Check your model first
Changing the model has the largest effect on accuracy. Models are on the Speech models page in the sidebar.
See Speech models.
Dictionary words have no effect
Whether your Dictionary changes what the model hears depends on the engine. These models receive no vocabulary at all:- Whisper Tiny and Base, including the English versions
- Parakeet, every version, on macOS and Windows
- Nemotron EN and Nemotron Multilingual
- Cohere Transcribe
1
Add misspellings to the Dictionary word
A misspelling is replaced with the correct spelling after transcription. See Dictionary.
2
Add a Thread
A Thread replaces a phrase with fixed text every time. Triggers match whole phrases, so a
sig thread does not rewrite the middle of “design”. See Threads.3
Turn on AI enhancement
AI enhancement receives your Dictionary as context and fixes words the model got wrong. This is the most effective fix on Parakeet and Nemotron. Turn it on in Language models › Configuration › Enhance transcription with AI.
4
Switch to an engine that uses your Dictionary
Moving from Whisper Tiny or Base to Whisper Small is the smallest change that turns vocabulary on. For the strongest effect, use Deepgram Nova 3, AssemblyAI, ElevenLabs Scribe v2, Speechmatics or Gemini
gemini-3.5-transcribe.Set your language
Auto-detect sometimes picks the wrong language, and a wrong-language transcript is far worse than a weaker model.- Open Settings › Language.
- Next to Dictation Language, click Change and pick your language.
Turn on AI enhancement
AI enhancement fixes most remaining errors and receives your Dictionary as context. Turn it on in Language models › Configuration › Enhance transcription with AI. If no AI provider is connected, you see a locked card with Connect an AI provider instead of the toggle. See AI enhancement.Specific issues
Words get mixed up when I speak fast
Words get mixed up when I speak fast
- Slow down slightly. Fast speech is harder for every model.
- Switch to a cloud model. Deepgram Nova 3 and ElevenLabs Scribe v2 handle fast speech well.
- On local Whisper, move up a size.
Technical terms are misspelled
Technical terms are misspelled
Check your engine first. See Dictionary words have no effect.
- Whisper Tiny or Base, Parakeet, Nemotron or Cohere: use misspellings, a Thread or AI enhancement, or switch engines.
- An engine that uses your Dictionary well: add the terms in Dictionary.
- Local Whisper Small or larger, or Groq: add them to the Dictionary. They are sent as a hint, which helps less.
Non-English accuracy is poor
Non-English accuracy is poor
- Use a multilingual model. Whisper English sizes, Parakeet V2, Phonon-2 and Nemotron EN are English only.
- Set the language instead of relying on auto-detect.
- Parakeet V3 and Parakeet Ultra cover 25 European languages. Cohere Transcribe covers 14 languages on a Mac.
- Parakeet Japanese and Parakeet Mandarin are dedicated Mac models.
- For Indian languages, use Saaras v3 (Sarvam AI).
- Whisper Large v3 covers 99 languages.
The output repeats or loops
The output repeats or loops
Repetition happens most on smaller models.
- Use Retry transcript on the History entry to run the saved audio through a different model.
- Move up a model size, or to a cloud model.
- AI enhancement removes repetitions.
Random 'Thank you' or invented text
Random 'Thank you' or invented text
Whisper models can invent text over silence, most often “thank you”.
- Start speaking as soon as you press the shortcut.
- Vowen already drops local results that are exactly “thank you”, “thank you.”, ”.” or a lone period with a line break.
-
For cloud models, turn on Settings › Experimental › Enhanced silence detection. A Sensitivity slider from 1 to 5 appears, set to 2 by default.

Only the first word, or a lone period, comes through
Only the first word, or a lone period, comes through
The recording was probably too short.
- Hold the shortcut for the whole time you speak, or set the shortcut to Tap in Settings › Shortcuts.
- Parakeet needs at least 300 ms of audio. Anything shorter is discarded with no error and no History entry.
- Check that the app you are typing in is not taking the shortcut. See Shortcut issues.
The first or last word is missing
The first or last word is missing
See First or last word cut off. Use Retry transcript on the History entry to check: it always re-reads your original recording.
Spacing or capitals are wrong around the inserted text
Spacing or capitals are wrong around the inserted text
Smart spacing and capitalization matches your dictation to the text around the cursor. When Vowen can’t read that text reliably, it inserts the dictation as spoken. Check that Settings › General › Smart Spacing and Capitalization is on. It is off by default. See Smart spacing and capitalization.
American instead of British spelling
American instead of British spelling
Set Settings › Language › English Spelling to British English. You don’t need an AI instruction for it.
Recommended setups
Mac, fully local transcription:- Speech: Parakeet Ultra, or Nemotron EN for a punctuated live preview.
- AI enhancement: any connected provider. Gemini 3.8 Flash is Google’s recommended model.
- Speech: Parakeet V2 or V3 locally, or Whisper Large v3 Turbo on Groq.
- AI enhancement: Gemini 3.8 Flash.
- Speech: ElevenLabs Scribe v2, AssemblyAI Universal-3.5 Pro, Deepgram Nova 3 or Gemini
gemini-3.5-transcribe. All of them use your Dictionary well. - AI enhancement: Claude Sonnet 4.6 or GPT-5.4.