Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195443,
        author = {Falak khan and Dr. Amol Joglekar},
        title = {SuchanaSaathi: A Multimodal AI Framework for Accessible Understanding of Government Schemes Using OCR, STT, TTS, and Translation.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {810-818},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195443},
        abstract = {India is a country with a literacy rate of approximately 80-81%. That leaves the illiteracy rate of around 19-20%. This section of the society deals with various challenges when it comes to reading and writing. The government of India has published various schemes and programs in order to help the underprivileged people. But most of the underprivileged people lack basic education which is why people are not able to access these programs and schemes from the existing portals because language barriers. People in these areas struggle with language comprehension, digital literacy and complex documentation when they try to use the government portal for accessing these schemes. This paper is about a system called SuchanaSaathi. SuchanaSaathi is a program that helps people find out about various government schemes. It uses different tools to do this. SuchanaSaathi uses Optical Character Recognition (OCR) to read text from papers and pamphlets. It also uses Neural Machine Translation so it can understand and talk to people in regional languages. SuchanaSaathi has a feature that reads text out to people, which is called Text-to-Speech. This is really helpful for people who cannot read or who prefer to listen. SuchanaSaathi also has a feature called Speech-to-Text that lets people talk to it and ask for help. The system looks at the person's information. Then gives them advice on which government schemes they might be eligible for. SuchanaSaathi does this with a part of the system called the eligibility detection module. This module makes sure that the advice given to people is just right, for them and their situation. Designed to operate efficiently on low-resource devices, the framework enhances accessibility for citizens regardless of literacy or linguistic background. By harmonizing vision, speech, and language technologies, SuchanaSaathi promotes inclusive and citizen-centric governance through equitable digital participation.},
        keywords = {Multimodal AI, Optical Character Recognition (OCR), Speech-to-Text (STT), Text-to-Speech (TTS), Neural Machine Translation (NMT), Eligibility Detection, Digital Inclusion, e-Governance, Public Service Delivery},
        month = {April},
        }