Suki launches AI dictation tool with EHR integration capabilities. Providers might choose the tool when documenting complex surgical procedures or medical codes to ensure the highest level of precision, Suki says. Published Aug. 26, 2026 Dive brief: * Artificial intelligence documentation startup Suki has launched a dictation tool that transcribes speech into text word-for-word, the company announced Tuesday. * The company's flagship product is a scribe that listens passively in doctors' offices and turns patient-provider conversations into summarized clinical notes, rather than a transcript. But the new tool captures spoken word verbatim, which can be useful for providers working with complicated medical jargon, Suki said in a press release. * The tool can be integrated into Epic and Meditech's electronic health records systems. Health tech companies can also embed it directly into their own products, eliminating the need to build tools from scratch, according to Suki. Dive insight: Suki says its new AI-powered dictation tool, which providers can deploy on its own or alongside Suki's ambient clinical documentation tool, allows clinicians to choose the most appropriate documentation method for each patient visit. The tool uses automatic speech recognition, a branch of AI that actively learns a user's vocabulary over time and removes filler words to make the notes more concise. Providers might choose the verbatim tool, Suki Dictation, when documenting complex surgical procedures or medical codes to ensure the highest level of precision, which is critical for accurate reimbursements, the company said. Meanwhile, a doctor having a more routine conversation with a patient might prefer an ambient listening tool that generates notes during the appointment and summarizes key talking points. Clinical dictation has progressed from in-person stenographers to today's AI-assisted tools embedded into EHR systems. Transcribing speech to text is not new technology, but Suki says leveraging AI to do it provides more value for clinicians. According to Abhi Pathak, Suki's chief product officer, the company's dictation tool shares a base infrastructure with its ambient documentation product, laying the groundwork for future products such as AI-backed procedure note generation, conversational voice editing and intelligent voice commands. Clinical documentation is one of the most popular use cases for AI in healthcare. Research shows that among hospitals using Epic's EHR, 63% use AI for documentation. AI scribes have been tied to time savings and an uptick in clinician job satisfaction. Suki is competing in a fierce market dominated by well-funded startups and EHR companies offering their own native AI scribes. Suki's dictation tool comes more than a year after one of its competitors, health tech startup Nabla, launched a dictation tool. Microsoft Dragon Copilot also offers dictation alongside ambient documentation.

Nabla has launched Nabla Dictation for Mac, the first fully on-device clinical dictation app designed natively for macOS. The product combines on-device speech recognition with Epic integration, extending AI capabilities beyond patient encounters to support tasks like managing inbox messages and drafting referrals. The application processes all speech on-device using Apple's Core ML and Neural Engine, eliminating cloud dependency whilst maintaining compatibility with existing dictation hardware including PowerMic and SpeechMike microphones. The company rebuilt its entire speech stack using Apple native technologies like Swift and Core ML. Forty-four per cent of Nabla's active clinicians work on Apple devices. The platform is trusted by over 100,000 clinicians across 190 health systems, including M Health Fairview, and supports more than 35 languages whilst integrating with all major electronic health records systems.

Nabla launches Dictation for Mac. Nabla, providers of artificial intelligence assistants in clinical care, has introduced a fully on-device clinical dictation app, Nabla Dictation for Mac, combining on-device speech recognition with deep Epic electronic health record integration. For health systems operating on Apple devices, Nabla is combining ambient documentation with medical-grade dictation on Mac in a single AI-native experience. The offering supports documentation, communication, and care coordination tasks through one unified voice layer while maintaining compatibility with existing dictation hardware, including PowerMic and SpeechMike microphones. "For decades, clinicians have been forced to adapt their workflows to software," said Laurent Landowski, chief product officer of Nabla, in a statement. "We believe it's time for software to adapt to clinicians. Voice is becoming the most natural interface for clinical work, but healthcare has been held back by fragmented tools and workflows that weren't designed for the AI era. Our vision is a future where clinicians can move through their entire day using a single, intelligent voice layer built around how care is actually delivered." To deliver the Mac app, Nabla rebuilt its full speech stack, including voice activation, speech-to-text, and medical post-processing using Apple native technologies like Swift and Core ML, and taking advantage of the power of Apple silicon. Using Apple's Core ML Tools, the team migrated years of PyTorch-based speech models onto Apple Silicon. On-device, the models are optimized for the Apple Neural Engine. This enables the low latency and efficiency required for medical-grade dictation, with no audio sent to servers and no cloud dependency. "Core ML and the Apple Neural Engine made it possible for us to bring our entire speech pipeline on-device for Mac without compromising the performance clinicians expect from medical-grade dictation," Landowski said. "That means clinicians get the speed and responsiveness they need, while keeping speech processing entirely on their device."