Fact · Languages and accents
100+languages
VivaDicta's documentation says its Whisper model, which runs locally on the Mac, supports 100+ languages.
Quote found word for word on the live source, last checked October 22, 2026
In the source's own words
“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.”
VivaDicta Documentation: Transcription Models, VivaDicta, n.d., Local Models, Whisper entry.
Open the original- What it measures
- On VivaDicta's transcription models page the Whisper entry sits under Local Models, which the page says run entirely on the Mac. The page gives Whisper's language count in the same entry as its model sizes.
- What it does not show
- The figure is a lower bound printed as 100+, and it is VivaDicta's statement about the Whisper model it offers, with no test set or date. The homepage's 100+ languages appears beside its translation feature, so it is not used as a separate figure. The page's counts for Parakeet, Qwen3-ASR, Canary and Cohere come from models made by others and are not rows for VivaDicta.
In the data
A row of How Many Languages Speech Recognition Supports, as VivaDicta, Whisper models: 100 languages.
- System
- VivaDicta (Whisper models)
- Maker
- VivaDicta
- Kind
- Dictation app
- What is counted
- Languages
- On device
- Yes
- As of
- 2026-10
- Note
- The source prints 100+, a lower bound; 100 is that stated figure.
Source
Used to calculate
- In the languages supported by speech recognition systems dataset, the 127 published figures for “Dictation app” have a median of 49 languages, ranging from 1 to 1,600.
- The languages supported by speech recognition systems dataset holds 279 data points, each a published figure traced to its source.
- The languages supported by speech recognition systems dataset draws on 232 distinct sources.