Prepare
Download and choose a local model
Install a local recognition model before starting microphone, desktop, or file transcription.
Speech to Text requires an installed local recognition model before microphone, desktop, or file transcription can begin.
Follow these steps
- 01
Open Provider connections and select the Speech to Text tab.
- 02
Review each model’s size and expected performance, then download the model suited to your device.
- 03
Wait for the download and verification to complete before opening Speech to Text.
- 04
Select the installed model and the language spoken in the recording.