Free, open-source dictation
Vietnamese
voice typing for Windows.
Tiếng Việt
Draft Vietnamese text with your voice on Windows while keeping speech recognition local. Saydraft uses the installed All languages model for Vietnamese dictation.
Choose Vietnamese, language code vi, in Languages. A single pin supplies a Vietnamese hint to the model. You can pin it with English or another supported language; multiple pins let the same model detect the language.
Requires the shared All languages speech model (Whisper large-v3-turbo, approximately 1,621.7 MB). Download once in setup or Models, then reuse it offline.
How to set up Vietnamese dictation
- Follow the current download and source setup instructions. Saydraft is a development preview for Windows 10 and 11.
- In Hub → Settings → Models, review the required model’s size and license. Choose Download / Resume if it is missing; Pause is available.
- Open Languages, enable automatic model choice, and select Vietnamese. Save your settings. A single language pin uses code
vi. - Put the cursor in an editable app field, hold Ctrl + Win, speak, then release. Review the transcript before sending it.
Language selection starts no transfer. If automatic routing is off, the model selected on Models remains in use; select a compatible model there. For more detail, see the setup guide.
Use your voice in everyday Windows apps
Use Vietnamese dictation for a message, a note or a document draft. Tone marks and vowel marks can change meaning, so review spelling, names and numbers in the result. The app does not offer a separate model setting for each regional accent.
Speech recognition and text cleanup run locally. There is no account or cloud transcription fallback. With compatible models installed, you can dictate without an internet connection. Optional AI cleanup has its own model requirements; rules-only cleanup needs no text model.
Are Vietnamese tone marks preserved?
The model produces Unicode text, including Vietnamese diacritics, rather than plain ASCII transliteration. Correct tone marks still depend on recognition quality. Review the output before sending, especially names and words that differ only by a tone mark.
What does language support mean here?
This page describes speech-model coverage and app configuration. It does not claim a measured accuracy score for Vietnamese. Accent, microphone, background noise and mixed speech affect results. The language choice does not translate the app interface or add Translate-mode output targets.