Choose speech models and languages

Veura lets you choose the transcription engine that fits your language, storage, speed, and accuracy needs. Downloaded model files remain on the device.

Updated 2026-11-118 min readPlain Markdown

Compare the models

ModelBest fitDisplayed download
Apple SpeechBuilt into iOS; language availability is managed by the systemSystem managed
Whisper TinyQuick dictation and lower device loadAbout 75 MB
Whisper BaseBetter accuracy for longer or noisy recordings148 MB
Whisper SmallHighest Whisper accuracy offered in Veura, with more processing487 MB
ParakeetMultilingual Core ML model optimized for Apple chipsAbout 2.58 GB
ParakeetV2English-optimized Core ML model with stronger recallAbout 2.58 GB
Veura model manager showing Apple Speech, Whisper, Parakeet, sizes, and licenses
The model manager shows download size, license, readiness, and the currently selected model.

Language behavior

  • Apple Speech uses supported languages installed through iOS and does not offer automatic language detection in Veura.
  • Whisper and Parakeet can use automatic detection where the model supports it.
  • ParakeetV2 is English only and forces English as the transcription language.
  • A note records its selected or detected language for later inspection and webhook delivery.

Choose a quality mode

ModeBehavior
AutoUses duration and language to choose speed versus quality
BalancedFaster transcription with lower battery use
Balanced+Better accuracy at moderate speed
Max QualityBest accuracy, with slower processing and higher battery use

Reprocess saved audio

When a note still has saved audio, open Reprocess and choose another ready model or language. Veura keeps the previous text as the original transcript while the new result becomes the working note text. Generated variants are reset when the source transcript changes.

Model licenses

Whisper model support is shown with the MIT license. Parakeet models are shown with CC BY 4.0 and require attribution. Veura includes third-party notices in Settings; review linked model terms before distributing a modified build.