Go to a github release, copy paste the addons folder to the demo folder. Restart godot editor.
SpeechToText Node has a transcribe which gets a buffer that it transcribes.
CaptureStreamToText - extends SpeechToText and runs transcribe function every 5 seconds.
The transcribe can block the main thread. It should run in about 0.5 seconds every 5 seconds, but check for yourself.
Go to a CaptureStreamToText node, select a Language Model to Download and click Download. You might have to alt tab editor or restart for asset to appear. Then, select language_model property.
Thanks goes to these wonderful people (emoji key):
 Dragos Daian 💻 |
 K. S. Ernest (iFire) Lee 💻 |
This project follows the all-contributors specification. Contributions of any kind welcome!