Official documentation
VivaDicta Documentation: Transcription Models
VivaDicta, n.d.
Read the originalRead on October 22, 2026
- What it is
- VivaDicta's own documentation page on the transcription models it offers, split into local models that run on the Mac and cloud services that receive the audio. It gives the language coverage of each local model, including a figure for its Whisper model.
- How much weight it carries
- Published by VivaDicta, the maker of the app, and describes what the app offers, so it is the right source for that. The page gives no date and no test set for its language figures, and it does not say whether the 100+ figure counts regional variants.
Facts taken from this source
- VivaDicta's documentation says its Whisper model, which runs locally on the Mac, supports 100+ languages.
“OpenAI's Whisper model running locally on your Mac. Multiple model sizes: Tiny, Base, Small, Medium, Large, Large Turbo. Larger models are more accurate but require more RAM and processing time. Best on Apple Silicon Macs (M1 and later). Supports 100+ languages.” (Local Models, Whisper entry)