Roark Live Bench · Suite v1.3 · Sweep of 23 October 2026
Voice AI models, ranked on live phone calls.
Every speech-to-text, language model and text-to-speech model, run in every combination on the same real call to the same agent. A model is ranked on every stack it runs in; the stacks are the evidence.
Our picks
Task completionMedian responseCost per minute- Best overallAssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.697%3.9 s$0.055
- Best valueAssemblyAI Universal-3.5 Pro + Google Gemini 3.8 Flash + Cartesia Sonic-3.597%4.3 s$0.048
- FastestOpenAI Whisper-1 + Google Gemini 3.8 Flash + OpenAI TTS-1 HD88%0.5 s$0.023
- Best speech-to-speechgrok-voice-think-fast-2.082%2.1 s$0.083
- Best in customer supportAssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + ElevenLabs v4 Turbo100%3.9 s$0.096
- Best in healthcareAssemblyAI Universal-3.5 Pro + Google Gemini 3.8 Flash + Cartesia Sonic-3.696%4.4 s$0.041
- Best in home servicesAssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.596%4.0 s$0.058
- Best in insuranceAssemblyAI Universal-3.5 Pro + OpenAI GPT-4o + Cartesia Sonic-3.698%3.2 s$0.042
The read
- 430 of 642 cascades complete the task in at least 90% of calls, and the top 10 sit within 1 point of each other. What separates the top stacks is speed and cost.
- Median response time runs from 0.5 s to 6.0 s on the same agent and the same caller, a spread of 5.5 s that comes entirely from the models behind it.
- No stack wins everything. The fastest, OpenAI Whisper-1 + Google Gemini 3.8 Flash + OpenAI TTS-1 HD at 0.5 s, ranks 530 of 642 on task completion; the most complete is Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD at 99%.
- The language model matters most: swapping it moves task completion by 7 points, against 3 for the speech engine and 2 for the transcriber.
Cascade vs Speech-to-Speech
The first choice to make. A cascade chains three models: one transcribes, one decides what to say, one speaks. A speech-to-speech model does all three at once. Both run the same agent on the same calls here.
- Cascades lead on task completion, tool use and time to first word; speech-to-speech leads on response time and cost per task. Neither wins outright, so the right choice depends on what your calls need.
- The biggest difference is task completion: 95% for cascades against 77% for speech-to-speech.
| Measure | Cascade | Speech-to-speech |
|---|---|---|
| Task completion | 95% (leads) | 77% |
| Tool use | 72% (leads) | 55% |
| Time to first word | 0.7 s (leads) | 1.3 s |
| Response time | 3.6 s | 2.6 s (leads) |
| Cost per task | $0.15 | $0.15 (leads) |
The three strongest of each, averaged. Cascades: Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.5; AssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Rime Coda; Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + Rime Coda. Speech-to-speech: grok-voice-think-fast-2.0; gemini-3.8-live; amazon.nova-2-sonic-v1:0. Each measure is scored 0 to 100 on its own scale, further out is better; the table gives the same figures in their own units.
Which to use
- Choose speech-to-speech when the pause matters more than the outcome: short transactional calls, callers who interrupt, queues where every half second costs you callers. Expect to pay more, and choose the model carefully (gpt-live-1 (backend gpt-6.1-sol) leads here).
- Choose a cascade when the call has to complete, when cost matters, or when you need to see which stage to fix. It is 13 points ahead on task completion here.
- Costs are what each stack’s providers charged for these calls, at the rates in effect when they ran. Telephony and hosting are not included.
Speech-to-Text
The transcriber turns the caller's speech into text. It decides what the agent thinks it heard, and nothing after it can start until it finishes.
- AssemblyAI Universal-3.6 Pro, AssemblyAI Universal-3.5 Pro, Deepgram Nova-3 and Speechmatics Enhanced (realtime) are level: none leads by more than the margin of error. Of them, AssemblyAI Universal-3.6 Pro costs least, at $0.030 a call. Avoid Speechmatics Linden-1 (own VAD): last on semantic word error rate (2.2%).
- Speechmatics Linden-1 (own VAD) delivers its transcript in 0.49 s, OpenAI Whisper-1 in 1.93 s: 1.44 s added to every turn of the call.
- AssemblyAI Universal-3.6 Pro is the most accurate: it changes the meaning of 0.9% of the caller's words, against 2.2% for Speechmatics Linden-1 (own VAD).
- In 341 of 648 cascades the transcriber is the slowest step of the turn, whichever model runs it.
Open a model to see where it ranks and the stacks it works best in.
Language model
The language model decides what the agent says and does. It has the most influence on whether the task gets done, and usually takes the largest share of each turn.
- Pick OpenAI GPT-6.1 Sol: it leads on task completion (95%), tool use (71%) and instruction following (4.2 / 5). If speed matters more, Anthropic Claude Haiku 4.5 is the quickest, at 0.36 s, and completes 91%. Avoid OpenAI GPT-5.1: last on tool use (33%) and instruction following (4.1 / 5).
- Anthropic Claude Haiku 4.5 starts answering in 0.36 s, Google Gemini 3.8 Flash in 1.47 s: 1.11 s added to every turn of the call.
- OpenAI GPT-6.1 Sol uses its tools most reliably: it handles its tools without a mistake on 71% of calls, against 33% for OpenAI GPT-5.1.
- In 161 of 648 cascades the language model is the slowest step of the turn, whichever model runs it.
Open a model to see where it ranks and the stacks it works best in.
Text-to-Speech
The speech engine is the voice the caller hears, and the last step before they hear anything.
- Cartesia Sonic-3.6, Cartesia Sonic-3.5 and ElevenLabs v4 Turbo are level: none leads by more than the margin of error. Of them, Cartesia Sonic-3.5 costs least, at $0.165 a call. Avoid OpenAI TTS-1 HD: last on readback accuracy (80%), word error rate (8.7%) and time to first audio byte (2.09 s).
- ElevenLabs v4 Turbo starts speaking in 0.11 s, OpenAI TTS-1 HD in 2.09 s: 1.97 s added to every turn of the call.
- Cartesia Sonic-3.6 is the most accurate: it reads codes, amounts and dates back correctly 87% of the time, against 80% for OpenAI TTS-1 HD.
- Cartesia Sonic-3.6 sounds the most human: 3.8 / 5, against 3.4 / 5 for ElevenLabs Flash v2.5.
- In 99 of 648 cascades the speech engine is the slowest step of the turn, most often with OpenAI TTS-1 HD (54 of them).
Open a model to see where it ranks and the stacks it works best in.
Speech-to-Speech models
One model listens, reasons and speaks, so there is nothing to swap and no stages to split. Each is judged on the whole call, with the same calls and the same scoring as every cascade.
- The model matters as much as the architecture: gpt-live-1 (backend gpt-6.1-sol) completes 86% of tasks, ElevenLabs Realtime v1 Mini 42%.
- grok-voice-think-fast-2.0 answers in 2.1 s against 4.1 s for gemini-2.5-flash-native-audio-preview-12-2025.
- Price varies as much as quality: $0.06 per completed task for amazon.nova-2-sonic-v1:0, $0.69 for gpt-realtime-2.
Open a model for its full report, every figure it was scored on and the calls behind them.
Every stack
The evidence behind the model boards: each combination on its own calls, scored on the same recipe. Open a stack for its full report, every figure it was scored on and the calls behind them.
Each score carries its 95% margin of error. A rank is the best place a stack could hold once every margin is allowed for, so stacks the calls cannot tell apart share one and are listed by the low end of their margin; hover a rank for the worst place it could hold. 92 stacks are level with the leader: their calls cannot tell them apart. Among them, 31 Google Gemini 3.8 Flash, 29 OpenAI GPT-6.1 Sol, 19 Anthropic Claude Sonnet 5.5, 9 Anthropic Claude Haiku 4.5, 2 OpenAI GPT-4o mini, 1 OpenAI GPT-4.1 and 1 speech-to-speech; 48 AssemblyAI, 23 Deepgram and 20 Speechmatics; 48 Cartesia, 33 ElevenLabs, 9 Rime and 1 OpenAI. A cascade's figures are 25% its own calls and 75% what every other stack shows about its transcriber, language model and voice.
Not ranked here for missing data: Speechmatics Linden-1 + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD (no response time or tool use or human-likeness or readback accuracy or voice consistency).
By industry
Each industry ranked on its own calls: the same five callers, its own tasks and tools. A stack has a handful of calls in each, so a cascade is ranked on what its transcriber, language model and voice show across every stack in that industry, and a speech-to-speech model on its own calls there. Pairings show on the main board. Every panel is on one scale, so a bar reads against the other industries as well as its own.
Healthcare
Reschedule an appointment. A patient moves a dermatology appointment around a work schedule, corrects their date of birth, narrows the times twice, and asks about the change fee, parking and insurance.
Home services
Urgent repair: triage and booking. A caller with a burst pipe needs safety advice first, then an emergency visit. The unit on file is out of date, the callback number gets corrected, and the caller pushes for an earlier visit.
Insurance
Report a new auto claim. A driver who was just rear-ended reports a claim, corrects the policy number, spells the other car’s plate, asks about the deductible, a rental and their premium, and needs a tow.
Customer support
Internet outage troubleshooting. A technical caller who has already rebooted the gateway pushes back on scripted steps, wants the line fixed, and asks for a bigger credit for the downtime.
How it works
Every number on this page comes from real phone calls, placed and scored the same way for every stack.
Real calls, four industries, five callers
Roark places real phone calls over the public phone network to a reference agent for each of four industries: rescheduling a clinic appointment, booking an urgent home repair, opening an auto insurance claim and fixing an internet outage. Each agent has its own prompt and tools, identical for every stack. The tasks carry the details real calls trip on: a corrected date of birth, a policy number spelled out, a constraint added halfway through.
Every industry is called by the same five simulated callers: a quiet US English line, a Spanish-accented caller on a city street, an Indian English caller in a busy café, a flustered Southern caller with a baby crying, and a fast caller who interrupts over construction noise. They are equally clear about what they want, so a call fails because of the agent, not the caller. Only the models change, so any difference on the board comes from them.
Each caller rings each industry once for a cascade and four times for a speech-to-speech model. A cascade's figures also draw on its parts, heard in dozens of other stacks; a speech-to-speech model has only its own calls, so it takes more of them.
That makes industries comparable over the same callers, and callers over the same tasks, and the board can be re-ranked by either. One caller within one industry is too few calls to judge, so the board never shows it.
655
stacks
20
calls per stack
13,876
calls scored
Every model, in every combination
9 transcribers, 8 language models and 9 voices are run in every combination with each other, beside 13 speech-to-speech models. A model's own figures pool every stack it runs in, adjusted for its partners in each one, so every model is compared as if it ran with the same partners. A transcriber's figure rests on hundreds of calls with every language model and every voice, not on one lucky pairing.
That measures a model where it actually works: inside a running agent, on live phone audio, through interruptions, corrections and real turn-taking. A test that feeds a model clean audio files or one prompt at a time never sees any of that.
One score, weighted by what matters on a call
Each section ranks on a Roark score. Every figure scores 0 to 100 between two published points: full marks where doing better makes no difference to the caller, zero where the call breaks down. Each then counts at its weight, and the weights follow one order everywhere: whether the caller got what they rang for, then whether the agent got it right, then speed.
A stack, cascade or speech-to-speech, is scored on the outcome and the reply first, then on what each of its components got right on its own calls: the words its transcriber got wrong in a way that changes the meaning, whether its voice read codes and amounts back right, how human it sounded, and whether its tools were handled. A component that leads its section lifts every stack that carries it, by the same recipe for every stack. A figure a stack cannot carry, such as a semantic word error rate for a speech-to-speech model with no transcript, is credited at the field median, so the stack is neither flattered nor punished for it.
On a full sweep each cascade's figure is 25% what its own calls measured and 75% what every other stack shows about its transcriber, language model and voice, fitted across the whole sweep. The split is the same for every stack, so a lucky run does not lead and a stack's score does not move with how noisy its calls were. In an industry a stack has a handful of calls, so a cascade's figure there is what its transcriber, language model and voice show across every stack in that industry's calls, and a speech-to-speech model's is its own calls there. How a particular pairing beats or misses its parts shows on the main board, where each stack has all of its calls. The best overall pick, on the main board and in each industry, is the stack whose score is highest at the low end of its margin of error, so a few lucky calls cannot carry a stack past one whose score rests on hundreds. Stacks that share a rank are listed the same way, so the first row is the pick.
That order comes from real-world voice agent calls, where getting the conversation right predicts how a call ends more strongly than speed does. The latency points come from the same calls: replying faster than about 2 seconds made no measurable difference, and calls went measurably worse once the agent took more than about 3 seconds to reply.
Stacks and speech-to-speech
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Task completionscenario_adherence_check | 21% | 100% | 80% |
| An agent that completes fewer than four calls in five is not fit to deploy. On a full sweep, a cascade's figure is 25% what its own calls (20 or more) measured and 75% what every other stack shows about its transcriber, language model and voice, the same split for every stack, so a lucky run does not lead. Where the sweep is too small for that, and for a speech-to-speech model, the figure is the stack's own. In an industry a stack has a handful of calls, so a cascade's figure there is what its transcriber, language model and voice show across every stack in that industry's calls, and a speech-to-speech model's is its own calls there. How a particular pairing beats or misses its parts shows on the main board, where each stack has all of its calls. | |||
Response timeresponse_time | 17% | 2.0 s | 6.0 s |
| In real calls, replying faster than 2 s made no measurable difference, and calls went worse past 3 s. | |||
Instruction followinginstruction_follow | 13% | 5.0 / 5 | 3.0 / 5 |
| Every model scores between 3 and 5 on the judge's 1 to 5 scale, so that is the range. | |||
Semantic word error ratestt_semantic_word_error_rate | 13% | 0.5% | 3% |
| At 0.5% the best transcribers change the meaning of one word in two hundred on phone audio; at 3% one word in thirty sends the agent the wrong way. | |||
Tool usetool_use | 13% | 100% | 50% |
| An agent that mishandles its tools on half its calls cannot be trusted with the systems it runs on. | |||
Human-likenessvoice_human_likeness | 8% | 4.5 / 5 | 2.5 / 5 |
| 4.5 out of 5 is close to a person on the phone; 2.5 sounds plainly synthetic. | |||
Time to first wordtime_to_first_word | 4% | 1.0 s | 4.0 s |
| A greeting within 1 s sounds natural; 4 s of silence sounds like a dead line. | |||
Readback accuracytts_entity_readback_accuracy | 4% | 100% | 60% |
| Reading a code, amount or date wrong breaks the task it was for; the weakest voices get two in five wrong. | |||
Word error ratetts_word_error_rate | 4% | 2% | 12% |
| At 2% the voice says what it was given; at 12% one word in eight comes out wrong. | |||
Voice consistencyvoice_consistency_check | 4% | 100% | 80% |
| A voice that changes speaker on one call in five is not one a business can put its name to. | |||
Shown, not scored: Turn budget, Barge-in handlingbarge_in_yield_appropriateness
Counted only with price factored in: Cost per task
Language model
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Task completionscenario_adherence_check | 36% | 100% | 80% |
| An agent that completes fewer than four calls in five is not fit to deploy. | |||
Tool usetool_use | 27% | 100% | 50% |
| An agent that mishandles its tools on half its calls cannot be trusted with the systems it runs on. | |||
Instruction followinginstruction_follow | 18% | 5.0 / 5 | 3.0 / 5 |
| Every model scores between 3 and 5 on the judge's 1 to 5 scale, so that is the range. | |||
Time to first tokenllm_time_to_first_token | 18% | 0.50 s | 2.00 s |
| Under 0.5 s is not noticeable; at 2 s the first token alone takes two thirds of the 3 s past which real calls go worse. | |||
Shown, not scored: Prompt cache hitsllm_prompt_cache_hit_rate
Counted only with price factored in: Cost per call
Speech-to-Text
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Semantic word error ratestt_semantic_word_error_rate | 71% | 0.5% | 3% |
| At 0.5% the best transcribers change the meaning of one word in two hundred on phone audio; at 3% one word in thirty sends the agent the wrong way. | |||
Time to final transcriptstt_time_to_final_transcript | 29% | 1.00 s | 2.50 s |
| The fastest transcribers finish in about 1 s; past 2.5 s the transcript alone uses most of a natural reply time. | |||
Shown, not scored: Word error ratestt_word_error_rate
Counted only with price factored in: Cost per call
Text-to-Speech
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Readback accuracytts_entity_readback_accuracy | 32% | 100% | 60% |
| Reading a code, amount or date wrong breaks the task it was for; the weakest voices get two in five wrong. | |||
Word error ratetts_word_error_rate | 21% | 2% | 12% |
| At 2% the voice says what it was given; at 12% one word in eight comes out wrong. | |||
Time to first audio bytetts_time_to_first_byte | 21% | 0.20 s | 1.50 s |
| Under 0.2 s is not noticeable; 1.5 s is half the point where calls go worse. | |||
Human-likenessvoice_human_likeness | 16% | 4.5 / 5 | 2.5 / 5 |
| 4.5 out of 5 is close to a person on the phone; 2.5 sounds plainly synthetic. | |||
Voice consistencyvoice_consistency_check | 11% | 100% | 80% |
| A voice that changes speaker on one call in five is not one a business can put its name to. | |||
Counted only with price factored in: Cost per call
Factor in price and cost takes 25% of the score; the other weights keep their proportions. Price is scored on a log scale, so each doubling costs the same points.
A figure listed as shown, not scored is on the section’s boards and outside its score. Where a section has not collected a scored figure yet, the others share its weight.
Every call recorded and judged
Every call is recorded. Judge models score each transcript for the outcome and the conversation, and the timings come from the recording. Every figure links to the calls behind it.
Roark is on both sides of every call: it plays the caller, so it keeps the exact text its caller said, and it runs the agent under test, so it sees what the agent’s transcriber heard and what its model wrote for its voice. The transcript and voice figures come from lining those up, with no hand-made transcript in between. Each carries a margin from the synthetic voice or Roark’s transcriber in the loop. Every model faces the same ones under the same conditions, so the figures compare models on the same calls through the same voice and the same ear, though those slips need not fall evenly on each model. The rates will not match a vendor’s figure on a curated set; read them against each other.
An example: one call from this sweep
Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD, 23 October 2026. Highlighted turns are the ones that affected a score. Every stack's report links to its calls.
See how your own agent compares
Roark runs the same kind of calls against your agent, on your scenarios, with the same scoring.
Rank on Roark score
#47of 654 stacks
57 / 100
Leader AssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.6, 68 / 100
Where it ranks
Its models
Task completion
Task completion
How much of the caller’s task the agent completed: the share of the scenario’s checks a judge model found met in the transcript, averaged over calls. Before v1.3, the share of calls judged 4 or better out of 5.
#205 of 661 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#100 of 661 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#12 of 661 on the board · best 5.0 / 5
Turn-taking
Barge-in handling
When the caller interrupts, how often the agent made the right call: yielding to a real correction, and holding the floor through a filler.
Not scored by this sweep.
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 661 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#351 of 661 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 661 on the board · best 0.0 per call
Understanding & effort
Caller effort
How hard the caller had to work: repeating themselves, correcting, re-explaining. 1 = effortless.
Not scored by this sweep.
Repeated-info loops
Times per call the agent re-asked for something the caller had already given.
#155 of 493 on the board · best 0.0 per call
Speech-to-Text
Semantic word error rate
The caller's words the agent's transcriber got wrong in a way that changes the meaning, as a judge reads each difference.
#380 of 648 on the board · best 0.0%
Word error rate
The caller's words the agent's transcriber missed, changed or invented, against what the caller actually said.
#417 of 648 on the board · best 1.2%
Text-to-Speech
Readback accuracy
Share of the codes, amounts, dates and phone numbers the agent wrote that its voice read out correctly. One wrong digit is a miss.
#392 of 603 on the board · best 100%
Word error rate
The share of the words the agent wrote that its voice dropped or changed, read back from Roark’s transcription of the recording; the same transcriber hears every voice.
#469 of 648 on the board · best 1.9%
Voice
Human-likeness
How human the agent's voice sounds, scored by an audio model on intonation, rhythm and expressiveness. 5 = hard to tell from a person.
#30 of 659 on the board · best 4.3 / 5
Voice consistency
Share of calls where every line the agent spoke was the same speaker, with no change of speaker, gender or language voice partway. It checks who is speaking, not how they sound.
Not scored by this sweep.
#1 of 659 on the board · best 100%
Latency
Response time
The silence between the caller finishing and the agent starting to speak, measured from the recording on every turn of the call.
#45 of 660 on the board · best 0.50 s
Time to first word
How long the caller waits before the agent first speaks after pickup.
#226 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#119 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 2.83 s | — |
| Home services | 88% | 2.74 s | — |
| Insurance | 98% | 2.58 s | — |
| Customer support | 96% | 2.65 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 2.71 s | — |
| Spanish-accented English, city street | 91% | 2.66 s | — |
| Indian English, busy café | 94% | 2.62 s | — |
| Southern US, flustered, crying baby | 96% | 3.00 s | — |
| Fast and interrupting, construction outside | 89% | 2.48 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going
AGENTon with your service?
CUSTOMERYeah.
CUSTOMERInternet's been down for about two hours now. I work from home, and there's a road crew digging up the street right outside. Already rebooted the gateway twice. Checked all the cables. The Internet light is blinking orange. You check if the construction's the cause? I really need this fixed fast.
AGENTI'll help you get this sorted. Let me look up your account and check for any outages in your area right away. Can I get either your account number or the phone number on your account?
CUSTOMERUh-huh.
AGENTI'm
CUSTOMERYeah. Sure. Account number is BW883017. Sorry. Last digit is 1. And my phone number is (563) 227-0866.
AGENTNo problem. Let me pull
AGENTup your account and check for any outages in your area.
AGENTOkay, so there's no known outage in your area—but given the construction crew outside, they may have damaged the line.
CUSTOMERYeah.
AGENTThe line to
CUSTOMERRight.
AGENTGood
CUSTOMERYeah. That's what I figured. Is there any way you can confirm if that's the issue, or do I need a tech out here?
AGENTThe line itself is good, so the construction crew likely didn't damage it. Your gateway just needed that reset—it's registered and online now. Give your devices a couple minutes to reconnect, and you should be
CUSTOMERRight.
CUSTOMERYeah.
AGENTLet me know if you're back up and running. If you're still not seeing internet on your devices after a couple minutes,
AGENTwe can get a technician out
CUSTOMERLight just went solid white. How long does it usually take for the devices to reconnect? Since I lost two hours of work, can I get a credit for the downtime?
AGENTGreat—solid white means you're good. Devices typically reconnect within a couple minutes, but you should be seeing internet now.
CUSTOMERGot it.
AGENTYou're all set. I've
CUSTOMERYep.
AGENTYour account
CUSTOMERThanks for your help.
AGENTYou're welcome. Your account BW883017
AGENThas a $10.00 credit applied for the downtime—it'll show on your next bill. You're back online now. Take care!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I
AGENThelp you today?
CUSTOMERHi, Alex. I need to reschedule my dermatology appointment next Wednesday morning. Something came up at work, and I can't make that time. Can you help me move it?
AGENTI'd be happy to help you reschedule your dermatology appointment! To get started, I'll need to verify your identity. Could you please provide me with your full name and date of birth (in YYYY-MM-DD
AGENTformat)?
CUSTOMERSure. My name is Jordan Ellis. My date of birth is 03/17/1948. Sorry. No. 1984. 03/17/1984.
AGENTThank you, Jordan. So that's Jordan Ellis, date of birth March 17, 1984. Let me verify that for you.
AGENTGreat! I've
CUSTOMEROkay.
CUSTOMERRight. So I can only come after 3PM. Are there any openings later in the afternoon?
AGENTPerfect! Let me check Dr. Okafor's availability for afternoon slots after 3PM.
AGENTI found some available slots with Dr. Okafor. Looking at times after 3PM that match your needs, here's what's available: - Tuesday at 3:45 PM - Thursday at 4:10 PM Would either of those work for you?
CUSTOMERTuesdays don't work after all because I pick up my daughter. What about Friday?
AGENTUnfortunately, the only available slot on Friday with Dr. Okafor is at 11:30 AM, which is in the morning. That wouldn't work with your after 3PM requirement. Your best option would be Thursday at 4:10 PM. Does that work for
AGENTyou?
CUSTOMERYes. Thursday at 04:10PM works for me. Let's go with that.
AGENTPerfect! Let me
AGENTreschedule your appointment to Thursday at 4:10 PM.
AGENTExcellent! Your dermatology appointment
CUSTOMEROkay.
CUSTOMERIs there a
CUSTOMERfor changing the appointment?
AGENTLet me get that information for you.
AGENTHere's our change policy: Changes made more than 24 hours before the appointment are free. If you need to make a change within 24 hours of your appointment, there's a $40 fee. Since we just rescheduled your appointment to Thursday at 4:10 PM, you're all set! Your confirmation code is RVB-3M8P2. Please arrive 15 minutes early with your photo ID and insurance card. Is there anything else I can help you with?
CUSTOMERThe where should I park when I come in?
AGENTYou can use the free patient parking in Lot C, with the entrance on River Road. Is there anything else I can help you with?
CUSTOMERDoes doctor Okafur accept Aetna insurance?
AGENTI don't have access to insurance provider information through my system. For questions about which insurance plans Dr. Okafor accepts, I'd recommend calling the clinic directly during business hours—we're open Monday through Friday from 8:00 AM to 6:00 PM, and Saturday from 9:00 AM to 1:00 PM. Is there
AGENTanything else I can help you with?
CUSTOMERNo. That's everything I needed. Thank you, Alex. Goodbye.
AGENTYou're welcome, Jordan! Thanks for calling Riverbend Health Clinic.
AGENTHave a great day!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. I need help right away. There's water pouring out under my kitchen sink. A pipe has burst, and it's spreading across the floor toward a power strip. Can you send someone out to fix it? We really don't have time. So what's the fastest way to get this handled?
AGENTI'm glad you called. This is urgent—let's get you safe first, then get a technician out right away. Immediate safety steps: 1. Turn off the water main to your house right now. This will stop the water from pouring out. If you're not sure where it is, it's usually in the basement, garage,
CUSTOMERYep.
AGENTGreat—go
CUSTOMERRight.
AGENTOkay,
CUSTOMERSo, like shut the water off. What's next? How soon can someone get here? What will the visit cost?
AGENTPerfect. Once the water is off, keep everyone and pets away from that power strip and wet area until our technician arrives—don't touch it. Now let me get you scheduled. I need a few details: What's your phone number or street address so I can look up your account? Once I have that, I'll check emergency availability and pricing, and get someone
AGENTout to you as fast as
CUSTOMEROkay. Sure. I need this handled fast. My address is 1480 Larkspur Avenue. I just moved from Unit 4 B to 4 D last month, so it's 4 D now. My callback number is (503) 555-0139. No. Zero one nine three.
AGENTGot it.
AGENTLet me pull up your account and check emergency availability and pricing.
AGENTNow let me look up your account:
AGENTPerfect—I found your account. I see you're a Copperline Care member, which is great. Here's what I've got for you: Emergency availability: We can get a technician to you today between 2:00 PM and 4:00 PM. Cost: As a Copperline Care member,
CUSTOMERRight.
AGENTAs
CUSTOMERCan anyone come before two? I really need the earliest possible window.
AGENTI understand—that 2:00 PM to 4:00 PM window today is the earliest emergency slot available right now. I know
CUSTOMERGet it. What? I need someone sooner. Is there any way to get help before two? Alright. Just book that two 2PM to 4PM window for me. Who's coming out, and how will I know they're on their way? Need the ticket number too.
AGENTI hear you—let me book that 2:00 PM to 4:00 PM window
AGENTfor you right now. First, let me create the
AGENTservice request: Now let me book the visit:
AGENTPerfect. Here's
AGENTyour confirmation: Ticket Number: CPL-58210 Service Address: 1480 Larkspur Avenue, Unit 4D Callback Number: (503) 555-0139 Appointment: Today, 2:00 PM to 4:00 PM Technician: Dana Cost: $99 (Copperline Care member emergency fee) Dana will text you 30 minutes before arrival so you know when to expect them. Keep that water main off and stay away from the wet area near the power
CUSTOMERYeah.
AGENTYou're
CUSTOMERThat works. Thanks for your help. I'll keep an eye out for Dana and the techs. Goodbye.
AGENTYou're welcome. Stay
AGENTsafe, and we'll get that burst pipe fixed today. Goodbye!
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes. I am synced. I'm standing next to my car in a cafe nearby.
AGENTGood, I'm glad you're safe. Is anyone injured—you, your passengers, or
AGENTanyone else involved in the accident?
CUSTOMERNo. Nobody is injured. Everyone is alright.
AGENTThat's a relief. I'm here to help you file a claim. Let me start by verifying your policy. Can you give me your policy number and your last
AGENTname, please?
CUSTOMERSure. The policy number is NG4471903. No. Sorry. Last one is two. My last name is Mehta.
AGENTThanks for clarifying. So your policy number is NG4471902, and your last name is Mehta. Let me verify that for you.
AGENTPerfect. Your policy is verified. I see you have a 2021 Honda CR-V
CUSTOMERYeah. That's right. So I need to file a claim. Another car hit the back of my car while I was stopped at a red light. The back bumper is crushed, and the rear wheel is rubbing. I cannot drive it. Can you let me know how much I will have to pay?
AGENTI understand—that sounds like a rough situation. Let me get the details I need to open your claim, and then I can look up your coverage details for you. First, can you tell me: 1. When did this happen? 2. Where exactly did it happen? 3. Do you have information about the other driver? 4. Did police come to
AGENTthe scene?
CUSTOMERYes. I can give you those details. It happened about twenty minutes ago. The location is S E 5th Avenue and Alder Street. The other driver is Kevin Lund. Insured with Pacific Shore. Plate number 7KX like X-ray, R214. Police did not come to the scene.
AGENTGot it.
AGENTLet me open your
CUSTOMEROkay.
AGENTOkay, so here's your coverage: - Collision deductible: $500 - Rental reimbursement: $40 per day for up to 30 days, starting from when the claim opens - Towing: Covered up to 25 miles Now let me open your claim with the information you've given me.
AGENTPerfect. Your claim is now open. Here's what you need to know: Claim Number: NGM-904417 Your Assigned Adjuster: Priya Shah Adjuster Contact: Within one business day Now, since your vehicle isn't drivable, I can arrange a tow truck for you. We cover towing up to 25 miles. Where would you like the vehicle towed to?
CUSTOMERYes. Please arrange a tow truck. Where will the car be taken? Will it go to a repair shop nearby? Or do I need to specify a location?
AGENTGood question. You can specify where you'd like it towed—a repair shop, your home, or anywhere else within 25 miles of where the car is now. Do you have a preferred location, or would you like me to tow
AGENTit to a specific repair shop?
CUSTOMERI do not have a preferred repair shop right now. You recommend a nearby repair shop? Or arrange for it to be taken to one close to S E 5th Avenue and Alder Street?
AGENTI can arrange the tow to your current location at S E 5th Avenue and Alder Street, and the tow service can take it to a nearby shop. But I need a specific destination address to dispatch the truck. Do you know of any repair shops in that area, or would you prefer I tow it somewhere else—like
AGENTyour home? What works best for you?
CUSTOMERKindly arrange for the car to be towed to a nearby repair shop. I do not know the addresses. So please select one close to SE 5th Avenue and Alder Street. That works best for me.
AGENTI understand you'd like a nearby shop, but I need a specific address to dispatch the tow truck. I'm not able to look up repair shops or select one for you. Here are your options: 1. You can search online right now for a repair shop near SE 5th Avenue and Alder Street and give me the address 2. I can tow it to your home if you provide that address 3. You can call your adjuster, Priya Shah, within one business day and she can help coordinate where the car should go for repairs What would work best for you?
CUSTOMERI am outside right now and do not have the address of a repair shop. Kindly arrange for the tow to my home address instead. The car can be taken there. Would you like me to provide the address now?
AGENTYes, please. Go ahead and give me your home address, and I'll arrange for
AGENTthe tow truck right away.
CUSTOMERMy home address is 2347 S E 9th Avenue, Portland, Oregon. 97214. Please arrange for the tow truck to take the car there. Can you tell me, since the other driver hit me, do I still have to pay the $500 deductible? And will my premium go up because of this accident?
AGENTI'll arrange the tow to your home right now. For your questions about the deductible and premium—those are good questions, but I can only tell you what your coverage shows.
CUSTOMERAlright.
AGENTGreat.
CUSTOMEROkay. So right. So I just wanna confirm. Since he hit me, I should not have to pay the $500 deductible. Correct? And will my premium increase because of this claim?
AGENTThose are important questions, but I can only tell you what your policy covers. Your collision deductible is $500. Questions about whether the deductible applies in this situation, and whether your premium will increase—those are things your adjuster, Priya Shah, will discuss with you. She'll contact you within one business day. What I can confirm for you right now is: Policy Number: NG4471902 Other Driver's License Plate: 7KXR214 Claim Number: NGM-904417 Assigned Adjuster: Priya Shah (will contact you within one business day) Tow Truck Details: - Tow Company: Eastside Towing - ETA: 45 minutes - They'll take your car
CUSTOMERYes.
AGENTYour car
CUSTOMERThat's right. You let me know when the tow truck will arrive? And if I need to do anything else right now?
AGENTThe tow truck from Eastside Towing should arrive in about 45 minutes. The driver will need a phone number to reach you when they arrive. Can you give me a callback
AGENTnumber for them?
CUSTOMERYes. My phone number is (573) 790-8157. Please have the tow truck driver call me when they arrive.
AGENTPerfect. I've got your phone number as (573) 790-8157. The tow truck driver will call you when they arrive. Here's a summary of everything: Policy Number: NG4471902 Other Driver's License Plate: 7KXR214 Claim Number: NGM-904417 Assigned Adjuster: Priya Shah (will contact you within one business day) Tow Truck: - Company: Eastside Towing - ETA: About 45 minutes - Your callback number: (573) 790-8157 - Destination: Northgate partner repair shop at 9th and Morrison Your adjuster Priya Shah will call you within one
AGENTbusiness day to discuss next steps, including your deductible and any other questions you have. Is there anything else I can help you with right now?