Deepgram is bringing enterprise-grade speech recognition directly onto PCs by optimising its Nova-3 speech-to-text model on the Qualcomm Hexagon NPU in the Snapdragon X Series platform.
The initiative enables developers and device manufacturers to deliver real-time speech recognition with greater speed, privacy, and reliability, without relying on a cloud connection. It also aims to enable developers to build real-time voice experiences for AI PCs as well as automotive, XR, industrial edge, IoT, mobile, and wearable devices.
“The future of voice-first interaction is about meeting users wherever they are — in a vehicle, on a factory floor, inside an XR headset — without compromising on accuracy or responsiveness,” said Abe Pursell, vice president, Business Development and Partnerships, Deepgram.
“To make that possible, you need enterprise-grade speech recognition that can deliver within the constraints of a device. We’re bringing Deepgram Nova-3 directly to the ecosystem of PCs with Snapdragon, providing a foundation to build voice into products that work wherever people happen to be, regardless of network conditions,” Pursell added.
Speech recognition on-device
Running speech recognition directly on the device instead of in the cloud reduces latency and enhances privacy, enabling more natural voice interactions even in areas with limited connectivity. Deepgram also states Nova-3 maintains high transcription accuracy in challenging audio environments.
“We recognise that voice AI technologies serve different needs. That’s why we value our work with Deepgram – because accuracy, latency, reliability, and scalability matter for developers building automotive systems, healthcare applications, industrial solutions, and other mission-critical experiences,” said Upendra Kulkarni, vice president, Product Management, Qualcomm Technologies, Inc.
Kulkarni added: “The on-device AI capabilities of Snapdragon processors combined with Deepgram’s enterprise-class voice AI uniquely bring those requirements together in a way that opens new possibilities for real-time voice experiences across the device ecosystem.”
Deepgram says Nova-3 is the first voice AI model to support real-time multilingual transcription and delivers a 24.7% lower word error rate than the next-best competitor.
