Intellectual Property India Publishes Patent Application for Embedded Artificial Intelligence-Based System For Multi-Lingual Chanting With Real-Time Voice Cloning And Adaptive Sensory Output Thereof

MUMBAI, India, July 30 -- Intellectual Property India has published a patent application (202641086918 A) filed by Karpagam Academy Of Higher Education; Karpagam College Of Engineering; Dr. K. P. Sridhar; Dr. S. Baskar; Dr. C. Prajitha; Dr. S. Deepa; and Dr. S. Nithya on July 16, 2026, for Embedded Artificial Intelligence-Based System For Multi-Lingual Chanting With Real-Time Voice Cloning And Adaptive Sensory Output Thereof.

Inventors include Dr. K. P. Sridhar; Dr. S. Baskar; Dr. C. Prajitha; Dr. S. Deepa; and Dr. S. Nithya.

The application for the patent was published on July 24, 2026, under issue no. 30/2026.

Abstract: The present invention discloses an artificial intelligence (AI)-driven, embedded audio chanting system configured for adaptive, multi-lingual rendering of Vedic scriptures and classical textual content. The system comprises a pre-recorded storage module (100) storing structured datasets of Rig Veda, Yajur Veda, Sama Veda, Atharva Veda, and Thirukkural couplets, operatively coupled to a Raspberry Pi-based processing unit (101) for dynamic content retrieval and control. A hybrid input interface including a selector switch (102) and a voice command module (103) enables both manual and natural language interaction. An ESP32-based AI module (104) is configured to perform real-time voice recognition, speaker profiling, and voice cloning to synthesize chanting output in a user-specific vocal signature, thereby enabling personalized audio generation across multiple languages. The voice-modulated chanting engine dynamically modifies phonetic rendering and prosodic elements depending on linguistic and user-defined factors. A speaker unit (105) and a frequency-responsive lighting display (106) that maps visual patterns to chanting frequency, volume, and modulation via a 3.5-inch TFT interface (107), provide a synchronized audio-visual feedback subsystem. Option converter switch (108) automates consecutive Thirukkural couplet playback with contextual explanation. The invention is characterized by the integration of real-time voice cloning, multi- lingual phonetic adaptation, and synchronized sensory feedback within a compact embedded architecture, thereby overcoming limitations of static, non-adaptive prior art chanting systems.

Disclaimer: Curated by HT Syndication.