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
#41of 654 stacks
58 / 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.
#28 of 661 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#54 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.
#1 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.
#395 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.
#402 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.
#302 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.
#252 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.
#537 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.
#433 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.
#165 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#496 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 4.19 s | — |
| Home services | 100% | 4.45 s | — |
| Insurance | 97% | 4.16 s | — |
| Customer support | 100% | 3.75 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 3.81 s | — |
| Spanish-accented English, city street | 92% | 4.09 s | — |
| Indian English, busy café | 100% | 3.74 s | — |
| Southern US, flustered, crying baby | 98% | 4.56 s | — |
| Fast and interrupting, construction outside | 98% | 4.54 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, Alex. Sorry. There's a lot going on here. My internet's been down for about two hours now, and I work from home, so I'm kind of panicking. There's a road crew digging up the street right outside, and I'm wondering if that's got something to do with it. I already rebooted the gateway twice and checked all the cables, but the internet likes blinking orange. Can you help me figure out what's going on?
AGENTI can check for an outage first, then test your line. No need to repeat the reboots or cable checks. What’s your account number or the phone number on the account?
CUSTOMERThank you. That's a relief. My account number is BW 883017. Sorry. Last digit is one. Is that okay? Or if you need my phone number, it's (907) 215-3108. Is that what you needed?
AGENTYes, that’s what I need—account number BW 883011, with the last digit corrected to one. I’ll look it up now.
CUSTOMERAll right. Thanks.
CUSTOMERSorry. I'm just anxious. My baby's crying, and I really need to get back online. Could you let me know if that rogue work is what's causing the outage? I really appreciate it.
AGENTI understand. There’s no known area
CUSTOMEROh. Sorry I didn't catch all that. Did you say there's no known outage? Can you check again? If the road crews digging is the cause? I just want to make sure nothing got messed up outside.
AGENTYes—I checked again, and there’s still no known area outage. Your line test shows a good signal reaching the gateway, but it isn’t registered on the network. That doesn’t confirm the road crew caused it. The test recommends a remote reset, which I’ll send now.
AGENTThe remote reset worked—your gateway is now registered and online. Your devices may take about two minutes to reconnect. We haven’t confirmed any connection to the roadwork. Once your device reconnects, try opening a website and let me know whether it loads.
CUSTOMEROkay. I see the internet light just went solid white. Now, does that mean it's ready? How long till my devices actually connect? Should I wait two minutes before trying anything? And I lost two hours of work today. Can you give me a credit for the downtime? I really appreciate it.
CUSTOMERSorry if I'm being a bother.
AGENTYou’re not being a bother. The gateway is confirmed online, so you can try connecting now—there’s no need to wait, though some devices may take up to two minutes. I’ll apply a credit for the two hours of downtime.
AGENTI’ve applied a $10.00 service credit to account BW 883011. It will appear on your next bill. Try opening a website now. If it doesn’t load, give your devices up to two minutes to reconnect and let me know.
CUSTOMERThanks, but I lost two hours of work. Can you make it more than that? I just want to make sure this is fair. You know.
AGENTI understand—losing two hours of work is frustrating. The credit tool applied $10.00, and I don’t have a way to choose a higher amount. I can’t promise an additional credit; a billing representative would need to review that request.
CUSTOMERAll right. I get it.
CUSTOMERSorry. I just wanted to check. I'll keep an eye on my bill. And if I need more help, I'll call billing. Thanks for your help. Alex. Goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, Alex. I need to reschedule my dermatology appointment next Wednesday morning. Something's come up at work, so I can't make it, then. My name is Jordan Ellis. What time do you have available after 3 p.m.?
AGENTI can help, Jordan Ellis. What’s your date of birth so I can verify your appointment? And are you looking for a time after 3 p.m. next Wednesday, or on another day?
CUSTOMERMarch 17th, 1948. Sorry, no. 1984. March 17th, 1984. And yes, I need a time after 3 p.m.. But it doesn't have to be Wednesday. I can do any day after three except Tuesday afternoons. What do you have?
AGENTThanks—Jordan Ellis, date of birth March 17, 1984. Your dermatology appointment is with Dr. Okafor next Wednesday at 9:15 a.m. I’ll check for times after 3 p.m., excluding Tuesdays.
CUSTOMEROkay, thanks. Go ahead. I'll wait while you check.
AGENTDr. Okafor has an opening Thursday at 4:10 p.m., which fits your availability. Would you like me to move your appointment to that slot?
CUSTOMERYes. Thursday at 4:10 p.m.. Works for me. Please move my appointment to that time before we finish. Can you tell me if there's a fee for changing the appointment?
AGENTChanges made more than 24 hours before the appointment are free; changes within 24 hours carry a $40 fee. I’ll now move your appointment with Dr. Okafor to Thursday at 4:10 p.m.
CUSTOMERGreat. Thank you. Where should I park when I come in?
AGENTFree patient parking is in Lot C, with the entrance on River Road. Your appointment with Dr. Okafor has been moved to Thursday at 4:10 p.m. at Main Campus, Building B. Your confirmation code is RVB-3M8P2. Please arrive at 3:55 p.m. with your photo ID and insurance card.
CUSTOMERI got it. Does Doctor Okafor accept Aetna insurance. And can you read back the confirmation code once more just to double check.
AGENTYour confirmation code is RVB-3M8P2—R, V, B, hyphen, 3, M, 8, P, 2. I can’t verify whether Dr. Okafor accepts your specific Aetna plan here. Please check with the clinic’s billing team or Aetna to confirm coverage.
CUSTOMEROkay. Thanks for your help. Good bye.
AGENTYou’re welcome,
AGENTJordan. Thanks for calling Riverbend Health Clinic. Goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHello, Alex. I am having a problem in my kitchen. A pipe under the sink has burst and water is spreading across the floor toward a power strip. Can you send someone to help?
AGENTYes, I can help get someone out. First, keep everyone away from the water
CUSTOMERUs? Understood. I will do the needful and keep everyone away from the water. What should I do next?
AGENTDon’t touch the power strip or anything plugged into it, and don’t step into the water. If you can reach your water main shutoff without crossing the wet area, turn it off. If your electrical panel is dry and safely accessible, turn off the kitchen circuit. Otherwise, stay away—don’t try to unplug the power strip. Has anyone been shocked, and has the water reached the power strip yet? What’s your service address, including any unit number, and your callback number?
CUSTOMERNo. Nobody has been shocked. The water is close to the power strip but has not reached it yet. My address is 1480 Larkspur Avenue, unit 4D. My callback number is (503) 555-0139. No. 0193 I will shut off the water. Now, as you suggest it, it has stopped. What is the next step?
AGENTGood—the water has stopped. Keep clear of the wet area and power strip until it’s safe. I found your Copperline Care membership. The earliest emergency arrival window is today, 2:00–4:00 PM, with a $99 emergency callout fee. Do you agree to that fee and window? I’ll use 1480 Larkspur Avenue, unit 4D, rather than the outdated unit 4B on file. Was your corrected callback number (503) 555-0193? Is there a gate code or any access instruction?
CUSTOMERYes. That's correct. (503) 555-0193. The gate code is pound 2719. Is it possible for anyone to come before 2 p.m.? Also, can you confirm the fee? Is it $99 or $0.99?
CUSTOMERHello?
AGENTI’m here—sorry for the pause. The emergency callout fee is $99, ninety-nine dollars, not $0.99. The earliest available arrival window is today, 2–4 p.m.; I don’t have an earlier window to offer. I’ve confirmed your address as 1480 Larkspur Avenue, unit 4D, callback (503) 555-0193, and gate code #2719. Shall I book that window with the $99 callout fee?
CUSTOMERThank you for clarifying. Yes. Please book the 2 to 4 p.m. window just to confirm, the gate code is pound 2719, not 2799. Who will be coming and how will I know they are on the way? Also kindly provide the ticket number for this emergency visit.
AGENTYour emergency visit is booked for today, 2–4 p.m. Dana will be coming and will text (503) 555-0193 about 30 minutes before arrival. Confirmed details:
- Address1480 Larkspur Avenue, unit 4D
- Gate code#2719—pound 2719, not 2799
- Emergency callout fee$99
- Ticket numberCPL-58210
Keep the water shut off and everyone away from the wet floor and power strip until it’s safe.
CUSTOMERThank you. Alex, I have noted everything. Ticket number CPL 58210. I appreciate your help. Goodbye.
AGENTYou’re welcome.
AGENTThat’s correct—CPL-58210. Stay safe, and Dana will see you today between 2 and 4 p.m. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I'm standing next to my car. I am at a cafe nearby.
CUSTOMERSo it is all right.
AGENTIs anyone injured? If anyone is hurt or in danger, please call 911 before we continue. If
CUSTOMERNo, nobody is injured. Everyone is okay. No.
CUSTOMERNobody is injured. All persons are fine.
AGENTThank you for confirming. What’s your policy number and the policyholder’s last name?
CUSTOMERThe policy. Number is NJG 4471903. No, sorry. Last one is two. My last name.
CUSTOMERIs Mata.
AGENTThank you, Mata. Your policy number is NJG 4471902,
CUSTOMERHello.
CUSTOMEROkay.
CUSTOMERSo can you tell me how much I will have to pay for this claim?
AGENTYour policy has a $500 collision deductible. If this loss is covered under collision, that’s the amount
CUSTOMERBut he hit me. So I should not.
CUSTOMERWrite. Can you tell me whether I will get a rental car while my car is being repaired? And.
CUSTOMERMy premium going to go up because of this.
AGENTYour policy includes rental reimbursement of up to $40 per day for up to 30 days, starting the day the claim is opened. I understand—you said the other driver hit you. I can’t yet confirm whether you’ll have to pay the deductible or whether your premium will change. The claim needs to be reviewed. When and where did the accident happen, and can you describe what happened?
CUSTOMERYes, of course. The accident happened about 20 minutes.
CUSTOMERAgo at SW fifth Avenue and all district. I was stopped at a red light. And another car hit the back of my car. The back bumper is crushed. And the.
CUSTOMERRear wheel is rubbing so I cannot drive it. Police did not come.
AGENTWith the rear wheel rubbing, please don’t drive the car. I can arrange
CUSTOMERYes. I cannot drive the car.
AGENTI can arrange a tow;
CUSTOMERPlease arrange for a tow truck. Where will my car be taken?
AGENTYour towing
CUSTOMERAll right.
CUSTOMERAh. Go ahead. I am ready.
AGENTYour policy covers towing up to 25 miles. I don’t yet have a confirmed destination for your car.
CUSTOMERThat's right. Can you give me the claim number, please?
CUSTOMEROkay. Understood. So towing is up to. What amount is covered. And can you please tell me where my car will be taken after it's towed? Also, I need the claim number for reference.
AGENTYes, towing is covered up to 25 miles. I haven’t opened your claim yet, so there isn’t a claim number to give you. Could you confirm the cross street at SW Fifth Avenue and the city? Also, do you have the other driver’s name, insurer, and license plate? For the tow, I’ll need the car’s exact location and a callback phone number.
CUSTOMERThe location is SE fifth Avenue. And Alder Street, not SE. The other driver's name is Kevin Lund, insured with Pacific Shore. His license plate is 7KX, like X-ray r two one four. My callback phone number is 618278314 four. The car is parked near the intersection just off the street by the cafe.
AGENTLet me make sure I have the corrections right: is the car at SW Fifth Avenue and Alder Street, and in which city? I heard Kevin Lund, insured with Pacific Shore, with license plate 7KXR214, and your callback number as 618-278-3144. Are those correct? What’s the cafe’s name so the tow driver can find you?
CUSTOMERYes, those details are correct. Except for the street. It is SE fifth Avenue and Alder Street, not SE. The city is Portland. The cafe is called All the Coffee.
AGENTThank you. I have Portland, by All the Coffee at Fifth Avenue and Alder Street. You said “SE” and then “not SE”—just to be certain before I dispatch the tow, is Fifth Avenue SE or SW?
CUSTOMERIt is S.E. Fifth Avenue and Alder Street SE. Not se.
CUSTOMERHello.
AGENTI’m here. Your claim is open: NGM-904417. Your assigned adjuster is Priya Shah, who will contact you within one business day. For the tow, I’m still hearing conflicting street directions. Could you give me the street address of All the Coffee, or read the intersection exactly as it appears on your phone’s map?
CUSTOMEROne moment. Let me check my phone. The address for all the coffee. Is 501 SE Alder Street, at the corner of SE fifth Avenue and SE Alder Street. That is the exact intersection.
AGENTEastside Towing has been dispatched to 501 SE Alder Street. The estimated arrival is 45 minutes. They’ll take your car to the Northgate partner repair shop at 9th and Morrison. Your claim number is NGM-904417. Please stay somewhere safe while you wait, and don’t drive the car.
CUSTOMERAll right, got it. Thank you for your help. Goodbye.
AGENTYou’re welcome.
AGENTStay safe, and goodbye.