Indian Flag
Government Of India
A-
A
A+

AI Accessibility Ecosystem: Jyoti AI, Shruti AI & Vaani AI for Inclusive Education, Communication and Independent Living

The AI Accessibility Ecosystem developed by Torchit Electronics integrates three AI-powered assistive solutions, Jyoti AI, Shruti AI, and Vaani AI, to support persons with visual, hearing, and speech impairments.

About Use Case

The AI Accessibility Ecosystem developed by Torchit Electronics addresses the diverse accessibility challenges faced by persons with disabilities, particularly in developing economies. Individuals with visual, hearing, or speech impairments often encounter barriers that limit their access to education, employment, and public services. Printed materials remain inaccessible to many visually impaired individuals, communication barriers persist for people with hearing impairments due to limited availability of sign language interpretation, and individuals with speech impairments often struggle to express themselves without specialized communication tools.

To address these challenges, Torchit created an integrated AI ecosystem consisting of three complementary solutions: Jyoti AI, Shruti AI, and Vaani AI. Each solution targets a specific disability while remaining part of a unified accessibility platform designed for deployment in educational institutions, workplaces, and community environments.

Jyoti AI focuses on assisting individuals with visual impairments or print disabilities. The system includes devices such as Jyoti AI Smart Glass and Jyoti AI Reader, which use computer vision and optical character recognition technologies to convert printed or digital text into spoken audio. These tools allow users to read textbooks, forms, medicine labels, and workplace documents independently. In addition to document reading, Jyoti AI also provides scene understanding and navigation cues that help visually impaired users interpret their surroundings.

Shruti AI is designed for individuals who are deaf or hard of hearing. The solution uses artificial intelligence to translate spoken language into Indian Sign Language representations. The model has been trained on thousands of commonly used words and phrases relevant to education, healthcare, and public services. By enabling real-time voice-to-sign translation, Shruti AI helps bridge communication gaps in classrooms, hospitals, government offices, and workplaces.

Vaani AI supports individuals with autism and speech impairments who require Augmentative and Alternative Communication (AAC) tools. The system allows users to communicate their needs and intentions through AI-assisted prompts and predictive communication features. Vaani AI can suggest phrases based on context such as location or time of day, enabling users to express themselves more effectively with caregivers, teachers, and service providers.

The ecosystem has been deployed through partnerships with NGOs, educational institutions, training centers, and government-supported programs. Implementation includes onboarding sessions for persons with disabilities, caregivers, and educators, as well as ongoing support and helpline services. The solutions are designed to function effectively in low-resource environments, emphasizing affordability, multilingual capabilities, and minimal infrastructure requirements.

Torchit’s ecosystem also emphasizes responsible AI practices. The systems incorporate privacy safeguards, user consent mechanisms, and bias mitigation strategies. Training datasets include diverse linguistic inputs to ensure relevance across Indian languages and contexts. Continuous feedback from users and educators helps refine the models and improve accuracy over time.

By combining AI-powered solutions for visual assistance, sign language translation, and augmentative communication, the Torchit ecosystem provides a comprehensive accessibility framework. The approach reduces fragmentation in assistive technologies and allows governments, NGOs, and institutions to deploy scalable solutions that address multiple disability needs simultaneously.

Overall, the AI Accessibility Ecosystem demonstrates how integrated AI technologies can significantly improve participation of persons with disabilities in education, communication, employment, and daily life. Through scalable deployment and user-centered design, the platform offers a practical model for inclusive AI adoption in emerging economies.

For additional context and detailed documentation of this use case, please refer to pages 37-39 in the attached Casebook.

Source Organization Source Organization

IndiaAI

Tags Tags

  • Accessibility

Tags Sector

Education and Skill Development

Resources Resources

External Resources:

Related Datasets Related Datasets

Updated 10 month(s) ago
VAANI: Multi-modal, Multi-lingual Dataset
VAANI: Multi-modal, Multi-lingual Dataset
Information-
VAANI is a multi-modal, multi-lingual dataset designed to represent the rich linguistic diversity of India. It currently includes data from two phases—Phase 1 (80 districts) and Phase 2 (40 districts)—spanning a total of ~21,500 hours of spontaneous, image-prompted speech collected from more than 110K speakers across 120 districts, describing 210K images in 86 languages. From this, 835 hours of transcribed audio data is available, distributed nearly evenly across all 120 districts.
Bengali
Gujarati
Kannada
Nepali
Punjabi
Telugu
Urdu
Sindhi
English
Tamil
Low-Resource Languages
Marathi
Malayalam
Odia
speech transcription
spontaneous speech
Sangtam
Ao
Halbi
Malvi
Sadri
Chhattisgarhi
Bhili
Malvani
multilingual corpus
Sumi
Bagheli
Khorth
Nyishi
multimodal dataset
Shekhawati
Bagri
Mewati
Meitei
86 Indian languages
Surgujia
audio-visual dataset
Garo
MagadhiMagahi
TTS training
Wancho
Awadhi
Galo
Oriya
speech + image + text
Tenyidie
regional dialects
Rajbanshi
Nagamese
manual transcription
Thethi
LLM speech integration
KhorthKhotta
Konkani
quality evaluated
speaker identification
diverse demographics
telemedicine AI applications
Marwadi
speaker diversity
Tulu
Assamese
Harauti
Rajasthani
language identification
120+ districts
Tagin
Marwari
Gondi
Bajjika
22 Indian states
Surjapuri
dialect diversity
Kokborok
image-prompted data
Santali
speech enhancement
Khariboli
Rengma
geo-centric data collection
Hajong
Hindi
ASR training
Wagdi
Bhatri
Dorli
multi-modal language resources
reallife recording environments
Mewari
linguistic diversity
Nimadi
Khandeshi
data for conversational AI
benchmarking dataset
Lotha
Kurmali
Bhojpuri
NissiDafla
Angika
Lambani
Magahi
Jaipuri
Bihari
Chakhesang
Magadhi
Angami
Chakma
Duruwa
Bearybashe
Khortha
Kumaoni
Kurukh
Garhwali
Maithili
Agariya
Bundeli
large-scale speech corpus
  • See Upvoters1
  • Downloads131
  • File Size0
  • Views1,267

INDIAN INSTITUTE OF SCIENCE (IISC), BANGALORE