![[alt: Dark teal gradient with "Oak-1" and the text "Speechmatics' new multilingual medical model" highlighted below faded Standard, Enhanced, Melia-1 and Linden-1 model names.]](/_next/image?url=https%3A%2F%2Fimages.ctfassets.net%2Fyze1aysi0225%2F2mET3THUhmJ7zfoFKr5Hsg%2F38d91ed62f9187034d7410cfbb12af5c%2FOak-blog-1-1200x960.webp&w=3840&q=75)
Product
Meet Oak: medical transcription that follows the conversation across languages and speakers
Oak is Speechmatics’ new medical speech-to-text model, built for clinical conversations that move between languages and speakers.
Read featured articleResources
- Company
Adobe and Speechmatics deliver cloud-grade speech recognition on-device for Premiere
- Use Cases
Best speech-to-text AI guide: APIs, platforms and services compared
- News
AI can now understand health signals from 15 seconds of your voice, including fatigue, stress and type 2 diabetes
- Technical
Speed you can trust: The STT metrics that matter for voice agents
- Product
Speechmatics and Cekura bring real-world STT testing to voice agent pipelines
- Technical
Speech-to-text in production: what 36 years of hard lessons taught me
- Use Cases
What Word Error Rate Is Acceptable for Legal Transcription?
- Use Cases
The court reporter shortage crisis: data, causes, and what legal teams are doing about it
- Product
Speechmatics achieves a world first in bilingual Voice AI with new Arabic–English model
- Product
Your voice agent speaks perfect Arabic. That's the problem.
