The partnership combines medical-grade speech models with autonomous agent and scribe solutions to eliminate administrative burden across enterprise healthcare, powered by NVIDIA

Speechmatics and Sully.ai today announced a strategic partnership to power the next generation of autonomous healthcare agents and scribes. Built on NVIDIA AI infrastructure, the collaboration combines best in class medical-grade speech models with autonomous agent workflows to deliver AI receptionists and clinical scribes that handle real operational tasks and deliver tangible ROI across clinical settings.

This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260112368009/en/

The partnership arrives as global healthcare faces acute staffing shortages and mounting administrative costs. Sully, which scaled from single-doctor clinics to enterprise customers with 500+ providers in under a year, is already driving significant efficiency back into healthcare. Their north star metric of Minutes Added to Workforce (MAW) measures how agentic AI drives efficiency within healthcare use cases. As of December 2025, Sully has added more than 30 million minutes back to the healthcare workforce and current customers include Oshi Health, Tebra and Midi.

21x ROI: Autonomous agents delivering measurable workforce impact, soon to benefit more patients around the globe

Sully's partners are seeing 21x ROI in early case studies with autonomous operating systems capitalising on a suite of multiple agents working in coordination. Typical ROIs include: 5%+ increase in patient retention, 2.4+ hours time saving per physician per day and 18.5% increase in capacity for patient appointments. Building upon these early positive signals, Sully is seeing rapid expansion across large, multi-site provider networks, hence the requirement for Speechmatics - highly accurate, medical grade speech models that scale across different clinical environments.

Sully.ai selected Speechmatics after extensive internal testing across multiple speech model providers. Evaluation focused on clinical accuracy, handling ambiguous medical pronunciations, and real-time performance in noisy environments. Speechmatics' English Medical Model set benchmark results in 2025, delivering 93% general real-time accuracy (7% WER) and 96% medical keyword recall, with a medical keyword error rate 50% lower than the nearest competitor. These gains reduce corrections, improve downstream documentation quality, and support more reliable automation in patient access and clinical workflows.

"We needed best-in-class speech models that work in real clinical environments: complex medical terminology, fast overlapping dialogue, accents, imperfect audio, not just clean test clips. Speechmatics has been the most responsive provider with solutioning for us, and we've seen them handle medications better on our troublesome audio than any competitor."

— Ahmed Omar, Founder and CEO, Sully.ai

Speechmatics and Sully.ai plan to expand into new global markets including the Middle East following the launch of an English-Arabic bilingual model in early 2026. Bilingual, code-switching conversations are expected to be a defining requirement for voice automation in care delivery and patient access within this region. Speechmatics' Arabic capabilities are designed to perform across Modern Standard Arabic as well as Egyptian, Gulf, and Levantine dialects, supporting consistent performance across varied speakers and accents.

Trained on 16 billion words of real medical conversations

Trained on over 16 billion words of medical conversations, clinical documentation, and healthcare interactions, the models deliver keyword error rates 5-20% lower than evaluated competitors on medical test sets across most languages.

This training scale enables the models to distinguish between "hypertension" and "hypotension" in noisy emergency rooms, understand pharmaceutical names with regional accents, handle overlapping clinician-patient speech, and parse medical abbreviations, drug dosages, and ICD-10 codes, all while maintaining near-batch accuracy at sub-second latency.

"High-accuracy, low-latency speech recognition is a core enabler for autonomous agents that 'actually listen' and operate safely in mission-critical environments. Together with Sully.ai, we're enabling healthcare organizations to deploy ambient scribes and AI agents across multiple languages and global markets without compromising on quality, security, or speed." — Katy Wigdahl, CEO, Speechmatics

Built on NVIDIA, deployed on healthcare's terms

The model is deployed using NVIDIA AI infrastructure, optimized through NVIDIA Triton Inference Server and NVIDIA CUDA libraries. This enables high-throughput, low-latency processing at scale, with deployment flexibility across data center, private cloud, and edge environments. This architecture supports rapid customization and horizontal scaling for diverse healthcare deployments: from telehealth platforms and contact centers to EHR-connected scribes and bedside tools.

Unlike cloud-only competitors, Speechmatics supports on-premises, private cloud, and SaaS deployment, critical for organizations navigating data residency requirements, HIPAA compliance, and regulatory frameworks. This flexibility allows enterprises to keep sensitive patient data within their own infrastructure while accessing state-of-the-art speech technology.

About Speechmatics

Speechmatics is the voice AI company on a mission to understand every voice. The company's speech-to-text technology delivers industry-leading accuracy across 55+ languages, with specialized medical models trained on over 16 billion words of clinical data. Speechmatics' real-time and batch transcription APIs power applications for healthcare, media, contact centers, and voice agent organizations worldwide, with customers including AI Media, Content Guru and boost.ai. Founded in Cambridge, UK, Speechmatics has deployment options spanning on-premises, private cloud, and SaaS infrastructure. Learn more at www.speechmatics.com.

About Sully.ai

Sully.ai is transforming healthcare operations with autonomous AI agents that handle mission-critical workflows across multi-doctor practices and large provider networks. The company's full suite (from voice AI receptionists to clinical scribes) is built on an agentic operating system designed for the complexity of real healthcare environments. Founded by a team bringing together medical expertise, technical founders, and entrepreneurial leadership, Sully scaled from single-doctor clinics to enterprise customers with 500+ providers in under a year. Learn more at www.sully.ai.

View source version on businesswire.com: https://www.businesswire.com/news/home/20260112368009/en/

Healthcare ROI, powered by Speechmatics + Sully.ai: 21x ROI across early deployments 2.4+ hours saved per physician, per day 30 million minutes returned to the workforce 93% real-time accuracy, 96% medical keyword recall Built on NVIDIA