Fact · Dictation software
Blurt's product page says there is no local model to load.
Quote found word for word on the live source, last checked October 20, 2026
In the source's own words
“Transcription lands in about 150 ms, cleanup in under a second. No local model to load, no job queue to poll.”
Blurt by AssemblyAI: Voice to text, wherever you want it, AssemblyAI, AssemblyAI, 2026, Thoughts to text in milliseconds.
Open the original- What it measures
- The sentence is a speed claim in the feature block Thoughts to text in milliseconds.
- What it does not show
- The page does not use the words not offline. The FAQ says Blurt runs on the AssemblyAI Dictation API, so transcription needs that service.
In the data
A row of Dictation App Features Compared: Offline, Privacy, AI, as Blurt: no local model: 0 1 = yes, 0 = no.
- App
- Blurt
- Feature
- Works offline
- Detail
- Needs the AssemblyAI API
- As of
- 2026-10
- Note
- 0 means the maker's page says it does not