Jev Gallery
← Back to collection

Docs / source reviewed

Vox Arcana

Turn spoken incantations into elemental spells for a magic duel

How this project uses Jev

Input
A browser speech-recognition transcript or typed incantation, plus the recognition language; Jev receives text rather than raw audio
Jev decides
Choice selects elements, shape and traits; Noul evaluates spell intent and homing; Score describes strength parameters
Code executes
Game code maps structured parameters into spells and combat effects, with practice and battle modes; repeated text decisions are cached

Evidence and limitations

MIT source and the Jev request path were reviewed without installation or paid model calls. Voice input depends on browser speech recognition and microphone permission; text is sent to a model service. Local parsing is a separate mode, not evidence of Jev performance. Third-party art and audio have separate notices.

This project has not been run independently here. Author-reported results are not independently verified results.

Original sources

Explore related use cases

Browse this category →

Learn the approach