In high-volume healthcare contact facilities, each affected person dialog carries each scientific and operational significance, making correct real-time transcription mandatory 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 eradicate handbook knowledge entry. By eradicating routine course of steps, employees can keep absolutely targeted on affected person conversations, bettering each the expertise and the result. As healthcare techniques search to steadiness effectivity with empathy, real-time transcription has turn into a functionality for delivering responsive, high-quality care at scale.
Switchboard, MD is a physician-led AI and knowledge science firm with a mission to prioritize the human connection in medication. Its service improves affected person engagement and outcomes, whereas lowering 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 steered 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, personalised 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 techniques. Clients utilizing Switchboard have seen outcomes corresponding to:
- 75% discount in queue occasions
- 59% discount in name abandonment charge
Regardless of these early successes, Switchboard confronted a crucial problem: their present transcription strategy couldn’t scale economically whereas sustaining the accuracy required for scientific workflows. Value and phrase error charge (WER) weren’t simply operational metrics—they have been crucial enablers for scaling automation and increasing Switchboard’s impression throughout extra affected person interactions.
On this submit, we study the particular challenges Switchboard, MD confronted with scaling transcription accuracy and cost-effectiveness in scientific environments, their analysis course of for choosing the appropriate transcription resolution, and the technical structure they applied utilizing Amazon Join and Amazon Kinesis Video Streams. This submit 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 concentrate on affected person care. Lastly, we’ll have a look at the broader implications for healthcare AI automation and the way different organizations can implement comparable options utilizing Amazon Bedrock.
Selecting an correct, scalable, and cost-effective transcription mannequin for contact heart automation
Switchboard, MD wanted a transcription resolution that delivered excessive accuracy at a sustainable value. In scientific settings, transcription accuracy is crucial as a result of errors can compromise EMR document matching, have an effect on really helpful remedy 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 corresponding to Open AI’s Whisper mannequin hosted domestically. However these choices introduced tradeoffs—both in efficiency, value, or integration complexity.
After testing, the group decided that Amazon Nova Sonic offered the appropriate mixture of transcription high quality and effectivity wanted to help their healthcare use case. The mannequin carried out reliably throughout reside caller audio, even in noisy or variable circumstances. It delivered:
- 80–90% decrease transcription prices
- A phrase error charge of 4% on Switchboard’s proprietary analysis dataset
- Low-latency output that aligned with their want for real-time processing
Equally essential, Nova Sonic built-in easily into Switchboard’s present structure, minimizing engineering carry and accelerating deployment. With this basis, the group diminished handbook 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 medication by eradicating administrative boundaries that get in the way in which of significant interplay. Nova Sonic gave us the velocity and accuracy we would have liked to transcribe calls in actual time—so our prospects can concentrate on what actually issues: the affected person dialog. By lowering 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 Hook up with seize reside 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 complete processing pipeline runs in a serverless surroundings, offering scalable operation designed to deal with hundreds of concurrent calls whereas utilizing Nova Sonic’s real-time speech-to-text capabilities for rapid 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 instances, with the flexibleness to prioritize both transcription or speech technology primarily based on particular wants. A key cost-optimization characteristic is the power to regulate speech output tokens – organizations can set decrease token values when primarily targeted on transcription, leading to important value financial savings whereas sustaining excessive accuracy. This versatility and price flexibility makes Amazon Nova Sonic a worthwhile instrument for healthcare organizations like Switchboard seeking to implement voice-enabled options.
Why serverless: Strategic benefits for healthcare innovation
Switchboard’s selection 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 group can concentrate on creating scientific automation options slightly than server administration. This structure supplies built-in fault tolerance and excessive availability for crucial healthcare communications with out requiring in depth configuration from Switchboard’s group.
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 routinely 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 chance of over-provisioning servers that may sit idle throughout low-volume durations.
Conclusion
Switchboard, MD’s implementation of Amazon Nova Sonic demonstrates how the appropriate transcription know-how can remodel 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 business.
By constructing on Amazon Bedrock, Switchboard now has the flexibleness to increase automation throughout extra use instances and supplier networks. Their success exemplifies how healthcare innovators can mix accuracy, velocity, and effectivity to rework how care groups join with sufferers—one dialog at a time.
Get began with Amazon Nova on the Amazon Bedrock console. Be taught extra about Amazon Nova fashions on the Amazon Nova product web page.
In regards to the authors
Tanner Jones is a Technical Account Supervisor in AWS Enterprise Help, the place he helps prospects navigate and optimize their manufacturing functions on AWS. He makes a speciality of serving to prospects develop functions that incorporate AI brokers, with a selected concentrate on constructing secure multi-agent techniques.
Anuj Jauhari is a Sr. Product Advertising Supervisor at AWS, the place he helps prospects innovate and drive enterprise impression with generative AI options constructed on Amazon Nova fashions.
Jonathan Woods is a Options Architect at AWS primarily based in Nashville presently working with SMB prospects. He has a ardour for speaking AWS know-how to companies in a related means making it simple for patrons to innovate. Outdoors of labor, he tries maintaining along with his three youngsters.
Nauman Zulfiqar is a senior account supervisor primarily based in New York working with SMB shoppers. He loves constructing and sustaining robust buyer relationships, understanding their enterprise challenges and serving because the buyer’s major enterprise advocate inside AWS.
