India Brings 65 Cultural Portals Into One AI-Powered Search Platform
The Culture Ministry’s new conversational search tool aims to make archives, manuscripts and heritage records easier to explore in 22 Indian languages, with voice features and links to official sources.
India’s cultural records are spread across archives, manuscript repositories, museum collections and specialist websites. The Ministry of Culture has introduced an artificial-intelligence search platform intended to make that material easier to discover through a single conversational interface, with support for 22 scheduled Indian languages.
The platform was launched on the Ministry’s primary digital portal by Culture Secretary Vivek Aggarwal on 16 November 2026. Government and public broadcaster accounts say it brings together information from more than 65 websites operated by the Ministry and its institutions. The initiative is designed to help students, researchers and members of the public find authoritative material without having to know which portal holds a particular record.
One search interface for a scattered heritage archive
The Ministry’s digital estate includes resources covering manuscripts, archival documents, museums, monuments, art forms and cultural programmes. Until now, users often had to know which individual portal to search. The new interface is intended to reduce that friction by interpreting questions expressed in ordinary language and retrieving relevant material across the connected websites.
According to the launch coverage, the system uses semantic search techniques rather than relying only on exact keyword matches. Its conversational assistant can present a consolidated response and link information back to source pages. That source trail matters: cultural and historical research depends on being able to inspect the underlying record, not simply accept a generated summary.
Language and voice access are central features
The platform has been developed with the government’s BHASHINI language technology initiative. The Ministry says it supports all 22 scheduled Indian languages and includes voice input and text-to-speech capabilities. These features could make digital collections more approachable for people who are less comfortable searching in English or navigating multiple specialist websites.
The language support is particularly relevant to heritage material, where source records and research interests may involve regional languages, local histories and different scripts. A common search layer could help users discover material that might otherwise remain difficult to locate. The stated language coverage is a platform capability announced at launch; its practical quality will depend on how well individual queries, translations and source records perform.
Why source links and accuracy will matter
AI-assisted discovery can make large collections easier to navigate, but it also introduces familiar risks. A search assistant may misread an ambiguous question, overlook a relevant document or summarise a record without enough context. For historians and students, a concise answer is only a starting point. The original archive entry, catalogue description or digitised document remains the evidence that should be checked.
The Ministry’s emphasis on references to official source pages is therefore an important design feature. Users should follow those references before citing a result in academic work, journalism or public communication. The platform’s usefulness will also depend on the completeness, metadata quality and continued maintenance of the websites it connects.
What happens next
The launch creates a shared discovery layer over a large set of government cultural resources. Its longer-term value will be measured by whether people can reliably find records that were previously hard to locate, whether multilingual and voice interactions work consistently, and whether citations lead directly to useful source material. Wider access to heritage information is a meaningful goal, but the quality of the underlying collections and the transparency of AI-generated answers will determine how much researchers and the public can trust it.
For now, Sanskriti represents a practical attempt to bring dispersed cultural information into one search experience. Researchers should treat its responses as guided routes into the Ministry’s collections, then verify important claims against the linked primary records.
Sources
Written with automated tools from the sources above and published without editor review. Spotted an error? Tell us · Corrections Policy
Related stories

Google Brings Gemini Computer Use to Mac, Letting Its AI Handle Multi-Step Desktop Tasks
Google has added computer-use capabilities to its Gemini app for Mac, allowing the assistant to navigate selected desktop apps, local files and websites in a separate window. The English-language rollout is initially limited to the United States.

A leaner 5G connection moves closer to everyday sensors and wearables
Ericsson and Altair Semiconductor say they have completed the first eRedCap network connection, a step towards lower-cost, lower-power 5G devices for sensors, trackers and connected wearables.

Small Businesses Get an AI Campaign Assistant as InMobi Unveils Accelerate
InMobi has introduced a self-serve advertising platform that uses seven specialised AI agents to help small businesses and agencies plan, build and optimise campaigns across major ad networks from one dashboard. Advertisers retain approval control over campaign plans, creatives and budgets.

India's BHASHINI and NIELIT team up to bring multilingual AI into technical learning
A new agreement between BHASHINI and NIELIT will explore using AI translation and speech tools across technical courses and digital learning, helping more students access technology education in Indian languages.
