A model for the job

Choose your local models.

Facts checked . Product plans and features can change.

Speech and cleanup are separate stages

The speech model turns audio into words. Deterministic rules can format those words; an optional text model can make further edits within its time and preservation checks. Choosing an AI cleanup model does not replace the speech model, and better prose does not prove better recognition.

Pick a compatible speech model

Fresh profiles recommend Parakeet v3 int8, with its disclosed tiny Whisper language detector. It recognizes 25 European languages, including English, French, German, Spanish and Portuguese. English max uses Parakeet v2.

All languages uses the shared Whisper large-v3-turbo model for the other supported language choices. Whisper base, small and medium are alternative local options. Use language pins and model compatibility to choose a route for the words you actually dictate.

Speech model or packageTransferLicense
Default: Parakeet v3 + language detector773.4 MBCC-BY-4.0 + MIT
English max: Parakeet v2661.3 MBCC-BY-4.0
Whisper base147.9 MBMIT
Whisper small486.2 MBMIT
Whisper medium1530.6 MBMIT
All languages: Whisper turbo1621.7 MBMIT
Optional Silero speech detection2.3 MBMIT
Optional GTCRN quiet-speech enhancement0.54 MBMIT

Sizes are calculated from the pinned catalog at build time, with dependency deduplication and bundled notices excluded from network transfer. MB means 1,000,000 bytes. Existing verified files and resumable partials can reduce the remaining transfer. Installed disk use and temporary space are separate.

Install explicitly, then reuse offline

Setup shows the recommendation, complete package size, source and license before Download / Resume. Pause is available. Downloaded files are verified before they are ready, and later launches reuse the installed models offline. Choosing a language, enabling a feature or starting recognition does not fetch missing files.

Settings → Models provides installation/storage status and selected-model performance checks. Existing local Whisper paths have a compatibility route; a successful local load is distinct from catalog checksum verification.

Optional AI cleanup and editing

Rules-only cleanup needs no text model. Optional Qwen cleanup weights and a compatible llama.cpp CPU or Vulkan runtime add separate transfers. Command, Translate and Ask share an experimental editing setup with a 4B model; downloading it does not enable any of those features or change ordinary speech settings.

Optional model/runtimeTransferLicense
Qwen3.5 0.8B cleanup579.6 MBApache-2.0
Qwen3.5 2B cleanup1396.2 MBApache-2.0
Qwen3.5 4B experimental editing3013.0 MBApache-2.0
llama.cpp CPU runtime46.9 MBMIT + LLVM OpenMP license notice
llama.cpp Vulkan runtime88.9 MBMIT + LLVM OpenMP license notice

Runtime choice and model preparation affect latency and memory. A capability recommendation is provisional; an installed-model check is a measurement of that test workload, not a promise for every recording. Quality and release-latency qualification remain separate.

Quiet speech and live preview

Settings → Microphone has an experimental, default-off Whisper mode for quiet speech: gain, AGC, a more sensitive speech-detection profile and optional local GTCRN enhancement. Its name does not select the Whisper ASR model. GTCRN setup is an explicit reviewed download; gain/AGC can be used without enhancement. The owner whispered-speech accuracy target is still unmeasured.

Live preview is another separate Labs model/setup choice. Its current model is English-specific. In quiet-speech mode, live partials keep their original signal while enhanced primary recognition supplies final text.

See styles for cleanup control and credits for the full attribution boundaries.

A few useful answers.

Is a larger download always better?

No. Compatibility, accuracy and speed depend on the language, recording and hardware. The larger decoder candidates have not established a universal improvement, and measured release-latency work remains open.

Are Lite, Standard and Pro subscriptions?

No. They are local hardware/performance profiles in the free, open-source app. Experimental editing needs Pro and its explicitly installed model/runtime.

Sources and further reading