Connect to the OBS WebSocket Server

Enter IP address or "localhost": Enter Port Number: Enter Password:

Choose an Audio and/or Video Source

Desktop Window (Video)
Microphone (Choose Microphone in Chrome Settings: chrome://settings/content/microphone)

Audio Frequency Analysis

Enter Frames Per Second:

Enter the name of peerConnections Enter the number of peerConnections

https://github.com/luser/gamepadtest

Press a button on your controller to start

Enter OBS Text Source Name:

Classifying text with the MediaPipe Text Classifier Task

This demo listens for event {speechToText}, then runs sentiment analysis. The result shows how likely the input text is to have a positive or negative sentiment.

Input:

CLASSIFY

Sentiment:

Text-to-Text large language model

Gemma 2B is a part of a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. The model contains 2B parameters and open weights. This model is well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. https://developers.google.com/mediapipe/solutions/genai/llm_inference
Gemma formatting and system instructions
Input:
example format
<start_of_turn>user
Some question?<end_of_turn>
<start_of_turn>model



Result:

Mouse coordinates

PTZ coordinates