customers
All customer stories
Top Voice AI companies are building with Assembly.
resources
Latest Release
Universal 3.5 Pro
Our new flagship speech-to-text model handles real-world audio the way it actually happens. Available for real-time and pre-recorded audio.
resources
Customer support is the highest-volume, highest-stakes use case for voice agents — and the one where accuracy failures are most expensive. Every misheard account number is a repeat call, every botched escalation a lost customer. Here's how to ship production-grade support experiences, from first-call resolution to real-time agent assist.
The production gap
The gap between shipped and actually works. Source: The Voice Agent Report.
Accuracy over cost
76%
Of organizations prioritize accuracy over cost when choosing voice AI infrastructure — because errors compound into repeat calls and churn.
Source: The Voice Agent Report
Fewer tickets
90%
Reduction in customer complaints and support tickets after Siro built on AssemblyAI.
Source: Siro case study
Phone-number error
3.55%
Universal-3.5 Pro Realtime's phone-number entity error rate on the Pipecat benchmark — best of the realtime models tested.
Source: Daily's Pipecat STT benchmark
End-of-turn
~300ms
Turn detection from tonality, pacing, and rhythm — so the agent doesn't cut callers off mid-sentence.
Source: Universal-3.5 Pro Realtime
Customer story · Report 2
“The transcription accuracy, reliability, and speed of AssemblyAI's API have greatly enhanced our operations, reinforcing our trust in their technology and solidifying our partnership.”
— Raj Shankar, SVP Product, Calabrio
The production gap
Support agents in production face what demos never show: callers with accents and background noise, alphanumeric soup (order numbers, confirmation codes, emails), multi-turn conversations with context dependencies, and the need to escalate gracefully to a human. Accuracy failures don't stay small — they compound into repeat calls, CSAT drops, and churn.
voice_focus isolates the primary speaker and suppresses background speech that would otherwise be transcribed as phantom words and fire false interruptions.
Universal-3.5 Pro RealtimeSpeakerRevision labels speakers during the call, then corrects them with a single ~500ms revision at stream end (up to 10 speakers) — ready for supervisor dashboards.
Universal-3.5 Pro RealtimeLive transcription feeds sentiment flags, escalation detection when calls go off-script, and post-call analytics via the Speech Understanding API.
Speech UnderstandingTurn-based agents
For flows where you do your own turn detection and just need a finished transcript per utterance — IVR menus, call routing, one-shot voice commands — the Sync API returns a completed transcript in a single HTTP request. No WebSocket to manage.
Sync API flow
Runs on Universal-3.5 Pro.
Two paths
Both run on the same Universal-3.5 Pro Realtime foundation — start fresh with the managed API, or slot the STT layer into your existing contact center stack.
Recommended
The fastest path to production support agents
$4.50 /hr
STT + LLM + TTS included — free tier available
Bring your own stack
The BYO layer for existing contact centers
$0.45 /hr
Transcription only — unlimited concurrency
From pilot to scale
Sophisticated teams want modular infrastructure they can plug into their own pipeline. Both lanes serve this — but production has table stakes.
Production readiness
Table stakes
Entity accuracy on the numbers and names that matter. 3.55% phone-number error on the Pipecat benchmark — best of the realtime models tested.
Unlimited concurrency without rate-limit surprises. Scale to peak call volume without throttling.
Enterprise compliance. SOC 2 Type 2, ISO 27001:2022, PCI DSS v4.0, and a BAA for healthcare-adjacent support.
Graceful escalation to a human. Tool calling plus escalation detection, with full context handed off.
voice_focus for noisy call-center floors. Background speech doesn't become phantom words.
Session resumption for dropped mobile calls. Reconnect within 30 seconds, context preserved.
Proven in production — CallRail added voice agents and Siro cut complaints and support tickets by 90%.
Get your free API key and start building — or talk to us about an enterprise contact center deployment.
AssemblyAI is built for contact-center audio: Universal-3.5 Pro Realtime posts the best entity error rates of the realtime models on Daily's Pipecat benchmark (3.55% on phone numbers), isolates the caller from background floor noise with voice_focus, and runs with unlimited concurrency so peak call volume never hits a rate limit. Use it as a standalone STT layer, or through the fully managed Voice Agent API.
Stream the live call to Universal-3.5 Pro Realtime and feed the transcript into your coaching layer: sentiment flags for frustrated callers, escalation detection when a conversation goes off-script, and live speaker labels corrected to async-grade accuracy with a single ~500ms SpeakerRevision at stream end. Post-call, the Speech Understanding API adds entity detection, topic classification, and summarization.
Yes. The Voice Agent API supports tool calling and escalation detection, so the agent can hand off to a human the moment a conversation needs it — with the full transcript and context passed along so the caller never has to repeat themselves.
An IVR follows a fixed menu tree ('press 1 for billing'); a voice agent understands natural speech and can look up an account, answer a question, or resolve an issue in conversation. For simple turn-based flows like IVR menus or call routing, the Sync API returns a finished transcript per utterance in a single HTTP request — no WebSocket to manage.
The Voice Agent API's session resumption reconnects within 30 seconds with the full conversation context preserved — so a dropped mobile call or a flaky network doesn't restart the interaction.
The Voice Agent API is a flat $4.50/hr with STT, LLM, and TTS included and no per-token surcharges. If you already run your own orchestrator, Universal-3.5 Pro Realtime is $0.45/hr for transcription only, with add-ons (diarization, prompting, voice isolation) billed only as used.
