Documentation Index
Fetch the complete documentation index at: https://docs.vowen.ai/llms.txt
Use this file to discover all available pages before exploring further.
Pro tip: The fastest path to high accuracy is pairing a cloud STT model (Groq Whisper Large v3 is free) with AI Enhancement, then adding the words you say most to your Dictionary. The cloud model handles fast or accented speech, AI Enhancement cleans the rest, and Dictionary keeps domain terms spelled correctly.
Choose the Right Model
The single biggest factor in transcription accuracy is your model choice. See the Models Guide for detailed comparisons. Quick rule of thumb:- For English, Base.en or Parakeet gives good everyday accuracy
- For professional work, use Large v3 Turbo or a cloud model
- For non-English, use the multilingual Large v3 or Groq
Microphone Tips
- Use a dedicated microphone when possible. Even basic earbuds are better than laptop mics at a distance.
- Minimize background noise. Vowen has noise suppression, but a quieter environment helps.
- Keep consistent distance from your microphone.
- Check your input device in Settings > Audio to make sure the right mic is selected.
Speaking Tips
- Speak at a natural pace. Rushing can cause words to blend together.
- Pause briefly before and after speaking. This prevents the first and last words from being cut off.
- Enunciate clearly for technical terms or unusual names.
- Say punctuation explicitly if needed: “period”, “comma”, “new line”. With AI enhancement, punctuation is added automatically.
Use Custom Vocabulary
Add frequently-used terms that the model might get wrong. See the full guide in Dictionary & Vocabulary.- Go to Settings > Dictionary
- Add product names, technical jargon, proper nouns, and acronyms
- The model uses these as hints during transcription
Use Threads for Long-Form Phrases
If you find yourself dictating the same long phrase over and over (a university name, a mailing address, a signature, a project tag), set it up as a Thread. Speak a short trigger and Vowen inserts the full text in your transcription. See the full guide in Threads (Snippets).- Go to Settings > Dictionary > Threads
- Add a trigger (what you say) and replacement (what gets inserted)
- Examples:
- Say “my university” → Vowen inserts “Stanford University, Stanford, CA”
- Say “my mailing address” → Vowen inserts “1234 Example Street, Sample City, ST 00000”
Enable AI Enhancement
For polished output, enable AI Enhancement in Settings > Recording > Enhance with AI. This:- Fixes remaining spelling and grammar issues
- Adds proper punctuation and capitalization
- Formats numbers correctly (e.g., “three thousand” becomes “3000”)
- Detects and applies spoken commands like “new paragraph”
Filler Word Removal
Vowen automatically strips filler words like “um”, “uh”, “like”, and “you know” from transcriptions before they reach AI Enhancement. This is on by default and works whether or not you have an AI provider connected. Toggle it in Settings > General > Remove filler words.Running into accuracy issues? See the Accuracy FAQ.