Platform edition

Reson8 for Windows

Reson8 transcription with real-time streaming and custom models, through the Reson8 cloud API or a compatible server.

Version: 1.2.10
Plugin ID: com.typewhisper.reson8
Requirements: TypeWhisper 1.1.0 or newer · Windows 10 or newer · A Reson8 API key

Inside this edition

Speech-to-text through the Reson8 API at api.reson8.dev, or a compatible server you enter
Live text while you speak, streamed over a WebSocket connection
Custom models available to your API key, alongside the default model
Dutch, English, French, German, Italian, Polish, Portuguese, Spanish, Swedish, and Frisian
If streaming fails, the recording is transcribed in a single request instead

Keep Server URL and Authentication header at their defaults unless you use a compatible server; after changing them, select Save settings
Enter your Reson8 API key under API key, select Save settings, then Check connection
Select Refresh custom models to load the custom models available to your key
Choose a Transcription model and, if it appears, select Use selected model

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 Reson8. 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.
Keep Server URL and Authentication header at their defaults unless you use a compatible server; after changing them, select Save settings
Enter your Reson8 API key under API key, select Save settings, then Check connection
Select Refresh custom models to load the custom models available to your key
Choose a Transcription model and, if it appears, select Use selected model
Under Settings > Dictation, select Reson8 as the Provider and choose a Model. A Dictation Only workflow can also use its own transcription model.

Transcription: Dictate a few sentences with Reson8 and check the language, model, and result before you use it for longer recordings.