Skip to Content
Documents⚡ Core FeaturesTranscription

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

  1. Select the “File” tab on the workbench
  2. Drag & drop a file, or click “Select File”
  3. (Optional) Adjust transcription options: language, model, temperature, etc.
  4. Click “Transcribe”
  5. Preview results in real time, segments append on the right

Transcription Options

OptionDescriptionRecommendation
EngineWhisper or Qwen3-ASRTry Qwen3-ASR for Chinese content; see Qwen3-ASR Engine
LanguageAuto-detect or specify source languageSpecifying improves accuracy
Modeltiny/base/small/medium/large or Qwen3-ASR 0.6B/1.7Bbase for speed, large for accuracy
TemperatureSampling randomness0 = deterministic, 1 = random, default 0
Stable TimestampsVAD-backed precise timestampsEnable for better subtitle timing
Speaker DiarizationIdentify different speakersEnable 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 transcription
  • Cmd/Ctrl + .: Abort transcription
Last updated