Back to Settings
Settings

Models — local vs cloud

Choosing a transcription model. Privacy, speed, accuracy, language support.

Whiskers supports local models (run on your Mac, no internet, no cost) and cloud models (faster on long files, no disk usage, but audio leaves your device).

Local models

ModelLanguagesSizeBest for
Parakeet V2English~400 MBFastest local English
Parakeet V325~600 MBMultilingual, fast, accurate
Whisper Tiny99+~75 MBLowest disk; basic accuracy
Whisper Base99+~150 MBLight footprint
Whisper Small99+~500 MBBalanced
Whisper Medium99+~1.5 GBHigh accuracy
Whisper Large v399+~3 GBBest accuracy, slowest

Trade-offs: disk space and (for big Whisper variants) RAM. Apple Silicon handles Large v3 comfortably with 16 GB+ RAM; older machines should pick smaller.

Privacy: audio never leaves your Mac.

Cloud models

ProviderModelNotes
GroqWhisper Large V3 TurboVery fast; generous free tier
OpenAIWhisper-1Reliable, paid per use
DeepgramNova-3, Nova-2Lowest latency on long files
GoogleGemini variantsMultilingual, paid per use

Trade-offs: audio sent to third party, requires internet, has usage costs. Some providers (Groq) have free tiers that cover normal personal use.

Each needs an API key — see API Key Setup.

Switching models

To a local model

  1. Settings → Models → On-Device.
  2. If not downloaded, click Download.
  3. Click the model card to activate.
Settings → Models → On-Device tab listing Parakeet V2, Parakeet V3, and Whisper variants with download buttons

To a cloud model

  1. Settings → Models → Cloud API.
  2. Pick a recommended card or expand a provider under All models.
  3. If the card says Setup Required, add the API key when prompted.

If you have multiple keys for a provider, the Cloud Transcription picker has its own chooser — so you can transcribe with one key and enhance with another.

From the menu bar

The menu bar icon has a quick model submenu. Click → hover Model → pick from the list.

Language

Once a model is active, a Language dropdown appears on its card if it supports multiple languages.

Auto-detect works but adds processing time and occasionally misidentifies short utterances. Set it explicitly if you primarily speak one language.

FamilyLanguages
Parakeet V2English
Parakeet V325 (incl. Spanish, French, German, Mandarin, Japanese, Hindi, Arabic)
Whisper (all sizes)99+

Which one to actually pick

  • English speakers: Parakeet V2. Fast, accurate, private, small.
  • Multilingual: Parakeet V3 if your language is in the 25, otherwise Whisper Large v3.
  • Privacy-critical: any local model.
  • Hour-long files in bulk: a cloud provider (Groq is usually fastest).
  • No disk space: any cloud provider.

You can always change later. Downloaded models can be removed from the same panel.