Every sound ever made on BEL is still here. The crystals keep it: wind, thunder, the voices of a crew that landed once and left. Listen long enough and you’ll hear yourself, a few seconds before you speak.
Class
Desert world with forests of silica crystal
Population
Unknown
Covers
Voice AI: the conversational avatar, BHAVA, the AI voice detector
Conversational AI avatar
An empathetic talking avatar for officer wellness support that runs entirely offline.
Built a multimodal pipeline for Bengaluru Police: speech synthesis (F5-TTS) plus video generation produce a realistic talking avatar.
Runs LLaMA 3 locally through Ollama, so sensitive officer data never leaves the machine, with sub-second responses.
Zero-shot voice cloning and lip-sync (SadTalker / Wav2Lip) turn the model’s text into matched audio and video.
A Gradio interface manages the whole path from typed input to a rendered digital human on local hardware.
This world is still being surveyed. The ship is open now.