Voice interaction service with VAD → ASR → LLM → TTS. Real-time streaming for Vietnamese, <900ms latency, barge-in support.
This project is a **Self-Guided AI Audio Tour Agent** that uses AI to provide interactive, voice-enabled guided tours based on your location or interest. It leverages a multimodal agent to narrate historical and cultural insights in real-time for an immersive travel experience.
This Project aims its objectives to multiple foregrounds namely Fun, Entertainment and Education through one app digitally. The application is to provide a gaming environment to the user whilst checking his/her knowledge also. The knowledge will be tested as the application asks you several question about what you want the application to predict…
Add a description, image, and links to the voice-interaction topic page so that developers can more easily learn about it.
To associate your repository with the voice-interaction topic, visit your repo's landing page and select "manage topics."