Eka Care builds India’s first offline-capable, unified medical scribe model using NVIDIA AI

Eka Care, a leader in AI-led digital health and connected care, announced that it will collaborate with NVIDIA to develop a next-generation medical scribe for doctors. This initiative will help Eka Care build a consolidated, end-to-end, multilingual medical scribe model, a variant of which would be capable of running entirely offline, a breakthrough that promises to bring AI-powered documentation to even the most remote clinics in India. 

By combining Eka Care’s deep clinical data expertise with NVIDIA AI infrastructure and domain expertise, the initiative will address critical challenges in healthcare such as data privacy, internet dependency, and the need for real-time, low-latency transcription. 

Powering the next wave of clinical AI: 

Eka Care will utilise NVIDIA NeMo Curator to refine its massive datasets of Indian medical conversations. Eka Care is using NeMo Curator to clean and organise clinical data, ensuring the highest standards of data hygiene. To prevent “catastrophic forgetting”—a common issue where AI models lose previously learned knowledge as they take on new tasks—Eka Care is integrating the NVIDIA Nemotron CC dataset for replay during the pre-training phase. This ensures the model remains robust and generalizable while becoming a specialist in medical terminology. 

Evaluating State-of-the-Art Architectures: As part of this initiative, Eka Care is actively evaluating NVIDIA Nemotron Speech models, including Parakeet automated speech recognition (ASR) to power its end-to-end application. The goal is to merge ASR and Large Language Model (LLM) capabilities into a single, efficient architecture that reduces computational overhead without sacrificing clinical precision. As of part of its open innovation initiative, Eka Care will be exploring potential open-sourcing of this consolidated model. 

“Building a medical scribe for India requires navigating complex code-mixing and diverse accents. By collaborating with NVIDIA, we aren’t just improving our accuracy; we are building a sovereignty-first model that can live on a doctor’s mobile, independent of cloud connectivity. This is the future of secure, private patient documentation” said Vikalp Sahni, Founder & CEO, Eka Care. 

“India’s AI startup ecosystem is primed for acceleration, driven by exceptional technical talent and global ambition,” said Tobias Halloran, director of EMEAI startups and venture capital at NVIDIA. “NVIDIA is accelerating this momentum by giving founders direct access to accelerated computing, scalable AI infrastructure, and programs like NVIDIA Inception for startups and the NVIDIA VC Alliance—helping startups scale faster and build for global markets.”

This announcement aligns with the broader momentum around the India–AI Impact Summit 2026, a flagship gathering hosted by the Government of India under the IndiaAI Mission, taking place in New Delhi.