customers
All customer stories
Top Voice AI companies are building with Assembly.
resources
Latest Release
Text-to-Speech API
Our first text-to-speech model, AssemblyAI-TTS-1, is built for voice agents, on live calls. It sounds natural, responds fast, and keeps callers on the line.
resources
Replace hold music with instant answers. AI voice agents handle appointment scheduling, caller routing, intake forms, and FAQs — so your front desk team focuses on the patients, clients, and customers who walk through the door.
Front desk agent
4 calls handledMaria Jensen
Reschedule cleaning — Tue 2pm
David Kim
Insurance verification question
Rachel Park
New patient intake — Dr. Patel
Tom Walsh
Confirm Fri appointment + directions
The average medical or professional office misses 30% of inbound calls. Patients and clients hit voicemail, hang up, and book with the competitor. Staff juggle ringing phones, walk-ins, and paperwork — leading to scheduling errors, long hold times, and burned-out receptionists. Every unanswered call is a missed appointment, missed revenue, and a worse first impression. AssemblyAI gives every office an always-on AI front desk.
Time to first audio from the Text-to-Speech API — callers never wait on dead air.
Lower entity error rate than the next-best streaming model.
Always-on for nights, weekends, holidays, and after-hours overflow.
Concurrent Universal-3.6 Pro Realtime streams — no busy signals, no hold queues.
Two ways to build
Run the full AssemblyAI voice stack, or drop best-in-class streaming STT into your existing PBX or IVR.
Universal-3.6 Pro Realtime listens, LLM Gateway reasons, and the Text-to-Speech API speaks — a front-desk agent that schedules, routes, and answers on one API key.
Best for
Appointment scheduling, intake, FAQs, caller routingTool calls for EHR / practice management write-backA natural voice that gets names and numbers right on read-back4,000+ voices in English, Spanish, French, German, Italian, and PortugueseFree tier available · No credit card required
Drop best-in-class speech recognition into your existing PBX or IVR stack. Bring your own LLM and TTS for full control over routing logic and voice.
Best for
Teams running their own LLM, TTS, and PBX/IVR307 ms median time to final transcript for real-time caller interactionAccurate capture of names + dates + IDsNative LiveKit, Pipecat, Vapi, and Twilio integrationsUnlimited concurrency for peak-hour call volumeNo concurrency caps · Autoscaling included
Caller reaches the voice agent instantly
No hold queue, no phone tree. The agent greets by name when caller ID matches your records, and asks how it can help in a natural voice from the Text-to-Speech API, with about 90 ms time to first audio.
Transcribed with name and date accuracy
Universal-3.6 Pro Realtime nails proper nouns, insurance IDs, phone numbers, and appointment times — the lowest entity error rate among benchmarked streaming models (14.41% vs 18.19% for the next best). No more callbacks to verify what the caller said.
Agent takes action via tool calling
Books or reschedules appointments, routes to the right department, verifies insurance, or collects new patient intake — all mid-conversation through JSON Schema function calls.
Confirms and follows up automatically
Reads back the appointment details, sends an SMS confirmation, and pushes the structured record to the EHR, practice management system, or CRM — without staff lifting a finger.
Front desk pipeline
Caller reaches the voice agent instantly
Transcribe with name + date accuracy
Take action via tool calling
Confirm + follow up automatically
LiveKit + Universal-3.6 Pro Realtime — multi-location routing
# LiveKit + AssemblyAI Universal-3.6 Pro Realtime: multi-location routing
from livekit.agents import Agent, AgentSession, TurnHandlingOptions
from livekit.plugins import assemblyai, cartesia, openai, silero
from livekit.plugins.turn_detector.multilingual import MultilingualModel
class FrontDeskAgent(Agent):
def __init__(self):
super().__init__(
instructions=(
"You are a front desk receptionist for a multi-location dental "
"group. Identify which office the caller needs. Check availability "
"across all locations. Book appointments, collect insurance details, "
"and route complex billing questions to the office manager."
),
)
async def entrypoint(ctx):
session = AgentSession(
stt=assemblyai.STT(
model="universal-3-6-pro",
keyterms_prompt=["Dr. Patel", "panoramic x-ray", "deep cleaning",
"Lakewood office", "Downtown office"],
),
llm=openai.LLM(model="gpt-4o"),
tts=cartesia.TTS(),
vad=silero.VAD.load(activation_threshold=0.3),
turn_handling=TurnHandlingOptions(
turn_detection=MultilingualModel(),
endpointing={"min_delay": 0.5, "max_delay": 3.0},
),
)
await session.start(room=ctx.room, agent=FrontDeskAgent())
Want AssemblyAI on the speaking side too? The Text-to-Speech API has reference implementations for LiveKit and Pipecat.
Universal-3.6 Pro Realtime captures dates, times, provider names, and insurance IDs with the lowest entity error rate among benchmarked streaming models (14.41% vs 18.19% for the next best) — no more "was that the 13th or the 30th?" callbacks. Keyterm prompting boosts recognition of your provider list and procedure vocabulary.
Book appointments, check provider availability, verify insurance, and route calls — all through JSON Schema function calls that execute mid-conversation without dropping the caller. Native integrations with LiveKit, Pipecat, Twilio, and standard WebSocket clients.
Universal-3.6 Pro Realtime has unlimited concurrency at $0.45/hr per stream — no busy signals, no hold queues. Auto-scales for Monday morning rushes, lunch-hour spikes, and after-hours volume so every caller gets answered on the first ring.
Calabrio replaced its legacy on-premise transcription solution with AssemblyAI's API, gaining extensive language support to power its enterprise workforce and conversation intelligence platform across global markets.
Calabrio
Read more Aloware's AloAi Voice Analytics platform processes 200 million calls and texts on AssemblyAI's API — converting half its client base to AI-powered packages and lifting lead-to-close rate by 27%.
Aloware
Read more