Centre to Deploy AI to Digitise Over One Crore Ancient Manuscripts

India's Ministry of Culture will deploy artificial intelligence and machine learning frameworks to decipher, digitise, and conserve more than one crore ancient manuscripts across the country. The extensive preservation drive forms a foundational component of the government's flagship Gyan Bharatam initiative, originally introduced in the 2025 Union Budget. The Standing Finance Committee sanctioned an allocation of 491.66 crore rupees to finance the comprehensive manuscript digitization mission across the 2025 to 2031 operational period. The central initiative focuses on creating a National Digital Repository designed to provide public access to ancient texts through intuitive voice and text-based query systems. A signature feature of the platform will include an interactive Talk-to-Manuscript utility, enabling researchers to explore specific philosophical domains and individual archival documents.

Text Recognition Capabilities and Provenance Analysis

Technical execution will leverage advanced Optical Character Recognition and Handwritten Text Recognition systems to convert fragile historical scripts into searchable digital formats. The digitization methodology preserves original manuscript structural elements, maintaining section headers, marginal glosses, and traditional artistic illustrations intact. Government officials disclosed that the ministry is actively engaging an external technology partner to engineer the underlying artificial intelligence platform. The computational algorithms will automatically transcribe handwritten scripts, generate multilingual translations, and assist in identifying anonymous historical authors. Machine learning models will also establish archival provenance, reconstruct damaged or faded script lines, and discover thematic connections between fragmented institutional holdings.

Physical Conservation Labs and Grassroots Volunteer Network

The ministry mandated that all algorithmically generated analytical answers must link directly to authenticated manuscript records through page-level citations and verbatim excerpts. More than 1.25 crore manuscripts recorded in multiple classical and regional languages have already been catalogued on the Gyan Bharatam digital portal. Out of that catalogued volume, project teams have already processed and published approximately 11.53 lakh manuscripts for public research review. Archival materials originate from diverse repositories, including state government archives, academic university libraries, religious trusts, and private family collections. The historical texts encompass varied preservation states, ranging from fragile to well-preserved archival folios. Gyan Bharatam's roadmap focuses on national and international collaborations by establishing Cluster Centres, Independent Centres, and Centres of Eminence, according to Ministry of Culture. During the National Manuscript Survey launched across all States and Union Territories, more than 1.19 crore manuscripts were reported.

To support long-term physical conservation alongside digital scanning, the ministry proposed establishing specialized preservation laboratories. These dedicated facilities will focus on stabilizing delicate substrates, including palm leaf strips, Himalayan birch bark sheets, and handmade papers. The government also plans to cultivate a grassroots capacity-building network termed Pandulipi Mitras, translating to manuscript friends, across roughly 100 districts. Trained district volunteers will support local surveys, identify uncatalogued private collections, and coordinate preservation assistance with regional owners. The deployment of modern artificial intelligence tools represents a transformative step in safeguarding India's extensive textual heritage for global scholarship.