Welcome to Muto RS Robot repository
1.Semantic Understanding, Instruction Following
Semantic Understanding & Instruction Following
Semantic Understanding & Instruction FollowingIntroductionStepsPrerequisitesGetting StartedVoice Version Large Model Interaction Guide
Introduction
In this tutorial, we will learn how to give instructions by chatting with Muto in the Dify interface.
Steps
Prerequisites
For this course, you need to start the Dify terminal in advance and have all the configuration items set up according to the previous chapters.



This course requires MutoRS to be powered on. Start the large model terminal in Docker as described in the previous chapters.


In this tutorial, we use the voice version of the large model. Do not include any parameters when starting it.
cd muto-llm-2.0/ && ./rebuild_and_launch.sh

Getting Started
Voice Version Large Model Interaction Guide
When we see the content in the red box as shown in the image above, it means our large model terminal has started successfully.
At this point, we can use the wake-up word "Hi, yahboom" or "hello yahboom" to activate it.
After successful activation, we can hear Muto's response "Hello~", and see the terminal output the following content:

Then we will hear a crisp "bee" sound from the buzzer. About one second after hearing the buzzer, we can start interacting with Muto.
The interaction flow for the voice version is as follows:
User wakes up ----> Muto receives the wake-up word and enables VAD recording ----> VAD recording ends ----> The recorded audio is converted to text via the cloud platform ----> The text is sent to the Dify backend for processing ----> Dify receives the text, understands, plans tasks, and attempts execution ----> The result is announced ----> Enters the state of waiting for the next wake-up word.
- Therefore, you need to ensure that the configured Bailian / iFLYTEK API is correct. Otherwise, you may encounter issues where speech cannot be recognized or Muto's speech cannot be converted to voice output (international users use the iFLYTEK model by default and do not need to configure it themselves).
Use voice input to say, “My name is Xiao ming. Please remember my name.”
In the next round after waking it up, say, “Do you still remember me?”
You can see that Muto has given a response.

