”
- (Optional) Adjust transcription options: language, model, temperature, etc.
- Click “Transcribe”
- Preview results in real time, segments append on the right
Transcription Options
| Option | Description | Recommendation |
|---|---|---|
| Engine | Whisper or Qwen3-ASR | Try Qwen3-ASR for Chinese content; see Qwen3-ASR Engine |
| Language | Auto-detect or specify source language | Specifying improves accuracy |
| Model | tiny/base/small/medium/large or Qwen3-ASR 0.6B/1.7B | base for speed, large for accuracy |
| Temperature | Sampling randomness | 0 = deterministic, 1 = random, default 0 |
| Stable Timestamps | VAD-backed precise timestamps | Enable for better subtitle timing |
| Speaker Diarization | Identify different speakers | Enable for meetings |
Speaker Diarization
When enabled, results are labeled Speaker 1, Speaker 2, etc. Supports up to 4 speakers.
- Requires additional ONNX model (auto-downloaded on first use)
- Accuracy depends on audio quality and speaker count
- Different speakers shown in different colors, click to jump
Abort & Retry
- Click “Abort” anytime during transcription
- Already transcribed content is preserved
- Adjust options and re-transcribe the same file
Shortcuts
Cmd/Ctrl + T: Start transcriptionCmd/Ctrl + .: Abort transcription
Last updated