How Switchboard, MD automates real-time name transcription in medical contact facilities with Amazon Nova Sonic
In high-volume healthcare contact facilities, each affected person dialog carries each medical and operational significance, making correct real-time transcription needed for automated workflows. Correct, instantaneous transcription permits clever automation with out sacrificing readability or care, in order that groups can automate digital medical document (EMR) document matching, streamline workflows, and get rid of guide information entry. By eradicating routine course of steps, employees can keep absolutely centered on affected person conversations, enhancing each the expertise and the end result. As healthcare programs search to steadiness effectivity with empathy, real-time transcription has change into a functionality for delivering responsive, high-quality care at scale.
Switchboard, MD is a physician-led AI and information science firm with a mission to prioritize the human connection in drugs. Its service improves affected person engagement and outcomes, whereas decreasing inefficiency and burnout. By designing and deploying clinically related options, Switchboard, MD helps suppliers and operators collaborate extra successfully to ship nice experiences for each sufferers and employees. Considered one of its key options is streamlining the contact heart utilizing AI voice automation, real-time medical document matching, and advised subsequent steps, which has led to important reductions in queue occasions and name abandonment charges.
With greater than 20,000 calls dealt with every month, Switchboard, MD helps healthcare suppliers in delivering well timed, customized communication at scale. Its AI platform is already serving to scale back name queue occasions, enhance affected person engagement, and streamline contact heart operations for clinics and well being programs. Clients utilizing Switchboard have seen outcomes reminiscent of:
- 75% discount in queue occasions
- 59% discount in name abandonment fee
Regardless of these early successes, Switchboard confronted a crucial problem: their current transcription strategy couldn’t scale economically whereas sustaining the accuracy required for medical workflows. Value and phrase error fee (WER) weren’t simply operational metrics—they have been crucial enablers for scaling automation and increasing Switchboard’s influence throughout extra affected person interactions.
On this put up, we look at the particular challenges Switchboard, MD confronted with scaling transcription accuracy and cost-effectiveness in medical environments, their analysis course of for choosing the best transcription answer, and the technical structure they carried out utilizing Amazon Connect and Amazon Kinesis Video Streams. This put up particulars the spectacular outcomes achieved and demonstrates how they have been ready to make use of this basis to automate EMR matching and provides healthcare employees extra time to deal with affected person care. Lastly, we’ll take a look at the broader implications for healthcare AI automation and the way different organizations can implement related options utilizing Amazon Bedrock.
Selecting an correct, scalable, and cost-effective transcription mannequin for contact heart automation
Switchboard, MD wanted a transcription answer that delivered excessive accuracy at a sustainable value. In medical settings, transcription accuracy is crucial as a result of errors can compromise EMR document matching, have an effect on really useful therapy plans, and disrupt automated workflows. On the identical time, scaling help for hundreds of calls every week meant that inference prices couldn’t be ignored.
Switchboard initially explored a number of paths, together with evaluating open supply fashions reminiscent of Open AI’s Whisper mannequin hosted regionally. However these choices offered tradeoffs—both in efficiency, value, or integration complexity.
After testing, the staff decided that Amazon Nova Sonic supplied the best mixture of transcription high quality and effectivity wanted to help their healthcare use case. The mannequin carried out reliably throughout dwell caller audio, even in noisy or variable situations. It delivered:
- 80–90% decrease transcription prices
- A phrase error fee of 4% on Switchboard’s proprietary analysis dataset
- Low-latency output that aligned with their want for real-time processing
Equally vital, Nova Sonic built-in easily into Switchboard’s current structure, minimizing engineering raise and accelerating deployment. With this basis, the staff lowered guide transcription steps and scaled correct, real-time automation throughout hundreds of affected person interactions.
“Our imaginative and prescient is to revive the human connection in drugs by eradicating administrative obstacles that get in the best way of significant interplay. Nova Sonic gave us the pace and accuracy we wanted to transcribe calls in actual time—so our clients can deal with what really issues: the affected person dialog. By decreasing our transcription prices by 80–90%, it’s additionally made real-time automation sustainable at scale.”
– Dr. Blake Anderson, Founder, CEO, and CTO, Switchboard, MD
Structure and implementation
Switchboard’s structure makes use of Amazon Connect with seize dwell audio from each sufferers and representatives. Switchboard processes audio streams by means of Amazon Kinesis Video Streams , which handles the real-time media conversion earlier than routing the information to containerized AWS Lambda capabilities. Switchboard’s Lambda capabilities set up bidirectional streaming connections with Amazon Nova Sonic utilizing BedrockRuntimeClient’s InvokeModelWithBidirectionalStream API. This novel structure creates separate transcription streams for every dialog participant, which Switchboard recombines to create the whole transcription document. The whole processing pipeline runs in a serverless atmosphere, offering scalable operation designed to deal with hundreds of concurrent calls whereas utilizing Nova Sonic’s real-time speech-to-text capabilities for instant transcription processing.
Nova Sonic integration: Actual-time speech processing
Harnessing Amazon Nova Sonic’s superior audio streaming and processing, Switchboard developed and constructed the potential of separating and recombining audio system’ streams and transcripts. This makes Amazon Nova Sonic notably efficient for Switchboard’s healthcare functions, the place correct transcription and speaker identification are essential.
Amazon Nova Sonic presents configurable settings that may be optimized for various healthcare use circumstances, with the pliability to prioritize both transcription or speech technology primarily based on particular wants. A key cost-optimization function is the flexibility to regulate speech output tokens – organizations can set decrease token values when primarily centered on transcription, leading to important value financial savings whereas sustaining excessive accuracy. This versatility and value flexibility makes Amazon Nova Sonic a beneficial instrument for healthcare organizations like Switchboard trying to implement voice-enabled options.
Why serverless: Strategic benefits for healthcare innovation
Switchboard’s alternative of a serverless structure utilizing Amazon Join, Amazon Kinesis Video Streams, and containerized Lambda capabilities represents a strategic resolution that maximizes operational effectivity whereas minimizing infrastructure overhead. The serverless strategy eliminates the necessity to provision, handle, and monitor underlying infrastructure, in order that Switchboard’s engineering staff can deal with growing medical automation options slightly than server administration. This structure gives built-in fault tolerance and excessive availability for crucial healthcare communications with out requiring intensive configuration from Switchboard’s staff.
Switchboard’s event-driven structure, proven within the following determine, permits the system to scale from dealing with dozens to hundreds of concurrent calls, with AWS mechanically managing capability provisioning behind the scenes. The pay-as-you-go billing mannequin helps Switchboard pay just for compute sources used throughout name processing, optimizing prices whereas eliminating the danger of over-provisioning servers that will sit idle throughout low-volume durations.
Conclusion
Switchboard, MD’s implementation of Amazon Nova Sonic demonstrates how the best transcription expertise can rework healthcare operations. By reaching 80–90% value reductions whereas sustaining clinical-grade accuracy, they’ve created a sustainable basis for scaling AI-powered affected person interactions throughout the healthcare trade.
By constructing on Amazon Bedrock, Switchboard now has the pliability to increase automation throughout extra use circumstances and supplier networks. Their success exemplifies how healthcare innovators can mix accuracy, pace, and effectivity to remodel how care groups join with sufferers—one dialog at a time.
Get started with Amazon Nova on the Amazon Bedrock console. Study extra about Amazon Nova fashions on the Amazon Nova product page.
In regards to the authors
Tanner Jones is a Technical Account Supervisor in AWS Enterprise Help, the place he helps clients navigate and optimize their manufacturing functions on AWS. He focuses on serving to clients develop functions that incorporate AI brokers, with a specific deal with constructing secure multi-agent programs.
Anuj Jauhari is a Sr. Product Advertising and marketing Supervisor at AWS, the place he helps clients innovate and drive enterprise influence with generative AI options constructed on Amazon Nova fashions.
Jonathan Woods is a Options Architect at AWS primarily based in Nashville at the moment working with SMB clients. He has a ardour for speaking AWS expertise to companies in a related approach making it straightforward for patrons to innovate. Exterior of labor, he tries maintaining along with his three children.
Nauman Zulfiqar is a senior account supervisor primarily based in New York working with SMB shoppers. He loves constructing and sustaining sturdy buyer relationships, understanding their enterprise challenges and serving because the buyer’s major enterprise advocate inside AWS.
