I’m currently working on functionality that would allow the robot to trigger a specific chain of commands through voice input. I’m running into some limitations with the ASR module and wanted to ask whether there’s a way to access the live audio transcript directly, without going through the full wake-up/conversation mode flow.
Ideally, I’d like the system to simply stream the recognized text locally, without prompting me to connect to the internet or requiring wake-up conversation mode to be enabled. Right now, although streaming is place, it keeps triggering the cloud access loop (asks user to connect to the internet, and changes LED colors), which inhibits my use case
Is this flow customizable in general? Specifically, is there a supported way to communicate with the robot by voice without enabling the full wake-up conversation mode?
For context, I’m using a Unitree G1 EDU+.
I’m currently working on functionality that would allow the robot to trigger a specific chain of commands through voice input. I’m running into some limitations with the ASR module and wanted to ask whether there’s a way to access the live audio transcript directly, without going through the full wake-up/conversation mode flow.
Ideally, I’d like the system to simply stream the recognized text locally, without prompting me to connect to the internet or requiring wake-up conversation mode to be enabled. Right now, although streaming is place, it keeps triggering the cloud access loop (asks user to connect to the internet, and changes LED colors), which inhibits my use case
Is this flow customizable in general? Specifically, is there a supported way to communicate with the robot by voice without enabling the full wake-up conversation mode?
For context, I’m using a Unitree G1 EDU+.