Speechmatics, the Voice AI company on a mission to understand every voice, today announced a partnership with Edvak EHR, an AI-native EHR platform, to embed enterprise-grade speech accuracy into real-time clinical workflows.
The collaboration enables Edvak EHR to transform live clinical conversations into structured, audit-ready documentation with clinician oversight, triggering tasks, referrals, care coordination, and coding support directly within the EHR. Darwin AI is embedded natively within Edvak EHR, converting speech into automated workflows. Speechmatics provides the speech accuracy layer that ensures this automation operates safely and reliably at enterprise scale.
In clinical environments, a single dropped word can reverse documented meaning. When “no fever and nausea” becomes “fever and nausea,” documentation, coding signals and clinical decision support can shift incorrectly. To support automation inside the EHR, Edvak EHR required speech recognition capable of performing with rapid medical terminology, overlapping dialogue, noisy environments and ambiguous pronunciation.
Speechmatics’ English Medical Model delivers 93 percent real-time accuracy (7 percent WER) and 96 percent medical keyword recall, with significantly reduced keyword errors. The model distinguishes between terms such as hypertension and hypotension, understands pharmaceutical names across accents and preserves structured clinical concepts required for ICD-10 coding. These gains reduce correction burden and enable reliable workflow automation across documentation, care coordination and revenue cycle operations.
“Voice AI is now healthcare infrastructure, not a transcription feature. Our AI-native EHR drives next steps automatically inside the record, with clinicians able to review and adjust outputs in real time. That only works when speech understanding preserves clinical meaning. Speechmatics ensures negations, medication names and subtle distinctions remain accurate, making downstream automation trustworthy at scale,” said Vamsi Edara, Founder and CEO of Edvak EHR.
Healthcare providers are increasingly shifting from standalone transcription tools to embedded intelligence within AI-native EHR platforms. Edvak EHR captures physician-patient conversations in real time, converts them into structured clinical data and executes actions directly within the EHR. By unifying documentation and execution, the platform reduces administrative burden while preserving clinical meaning.
“Edvak EHR represents the next generation of EHR systems, where AI and voice drive action, not just documentation. Healthcare professionals need systems that handle the messiness of real medicine: overlapping voices, rapid terminology and imperfect conditions. Our medical models are designed to be the reliable foundation for this level of automation. That’s how Voice AI becomes infrastructure,” said Katy Wigdahl, CEO of Speechmatics.
Speechmatics supports on-premises, private cloud and SaaS deployment, meeting data residency and HIPAA-aligned compliance requirements. Medical models are available across multiple languages, enabling enterprise-scale deployment across global healthcare environments.