call_center_ai · realestate · workflow
Super cuts STT costs by ~30% and scales real-time voice agents for real estate with AssemblyAI Universal-3 Pro Streaming
Super's real-time phone agents were limited by STT providers that offered only basic turn detection timing controls, hit concurrency ceilings at scale, and provided keyterm prompting with minimal real-world impact for real estate vocabulary.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Phone call reaches voice agent
Inbound and outbound phone calls trigger Super's real-time voice agents.
Tools used
AssemblyAIUniversal-3 Pro StreamingLiveKit
Outcome
Universal-3 Pro Streaming delivered approximately 30% cost savings on STT, freed the engineering team from reactive maintenance to focus on product development, and improved conversational quality across thousands of daily calls.
What failed first
Multiple prior STT providers were tested and consistently fell short on turn detection, concurrency, and keyterm prompting, forcing workarounds that consumed engineering resources.
Results
Time savedapproximately one day
Volumeone engineer plus QA support
Cost replaced~30%
Grounding & classification
Source type: vendor customer story
25 fields verified against source quotes.
conversational aimulti agent workflowspeech to textvoice aicall recordingfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedreal estatecost reductionemployee productivityvendor customer storycall center aivoice call handling