Text/Voice Input
- This topic has 2 replies, 2 voices, and was last updated 1 week ago by
.
-
Posts
-
We want to implement semantic interactions (like a chatbot). We see there is a way to display dynamic text, but is there a way to input text and/or voice (via a microphone)?
Currently not. If I understand you correctly, you would like to have an audio recorder which can stream the audio input to a speech-to-text AI which then passes this on to a LLM AI which can answer (as text or again as audio). Correct?
On our ToDo-List there is actually a similar setup planned for controlling the World Builder (Assistant) and, when done, we could open this feature to you in the form of a node or nodes in the Logic Editor.
Sometime early next year, we are also planning to finalize the dynamic scripting feature where you can add your own scripts and/or Nodes to the World Builder. This would enable to program a Node which does exactly what you want to do.
Yes, that’s correct. Integrating an audio recorder to stream input to a speech-to-text AI, which then passes it to an LLM for responses (in text or audio), is our goal.
Your proposal to enable this via a Logic Editor node and the upcoming dynamic scripting feature is nice. Looking forward to those updates!
- You must be logged in to reply to this topic.