Platform edition

AssemblyAI for Windows

Cloud transcription with AssemblyAI Universal-3.5 Pro or Universal-2, with live text, dictionary terms and optional speaker diarization.

Version: 1.1.4
Plugin ID: com.typewhisper.assemblyai
Requirements: TypeWhisper 1.1.0 or newer · Windows 10 or newer · An AssemblyAI API key

Inside this edition

Cloud speech-to-text with Universal-3.5 Pro (18 languages) or Universal-2 (37 languages)
Live text while you speak through AssemblyAI streaming
With Universal-2, live text covers only English, Spanish, German, French, Portuguese and Italian; with another spoken language set, the recording is transcribed after you stop
Transcription of the full recording when the live connection fails
Automatic language detection or a fixed spoken language
Dictionary terms sent to AssemblyAI as recognition hints
With more than 100 dictionary terms or terms longer than 50 characters, TypeWhisper 1.3 or newer still shows live text and transcribes the complete recording with every term after you stop
Optional speaker diarization with speaker labels in the text, which turns off live text

Set up the add-on and verify its platform-specific capabilities with a first practical workflow.

Roles in TypeWhisper

Transcription

In TypeWhisper, open Settings > Discover plugins and install AssemblyAI. The add-on then appears in the Settings sidebar, and its page opens. If it is already installed, open its page in the sidebar.
On the add-on's page, review the options available in this edition.
Enter your AssemblyAI API key and select Check connection
Choose Universal-3.5 Pro or Universal-2 as the Transcription model
Turn on Speaker diarization only when you need speaker labels
Select Save settings
Under Settings > Dictation, select AssemblyAI as the Provider and choose a Model. A Dictation Only workflow can also use its own transcription model.

Transcription: Dictate a few sentences with AssemblyAI and check the language, model, and result before you use it for longer recordings.