Expanding a Nordic medical lineup with 3.91% KWER model that delivers sub-second latency across Swedish, Finnish, Danish, and Norwegian clinical workflows
CAMBRIDGE, United Kingdom, Jan. 28, 2026 (GLOBE NEWSWIRE) -- Speechmatics today launched a medical-grade Swedish speech-to-text model achieving 3.91% keyword error rate (KWER) on medical terms-40% lower than the closest competitor-expanding the company's Nordic medical language portfolio with real-time performance across major Scandinavian healthcare markets.
The model handles complex Swedish medical terminology, rapid multi-speaker dialogue, and diverse Nordic accents in noisy clinical environments, delivering accuracy that enables reliable automation in patient documentation, ambient scribes, and voice-driven workflows. Nordic healthcare providers can now standardize on a single Voice AI platform while supporting native-language operations across Swedish, Finnish, Danish, and Norwegian clinical environments.
This expansion arrives as healthcare organizations increasingly adopt ambient documentation and autonomous AI agents, where transcription accuracy is non-negotiable.
Why Swedish medical speech is hard
Swedish presents distinct challenges for speech recognition: compound words that combine multiple terms into single units, regional dialectal variation, and pitch accents that change meaning. Layer in medical domain complexity-pharmaceutical names, dosages, procedures, ICD-10 codes-and the difficulty compounds. Clinicians speak fast, often with overlapping dialogue between patient and provider, in rooms with background noise and interruptions.
Speechmatics collected region-specific training data, modeled acoustic variation across dialects, and built language models that understand compound word formation rather than memorizing every possible combination.
Proof: Swedish medical model vs. competitors
Results from medical test sets:
| Provider | Model | KWER | |
| Speechmatics | Medical | 3.91 | |
| OpenAI | Whisper-1 | 6.81 | |
| AssemblyAI | Universal | 6.05 | |
| Chirp_2 | 5.72 | ||
| Deepgram | Nova-3 | 7.87 | |
The 3.91% KWER translates to approximately 1,800 more words transcribed correctly per hour of audio compared to a 6% baseline. Speechmatics now supports dedicated medical models across Swedish (3.91% KWER), Finnish (5.41% KWER), Danish (6.15% KWER), and Norwegian (7.25% KWER).
Enabling autonomous medical AI workflows across the Nordics
Medical-grade speech recognition is becoming foundational infrastructure for autonomous healthcare agents. Speechmatics' recent partnership with Sully.ai demonstrates this shift in practice. Sully scaled from single-doctor clinics to enterprise customers with 500+ providers in under a year, deploying AI receptionists and clinical scribes.
"We needed speech models that work in real clinical environments: complex medical terminology, fast overlapping dialogue, accents, imperfect audio. Speechmatics has been the most responsive provider, and we've seen them handle medications better on our troublesome audio than any competitor," said Ahmed Omar, Founder and CEO, Sully.ai.
The Swedish launch extends this capability across the Nordics, enabling ambient scribes, AI receptionists, and documentation assistants to operate in native languages without sacrificing the accuracy that makes automation practical.
Nordic healthcare organizations can begin testing the Swedish medical model today through the Speechmatics Portal and API, with support for both real-time and batch transcription workflows.
Contact: Mieke Smith // mieke.smith@speechmatics.com
