Bengaluru, Feb 16: Eka Care today announced the launch of Parrotlet-a v2, India’s most performant clinical-grade, real-time Automatic Speech Recognition (ASR) model, purpose-built for healthcare documentation. Designed for Indian hospitals and outpatient departments, the model sets a new benchmark in AI-driven medical transcription by transforming doctor–patient conversations into structured clinical notes in near real-time.
As electronic medical records (EMRs) expand across India, clinicians face rising documentation burdens that often reduce patient interaction time. Parrotlet-a v2 addresses this challenge by generating accurate, structured clinical notes within seconds, streamlining workflows, and helping reduce clinician burnout in high-volume OPDs and hospital settings.
“India’s clinical reality is multilingual, acoustically noisy, and filled with hyper-local medical terminology that global AI systems are not trained to handle,” said Vikalp Sahni, Founder & CEO, Eka Care. “Parrotlet-a v2 is tuned for Indian healthcare. In benchmark evaluations against leading global and India-focused models—including Gemini 3 Pro, Gemini 3 Flash, and Saaras V3—it demonstrated leading Semantic Word Error Rate performance while delivering sub-second inference speeds, enabling documentation seamlessly during consultations.”
Parrotlet-a v2 powers EkaScribe, Eka Care’s AI-driven digital medical scribe platform currently used by over 3,000 doctors. The 5B parameter model balances lightweight efficiency with advanced intelligence, accurately interpreting code-mixed Hindi and Indian English conversations, overlapping dialogue, regional accents, and India-specific drug names while minimizing hallucinations.
Key Performance Highlights:
- Medical Keyword Accuracy: 93% in Indian English, 85% in Hindi
- Phantom Speech Rate: 3% in noisy hospital environments
- Inference Speed: Sub-second, up to 30x faster than other large models
“Healthcare digitisation at scale requires AI that is accurate, fast, reliable, and economically sustainable,” said Deepak Tuli, Co-founder & COO, Eka Care. “Parrotlet-a v2 understands Indian clinical practice, enabling deployment across hospital networks without compromising workflow speed, affordability, or patient safety.”
Eka Care aims to support nationwide healthcare digitisation through Parrotlet-a v2, reducing administrative overhead and enabling structured data capture at the point of care. The company plans to expand language coverage and strengthen integrations with hospital, insurance, and public health systems to create a more connected and data-driven healthcare ecosystem.
Availability:
Parrotlet-a v2 is available through Eka Care’s developer APIs for integration into healthcare platforms and clinical systems.