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
#21of 654 stacks
59 / 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.
#177 of 661 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#1 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.
#304 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.
#180 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.
#512 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.
#426 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.
#348 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.
#179 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.
#7 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.
#100 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.
#320 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 | 95% | 2.79 s | — |
| Home services | 92% | 2.97 s | — |
| Insurance | 92% | 3.10 s | — |
| Customer support | 98% | 2.94 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 96% | 2.83 s | — |
| Spanish-accented English, city street | 98% | 2.97 s | — |
| Indian English, busy café | 92% | 2.72 s | — |
| Southern US, flustered, crying baby | 98% | 3.08 s | — |
| Fast and interrupting, construction outside | 87% | 3.33 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey. Yeah. So I work from home, and my internet's been down for two hours now. There's a road crew digging up the street right outside, so I'm guessing that might be the reason. I already rebooted the gateway twice and checked every cable. The internet light is blinking orange. Can you check what's happening? I really need this fixed fast.
AGENTI'll help you get this sorted. Let me pull up your account and check for an outage in your area. Can I get either your account number or the phone number on your account?
CUSTOMERDied.
AGENTSorry, I didn't
CUSTOMERYeah, sure. No worries. Here's my account number BW883017. Sorry, last digit is one.
AGENTGot it—account BW883017. Let me check for any outages in your
CUSTOMERGot it.
AGENTNo
CUSTOMERYep. That's right. Just a heads up, it's BW883011. Last digit is one go ahead. Can you see if the road crew outside is causing this?
AGENTGot it—BW883011. Let me check for outages at your address.
AGENTNow
CUSTOMERRight, thanks.
CUSTOMERYeah. Please check now. I really need this backup. I lost two hours of work already.
AGENTI understand—let me run a line test to see what's happening with your connection.
AGENTThe line test shows your gateway isn't registering, but the signal is good. Let me send a remote reset to your gateway now.
AGENTGood news—the reset worked. Your gateway is now registered and online. Give your devices about two minutes to reconnect, and you should be back up.
CUSTOMERYeah, I just went solid white. How long does it usually take for everything to come back online? Since I lost two hours of work. Can I get a credit for the downtime?
AGENTGreat—solid white means it's fully online now. Your devices should reconnect within a couple minutes. Let me apply a credit for those two hours of downtime.
AGENTDone.
CUSTOMERYeah.
AGENTYou're all set.
CUSTOMERI.
AGENTAnything
CUSTOMERI lost.
CUSTOMERTwo hours of work. Can you. Make it more than that?
AGENTI hear you—that's frustrating. I've
CUSTOMERAll right.
CUSTOMERYeah, it really is. Thanks for. Sorting it out so quickly. Goodbye.
AGENTYou're welcome. Your account
AGENTBW883011 has a $10.00 credit applied for the downtime—it'll show on your next bill. Glad we got you back online. Take care!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERYes, hello. I am having one dermatology appointment next Wednesday morning and I need to move it because I have a work shift now. My name is Arjun Mehta. Can you help me reschedule?
AGENTHi Arjun! I'd be happy to help you reschedule your dermatology appointment. To verify your account, I'll need your date of birth. Could you provide that for me in the format MM/DD/YYYY
CUSTOMERYes. Of course. March 17th, 1948. Sorry. No. 1984. March 17th, 1984.
AGENTThank you, Arjun. So that's March 17th, 1984. Let me pull up your account.
AGENTGreat! I've verified your account. Now let me find your upcoming appointments.
AGENTPerfect! I found your appointment. You have a dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at the Main Campus, Building B. You mentioned you need to move it because of a work shift. What day and time would work better for you? And do you have any other time constraints I should know about?
CUSTOMERYeah. I can only come after 3 p.m.. Is there any slot available after three. Please.
AGENTLet me check Dr. Okafor's availability for slots after 3 p.m.
AGENTI found a couple of options after 3 p.m. for you: 1. Tuesday at 3:45 p.m. (15:45). 2. Thursday at 4:10 p.m. (16:10). Which of these works better for your schedule?
CUSTOMERTuesdays do not work after all. I'm picking up my daughter that day. What about Friday? Is there anything on Friday after 3 p.m.?
AGENTUnfortunately, the only Friday slot available with Dr. Okafor is at 11:30 a.m., which is before 3 p.m. So your best option after 3 p.m. is Thursday at 4:10 p.m. Does that work for you?
CUSTOMERYes. Thursday at 4:10 p.m.. Works for me. Please book that slot.
AGENTPerfect! Let me reschedule your appointment to Thursday at 4:10 p.m.
AGENTExcellent! Your appointment has been rescheduled. Here are your details: Appointment Confirmation. - Name: Arjun Mehta. - Provider: Dr. Okafor (Dermatology). - New Day & Time: Thursday at 4:10 p.m. - Location: Main Campus, Building B. - Confirmation Code: RVB-3M8P2. Please arrive 15 minutes early with your photo ID and insurance card. Is there anything else I can help you with?
CUSTOMERYes. May I ask, is there any fee for changing the appointment?
AGENTThat's a great question. Let me check our change policy for you.
AGENTGood news! According to our policy, changes made more than 24 hours before the appointment are free. Since your original appointment was next Wednesday and you're rescheduling now, you're well within that window, so there's no fee for this change. Is there anything else I can help you with today?
CUSTOMEROkay. Thank you. Where should I park for the appointment?
AGENTYou can park in Lot C, which has free patient parking. The entrance is on River Road. Is there
CUSTOMERAha! Got it. One more thing. Does Doctor Okafor accept Aetna insurance?
AGENTI don't have access to information 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 a.m. to 6:00 p.m., and Saturday from 9:00 a.m. to 1:00 p.m. They'll be able to confirm your coverage right away. Is there anything else I can help you with?
CUSTOMERNo. That's all. Thank you for your help. Goodbye.
AGENTYou're welcome, Arjun! Thank you for choosing Riverbend Health Clinic. Have a great day,
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. I have an emergency in my apartment. The pipe under my kitchen sink has burst and water is spreading across the floor, heading toward a power strip. I need someone to come out as soon as possible. Can you help with that?
AGENTI can absolutely help. This is serious—let
CUSTOMEROkay.
CUSTOMERYes, it's pretty urgent. What should I do? Right now, I haven't set the water off yet. Can you tell me how to do that?
AGENTYes, absolutely—do this right now: Shut off the water immediately. Look for the water shut-off valve under your kitchen sink first—it should be on the pipe coming in. Turn it clockwise as far as it will go. If you can't find it or it won't turn, go to your main water shut-off valve. This is usually in a basement, crawl space, or utility closet—look for the main line coming into your apartment. Turn that valve clockwise to stop all water flow. Then move that power strip away from the water or unplug it if you can do so safely without stepping in water. Once you've shut off the water, let me know and we'll get a technician out to you right away. Have you been able to locate the shut-off valve?
CUSTOMERYes, I found it and turned it off. The water has stopped now. Oh. I moved the power strip to. So that's safe. Can you send someone out? And how much will the visit cost?
AGENTGreat work—you've made this safe. Now let me get you set up with a technician. I need a few details
CUSTOMEROkay. Go ahead.
AGENTI need your phone number and your street address so I can look up your account. What's the best number to reach you at, and what's your full address including your apartment number?
CUSTOMERMy phone. Number is 503 5550139. No, 0193. The address is one 480 Larkspur Avenue, apartment four D. I moved from four B to 4D last month. Just to be clear.
AGENTGot it. Let me look that up for you.
AGENTI found your account, but it shows your unit as 4B. You just mentioned you moved to 4D last month—is that correct? I want to make sure we send the technician to the right place.
CUSTOMERYes, that's right. I'm in unit 4D now. Please send the technician to 1480 Larkspur Avenue, apartment 4D.
AGENTPerfect, I've got that. You're at 1480 Larkspur Avenue, apartment 4D. Now let me check availability for an emergency visit and get you booked.
AGENTExcellent news.
CUSTOMEROkay. Go ahead.
AGENTHere's what I have for you: Emergency visit today, 2:00 PM to 4:00 PM. You're a Copperline Care member, so the emergency callout fee is $99. This covers the technician's visit to assess and begin repairs on the burst pipe. Does that work for you? Should I go ahead and book the 2:00 PM to 4:00 PM window today?
CUSTOMERIs there any way someone. Could come before 2 p.m.? The situation is pretty urgent. If that's not possible, I'll take the earliest emergency window you have.
AGENTI understand—that 2:00 PM to 4:00 PM window today is the earliest emergency slot available. Unfortunately, I can't offer anything sooner than that. That's your best option for an emergency visit. Should I book that for you?
CUSTOMERYes. Go ahead and block the. 2 p.m. to 4 p.m. window. Who will be coming? And how will I know when they're on their way? Also, can you give me the ticket number for this visit?
AGENTLet me open the service request and book that window for you.
AGENTNow let me book
CUSTOMERAll right.
AGENTPerfect. Here's your confirmation: Ticket Number: CPL-58210. Service Address: 1480 Larkspur Avenue, apartment 4D. Appointment: Today, 2:00 PM to 4:00 PM. Technician: Dana.
CUSTOMEROkay. Got it. So will the technician be. And how will I know when they're on the way?
AGENTDana will be your technician. You'll get a text message to 503-555-0193 about 30 minutes before Dana arrives, so you'll have a heads up. Is there anything else you need, or do you have
CUSTOMERNo. That's everything I needed. Thank you for your help. Goodbye.
AGENTYou're welcome!
AGENTStay safe, and Dana will be there this afternoon. Goodbye!
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I'm at home right now. Sorry. I'm pretty flustered. I got a little one here crying. I'm safe though. Just can't drive my car because the back end is all messed up. Is that going to be a problem?
AGENTI'm sorry you're dealing with this. Don't worry—we'll get this sorted out. The fact that you're safe at home is what matters most right now. First,
CUSTOMERI. Thank you. That's a relief. I really appreciate it. Uh, so I need to file a claim. Another car hit me about 20 minutes ago at SW fifth Avenue and Alder Street. I was stopped at a red light, and they just ran right into the back of me. Nobody's hurt, but the bumper is crushed and the rear wheels rubbing so I can't drive it. Is that okay for you to start the claim?
AGENTI'm glad nobody's hurt. That's the
CUSTOMEROh. Yeah. Thanks. I'm glad to. I've got my policy number here. Do you need that now or do you want more details first?
AGENTI'll need your policy number now to verify your coverage. Go ahead and give that to me.
CUSTOMERAll right. I hope I'm reading this right. It's NG4471903. Oh wait sorry, last one is two. Is that okay?
AGENTNo problem. Let me get that straight—your policy number is NG4471902. And what's your last name so I can verify the policy?
CUSTOMERYeah that's right. Thank you for checking. Uh, my last name's Carter. Is that going to pull up my policy? All right.
AGENTLet me verify that for you now.
CUSTOMEROh. Sorry. Just checking in. Did you find my policy okay, or do you need anything else from me?
AGENTGreat news—your policy is verified. I've got you down as a 2021 Honda CR-V with collision coverage, rental reimbursement, and roadside towing. Now let me get the details of what happened so I can open your claim. You said another car hit you from behind at SW Fifth Avenue and Alder Street about 20 minutes ago while you were stopped at a red light. Do you have the other driver's name, their insurance company, and their license plate number?
CUSTOMEROh. Thank goodness. That's a relief. Uh, yeah, I've got all that right here. The other driver's name is Kevin Lund. He's insured with Pacific Shore. And the. License plate is 7KX, like X-ray R 214. Is that enough for you?
AGENTGot it. So the other driver is Kevin Lund with Pacific Shore insurance, and the license plate is 7KX R 214. Did police come to the scene and file a report?
CUSTOMERNo. Sorry. The police didn't come out. I called, but they said since nobody's hurt and it's not blocking traffic, they wouldn't send anybody. Is that going to cause any trouble for the claim?
AGENTNo trouble at all. That happens sometimes. Okay, I've got everything I need. Let me open your claim now.
AGENTPerfect. Your claim is now open. Here's what you need to know: Claim number: NGM-904417. Your assigned adjuster is Priya Shah, and she'll be in touch with you within one business day. Now, you mentioned the car isn't drivable. Do you need me to arrange a tow truck to pick it up from your home?
CUSTOMEROh, yes. Please. I really appreciate that. I'm worried about leaving it here with the wheel rubbing. Uh. where's the car going to be taken? And could you tell me again? Claim number is NGM904417, right?
AGENTLet me arrange that tow for you right now. The tow truck will come to your home. I'll need a callback number so the driver can reach you when they're on the way.
AGENTActually, I need your phone number first so the driver can call you. What's the best number to reach you?
CUSTOMERSure. Sorry if this is a bother, my number is (907) 416-2671. Is that all right?
AGENTPerfect. Let me get that tow arranged now.
AGENTGreat. Your tow is dispatched. Eastside Towing will be there in about 45 minutes, and they'll take your 2021 Honda CR-V to our partner repair shop at 9th and Morrison. They'll call you at (907) 416-2671
CUSTOMERI.
CUSTOMERYeah that's right. 2671. Thank you for confirming that. Uh, can I ask how much am I supposed to pay out of all this? Is there a deductible or anything?
AGENTThat's a good question. Let me pull up your coverage details for you.
AGENTHere's your coverage: Your collision deductible is $500. That's what you'll pay toward the repair. Your rental reimbursement covers up to $40 a day for up to 30
CUSTOMERBut he hit me, so I. Should not have to pay that. Right? Sorry. I just want to make sure I'm not missing something. And, uh, does that mean I get a rental car while mine's in the shop?
AGENTI understand your frustration—you're right that the other driver hit you. However, your deductible applies to your collision coverage regardless of who was at fault. That's how collision coverage works.
CUSTOMERI. All right. I guess. That makes sense. I just wanted to be sure I wasn't stuck paying for something I didn't cause. Uh, about the rental. Do I get one right away, or do I need to wait for the adjuster to call? And it's my premium. going to go up because of this? I'm a little worried about that.
AGENTGood questions. Your rental reimbursement is $40 per day for up to 30 days, starting from today when the claim opened. You can arrange a rental car right away—you don't have to wait for the adjuster. As for your premium, I don't have information about that. Those questions are best answered by your adjuster, Priya Shah. She'll be calling you within one business day, and that's a perfect time to ask her about your premium and any other concerns you have. Let me make sure I have everything straight for you: - Policy number: NG4471902. - Your vehicle: 2021 Honda CR-V. - License plate: 7KX R 214. - Claim number: NGM-904417. The tow truck will be there in about 45 minutes. Is there anything else I can help you with right now?
CUSTOMERNo, that covers it. Thank you. Uh, you've been really helpful. I appreciate you taking the time. Goodbye.
AGENTYou're very welcome. I'm glad I could help. Take care,