Integrates spatial audio and speech processing into XR Blocks applications.
npx skills add https://github.com/google/xrblocks --skill xb-sound
Please help me install this Agent Skill. Skill: xb-sound Source: https://github.com/google/xrblocks/tree/main/skills/xb-sound Command: npx skills add https://github.com/google/xrblocks --skill xb-sound
This Skill simplifies the integration of spatial audio and speech processing capabilities into XR Blocks applications, enabling developers to create immersive and interactive audio experiences.
Use the xb-sound skill to play a spatial audio file in your XR Blocks app and capture voice input from the user.
High-intent search queries and answers about installing and using this skill.
To add spatial audio to an XR Blocks app, use this Skill to play and capture audio in 3D space, anchoring positional audio outputs directly to scene objects. It simplifies integrating immersive audio environments into your applications.
Yes, you can implement speech recognition in XR Blocks. This Skill provides speech-to-text functionality, enabling voice interaction features and voice-controlled character movements by utilizing TensorFlow Lite or PyTorch for recognition processing.
Yes, you need TensorFlow Lite or PyTorch for speech processing in XR Blocks. These frameworks are required alongside the XR Blocks framework to handle underlying gestures and speech recognition capabilities.
The best way to record microphone input for an immersive XR experience is using this Skill's microphone recording and playback capabilities. It allows capturing user audio and integrating it directly into your spatial environment.
You control master volume in XR Blocks applications through the provided master volume control feature. This allows adjusting the overall volume of audio output across your spatial audio environment.
Yes, XR Blocks supports text-to-speech synthesis for voice interaction. This Skill implements speech synthesis functionality, allowing generation of voice outputs and creation of interactive audio experiences within your application.
googleLoad and display GLTF, GLB, and .spz 3D models in XR Blocks applications.
googleExtract semantic trees and visible-object states from XR scenes.
googleDesign interactive 3D user interfaces for XR Blocks with Three.js and uikit.
softweekTranscribe and translate local audio files using the Whisper CLI.
