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
#171of 654 stacks
53 / 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.
#162 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.
#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.
#179 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.
#290 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.
#467 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.
#337 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.
#476 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.
#254 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.
#124 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#220 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 97% | 3.46 s | — |
| Home services | 95% | 3.39 s | — |
| Insurance | 95% | 3.13 s | — |
| Customer support | 91% | 3.45 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 3.63 s | — |
| Spanish-accented English, city street | 96% | 3.26 s | — |
| Indian English, busy café | 96% | 3.17 s | — |
| Southern US, flustered, crying baby | 95% | 3.75 s | — |
| Fast and interrupting, construction outside | 87% | 3.11 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey. Sorry. I'm a little flustered here. My Internet's been down for about two hours now, and I work from home. So it's been kinda stressful. Also, I got a baby crying in the background, so I'm trying to get this sorted quick. There's a road crew digging up the street outside, and I already rebooted the gate twice, checked all the cables, but the Internet light is just blinking orange. Is that roadwork maybe the cause?
AGENTIt absolutely could be the roadwork, yes—if they hit or disconnected our line, your service would drop and the modem would just sit there blinking. Let’s get you back online as fast as possible. I’ll start by checking your line and for any local outage on our side. Can you give me either:
- your Brightwave account number, or - the phone number on the account? Once I have that, I’ll
1. Pull up your account,
2. Check for any outage at your address,
3. Run a line test to see if the problem is in the street vs. inside your home. You don’t need to reboot anything again—I’ll work from my side and only ask you to do something if it’s absolutely necessary.
CUSTOMEROkay. I think my account number is BW883017.
CUSTOMERSorry. Last digit is one. Could you let me know if that's the right one? I just wanna make sure nothing gets messed up. The phone number should be 607237263. Is that what you see on your end?
AGENTYou had it right: your account number is BW883011 (ending in one), and that’s what I’m working on. Here’s what I see and what I did: - No area outage at your address. - Line test showed good signal to your place, but your gateway wasn’t registered. - I just sent a remote reset to your Brightwave BX7, and it’s now showing registered and online on my side. Your devices may take up to 2 minutes to reconnect. Can you quickly check:
- Is the Internet light now solid (usually solid white/green) instead of blinking orange? - Can you get online on either your work laptop or your phone over Wi‑Fi? If it’s easier with the baby, just test one device and tell me what happens—if it’s still not working, we’ll dig in further, but from here it looks like it should be back.
CUSTOMERAlright. So, I just looked, and the Internet light is solid white now, not blinking anymore. That's a relief. How long does it usually take for my devices to reconnect? Should I expect everything to be back up right away, or it normal for it to take a couple minutes?
AGENTSolid white is exactly what we want—that means the connection is back. For your devices:
- Most will reconnect within 30–60 seconds. - Some (especially work laptops or smart TVs) can take up to 2–3 minutes to fully reconnect. - If anything is still offline after about 3 minutes, just toggle Wi‑Fi off/on on that device or briefly disconnect/reconnect it from your network. If you want to be sure it’s all good, try loading a website on your work laptop now and tell me if it comes up.
CUSTOMEROkay. That helps. Thank you. I'll go ahead and check a site on my laptop now.
CUSTOMERYeah. Looks like it's loading fine. I think I'm good to go. I lost two hours of work today, though. Is there any way I can get a credit for the downtime? Sorry if that's a bother. I just wanna make sure I'm covered.
AGENTYou’re not bothering me at all—it makes sense to ask. I’ve gone ahead and added a credit for you. Here are the details: - Account: BW883011 - Credit amount: $10.00 - It will appear on: your next bill If you notice anything weird with the connection again—especially with that road crew out front—reach out right away and mention that your gateway had to be remotely re-registered today.
CUSTOMERAre you sure about that amount? $10,000 seems awfully high. I lost two hours, but I was just hoping for a fair adjustment. Can you make it more than the usual, but maybe not that much? I just wanna be sure it's reasonable and covers the time I was out.
AGENTThanks for double-checking—that’s important. The credit I applied was $10.00 (ten dollars), not $10,000. Let me read it back clearly: - Account: BW883011 - Credit amount: $10.00 - Will appear on: your next bill I’m not able to arbitrarily increase it beyond what our system allows for a short interruption like this, but $10 is already above what we typically do for just a couple of hours of downtime, so you’re covered fairly for today’s issue. If you have more outages or a longer disruption, we can always review additional credits based on the total impact.
CUSTOMERAlright. I appreciate you looking out for me. That helps. And I'll keep an eye on things in case anything else comes up. Thanks for your help today. Goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi. I need to reschedule my dermatology appointment. Was supposed to be next Wednesday morning, but I just got a work shift then. You help me move it? My name is Lucia Ramirez.
AGENTI can help with that. I’ll just need to verify your account first. Please provide:
- Your full name as it appears on your records (including any middle name, if you use one), and - Your date of birth (YYYY-MM-DD). Once I have that, I’ll look up your dermatology appointment for next Wednesday morning and check new times for you.
CUSTOMERSure. My full name is Lucia Ramirez. My date of birth is 03/17/1948. Sorry. No. 1984. 03/17/1984.
AGENTThanks, Ms. Ramirez. I have you as:
- NameLucia Ramirez
- Date of birth1984-03-17
I see a dermatology
CUSTOMERRight. That's the one. Oh, I can only come after 3PM now. Do you have any slots available then?
AGENTI checked Dr. Okafor’s schedule starting from next Wednesday for times after 3:00 PM. The closest available options that meet your “after 3 PM” requirement are:
- Thursday at 410 PM
- Tuesday at 345 PM (that’s earlier in the week)
Would you like to
CUSTOMERTuesdays don't work after all because I pick up my daughter then. What about Friday?
AGENTTotally understand about Tuesdays. For Dr. Okafor, the only Friday slot I see is:
- Friday at 1130 AM
There’s nothing on Friday after 300 PM with Dr. Okafor in the current schedule. Would you prefer: - Thursday at 4:10 PM with Dr. Okafor, or - Keeping your original Wednesday 9:15 AM, or - Having me check if any other dermatologist (different provider) has something after 3 PM on another day?
CUSTOMERThursday at 04:10PM with doctor Okafor. Sounds good. Let's go with that. Thursday at 04:10PM with doctor Okapur. Works for me. Please book that.
AGENTYou’re all set, Ms. Ramirez. I’ve moved your dermatology
CUSTOMEROkay. So before we finish, could you tell me if there's any fee for changing the appointment?
AGENTFor your change today, there’s no fee. Our policy is: “Changes made more than 24 hours before the appointment are free; later changes carry a $40 fee.” Since you rescheduled your appointment with Dr. Okafor well
CUSTOMERUh-huh. Got it. Where should I park when I come in for the appointment?
AGENTFor your appointment with Dr. Okafor on Thursday at 4:10 PM, you can use our patient parking:
- ParkingFree patient parking in Lot C - Entrance: Off River Road
Plan to arrive about 15 minutes early to find parking and check in with your photo ID and insurance card.
CUSTOMERAlright. Thanks. And does doctor Okapoor accept Aetna insurance?
AGENTI don’t have access to provider-by-insurance details, so I can’t safely confirm that for you. To be sure about Aetna coverage with Dr. Okafor, please either:
1. Call our front desk at Riverbend Health Clinic and ask if Dr. Okafor is in-network for Aetna, and/or 2. Check directly with Aetna (website or member services) using
- Provider nameDr. Okafor - Specialty: Dermatology - Location: Riverbend Health Clinic, Main Campus, Building B
They can confirm network status and any copays or referral requirements for your visit.
CUSTOMEROkay. I will check with them. And could you give me the confirmation code for the new appointment, please?
AGENTYour new dermatology
CUSTOMERMhmm. Could you please read back the confirmation code for Thursday at 04:10PM?
AGENTYour dermatology appointment with Dr. Okafor on Thursday at 4:10 PM has confirmation code RVB-3M8P2.
CUSTOMERAlright. That's clear. Thank you for your help. Goodbye.
AGENTYou’re welcome, Ms. Ramirez. To recap: your dermatology appointment with Dr. Okafor is on Thursday at 4:10 PM, confirmation code RVB-3M8P2. Goodbye, and take care.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, Alex. I've got a burst pipe under my kitchen sink. Water's spreading across the floor toward a power strip. I haven't shut the water off yet. Can someone come out right away?
AGENTThanks for telling me right away—let’s get you safe first. 1. Stay away from that power strip and any outlets the water is reaching. Don’t touch it. 2. If you can safely reach it without stepping in water, unplug the power strip by pulling the plug from the wall. If you’d have to stand in water or reach over water to do it, don’t touch it—just move away. 3. Let’s shut off the water:
- Do you know where your main water shutoff is (often in a basement, garage, utility room, or outside by the street in a box)? - If yes, please go turn the handle/valve clockwise all the way to shut off the water to the house. - If you can’t find it quickly, look under the kitchen sink for a local shutoff valve (small oval or lever handles on the pipes) and turn those clockwise to close. Please tell me
- Have you been able to shut off the water yet? - Is anyone in the home experiencing shocks, tingling, or having trouble breathing? Because there’s active water heading toward electrical, this is an emergency and we’ll get someone out as soon as possible. To set this up, I’ll need to pull up your account
1. Best callback number for you right now? 2. Service address including unit or apartment number, and any gate code or access instructions? 3. Is this your home or a rental property? Once I have that, I’ll check our emergency availability and fees, go over the price with you, and then book the earliest arrival window we have today.
CUSTOMEROkay. I'm away from the power strip. I found the shutoff under the sink. And I've turned it off. The water has stopped. No one here is having any shocks or trouble breathing. The best callback number is (503) 555-0139. No. 0193. The address is 1480 Larkspur Avenue. Unit 4 D. I moved from 4 B to 4 D last month. Just to clarify, the building gate code is Pound 2719. This is my home. How much will the emergency visit cost before we book? And can anyone come before two?
AGENTI’m glad you got the water shut off and everyone’s okay. Please keep everyone away from that wet area and the power strip until we’ve had a chance to check things out; don’t plug it back in. You’re a Copperline Care member, so your emergency callout today would be $99, with parts and labor additional. We take card or check on completion. For today’s availability, the earliest emergency window I can offer is:
- Today, 200 PM to 4:00 PM (emergency)
There’s nothing earlier than 200 PM showing for emergency slots, and the next option after that is a standard visit tomorrow, 8:00 AM to 10:00 AM, which is lower priority. Given the burst pipe and the electrical nearby, I strongly recommend we book the today 2–4 PM emergency window. A couple of quick confirmations before I create the ticket:
- Service address1480 Larkspur Avenue, Unit 4D (I’ll update from 4B to 4D as you mentioned) - Building gate code: #2719 - Best callback number: (503) 555-0193
And can you confirm you agree to the $99 emergency callout fee for today’s 2–4 PM window? Once you say yes, I’ll open the service request and book that arrival window for you.
CUSTOMERYes. That's all correct except for the gate code. It's pound. 2719. And, yes, I agree to the $99 emergency callout fee for today's two to 4PM window. Who will be coming out, and how will I know they're on the way? I'd also like the ticket number, please.
AGENTYou’re all set, and thanks for the clarification on the gate code. Here’s what I’ve got:
- Service address1480 Larkspur Avenue, Unit 4D - Building gate code: Pound 2719 - Callback number: (503) 555-0193 - Ticket number: CPL-58210 - Appointment: Today, 2:00 PM to 4:00 PM (emergency)
We’ve booked this as an emergency plumbing visit for the burst pipe, with a note to also check electrical safety around the affected area. About who’s coming and how you’ll know
- A Copperline technician will be assigned to ticket CPL-58210 for that 2–4 PM window. - You’ll get a text to (503) 555-0193 about 30 minutes before arrival, letting you know they’re on the way and giving you their name. For now
- Keep the under-sink valve closed. - Don’t use that power strip; leave it unplugged until our technician has checked the area. - If water starts leaking again or you see it reaching any outlets, stay clear of the water and outlets and let us know right away. Is there anyone we should ask for at the door, or any special parking instructions I should add to your ticket?
CUSTOMERNo special instructions. Just my name. Jordan Ellis. No special parking needed. I'll watch for the text before arrival. Thanks for your help, Alex. Goodbye.
AGENTGot it, Jordan—thank you.
AGENTI’ve added your name to ticket CPL-58210 and noted no special parking needed. You’re booked for today, 2:00 PM to 4:00 PM at:
1480 Larkspur Avenue, Unit 4D
Gate codePound 2719
Callback(503) 555-0193
TicketCPL-58210
Please keep the water shut off at the sink and stay clear of that power strip area until our tech has checked it. You’ll get a text about 30 minutes before they arrive. Take care, and goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERMhmm. Yes. I'm standing next to my car. I'm on the street, but I'm safe.
AGENTI’m glad you’re safe. Is anyone injured at all—either in your car or the other vehicle? - If anyone is hurt or feels dizzy, confused, or in pain, please hang up and call 911 right away before we continue.
CUSTOMERNo. Nobody is hurt. We are both okay. It's just the cars are damaged.
AGENTI’m glad to hear everyone’s okay. We’ll get your claim started. First, I’ll need to locate your policy. - What’s your auto policy number? - And the policyholder’s
CUSTOMEROh, yeah. The policy number is ND4471903. Oh, sorry. Last one is two.
AGENTThanks. I have policy ND4471902 pulled up. Now I’ll gather some details about what happened so we can open the claim. 1) When did the accident happen? 2) Where did it happen? 3)
CUSTOMERSure. The accident happened about twenty minutes ago. At the intersection of S E 5th Avenue and Alder Street.
AGENTThank you. I’ve got that it happened about 20 minutes ago at S E 5th Avenue and Alder Street. Next, I need a little more detail:
1) Can you tell me what happened? 2) What’s the other driver’s full name, their insurance company (if they have it), and their license plate number? 3) Did the police come to the scene, and if so, is there
CUSTOMEROkay. I was stopped at a red line. And another car hit the back of my car. The other driver is Kevin Lund, insured with Pacific Shore. The license plate is 7K x like X-ray, R214. No. The police did not come.
AGENTThanks, I’ve got all that noted. Let me read back the key details to make sure everything is correct:
- Policy numberND4471902 - What happened: You were stopped at a red light and another car hit the back of your car. - Location: Intersection of SE 5th Avenue and Alder Street - Other driver: Kevin Lund, insured with Pacific Shore - Other vehicle license plate: 7KXR214 - Police: No police came to the scene - Injuries: None reported
I’ve opened a claim for you- Your claim number is NGM-904417. - The assigned adjuster is Priya Shah. You should hear from her within one business day. A couple of quick questions about your car’s condition so we can decide next steps: 1) Is your Honda CR‑V drivable—no fluids leaking, tires okay, lights working, and the rear wheels moving
CUSTOMEROh, no. It's not drivable. The back bumper is crushed. And the rear wheel is rubbing. So I can't drive it.
AGENTYou’re right not to drive it if the wheel is rubbing—that’s not safe. I’ll set up a tow for you. I’ve arranged a tow with: - Eastside Towing - They’ll be there in about 45 minutes. - They’ll take your 2021 Honda CR‑V to our Northgate partner repair shop at 9th and Morrison. If you’d rather have it towed somewhere else (like a shop you prefer or your home), tell me now
CUSTOMERNo. That's fine. Nathan Morrison is okay. Oh, tell me? Do I have to pay anything for this? What's the deductible?
AGENTFor your policy ND4471902: - Your collision deductible is $500. That’s the amount you’d be responsible for toward the repairs if we handle it under your own policy. - Towing is covered up to 25 miles, so the tow we just set up to the partner shop at 9th and Morrison should be covered under that limit. - You also have rental coverage: up to $40 per day for up to 30 days, starting from today when the claim was opened. A couple of quick clarifications and next steps: 1) Since you were rear‑ended and the other driver is insured with Pacific Shore, your adjuster, Priya Shah, will talk with you about whether to go through Pacific Shore, your own policy, or both. That will affect if/when your $500
CUSTOMERBut he hit me, so I should not have to pay that. Right? Will the deductible still apply if Pacific Shore covers it? And about the rental car, do I just pick one up today, or will someone contact me? Also, is my premium going to go up because of this?
AGENTI’ll walk through each of those, one by one, based on how it usually works. Your adjuster will make the final call, but here’s what your policy info and typical handling suggest. 1) Do you have to pay your $500 deductible if the other driver is at fault? - If Pacific Shore accepts 100% liability and pays the claim directly (their policy pays for your damage): - Your $500 collision deductible would not apply under your policy, because we wouldn’t be using your collision coverage to pay for the repairs. - If we pay your repairs first under your collision coverage (which is sometimes faster) and then go after Pacific Shore for reimbursement: - You’d initially be responsible for the $500 deductible, but - If we recover that money from Pacific Shore, we typically reimburse your deductible. Your adjuster, Priya Shah, will confirm which route they’re taking and how your deductible will be handled in this specific case. 2) Rental car – what do you do today? Your policy shows rental coverage of $40 per day for up to 30 days from today. Normally, it works like this:
- We either- Set you up with a preferred rental company that bills Northgate directly up to your limits, or - You rent a car and keep receipts, and we reimburse you up to $40/day. - Since I’m the intake line and can’t set up the direct rental myself, Priya or someone from her team will contact you about the rental setup. That should be within one business day. Because the car isn’t drivable
CUSTOMEROkay. Got it. So I wait for Priya to contact me about the rental. And I can get reimbursed if I need to pay upfront. Can you tell me, will my premium go up after this claim?
AGENTI can’t see or change your premium from here, so I can’t say for certain what will happen to your rate. I can tell you how it’s usually handled:
- If you’re clearly not at
CUSTOMERAlright. So if I'm not at fault, my premium should not go up. Right? And just to confirm, the tow truck is coming. And the car will go to the partner shop at 9th. And, also, my claim number is NGM904417. Correct?
AGENTfault
AGENTLet me clear each of those up. 1) Premium going up I can’t promise your premium won’t change, because rating decisions depend on state rules and the final claim outcome.
CUSTOMEROkay. Understood. You for explaining all that. I'll wait for Priya to contact me, and the Toastmaster is coming soon. That's all I needed. Goodbye.
AGENTYou’re all set, and I’m glad you’re safe. Just to reconfirm before you go:
- Policy numberND4471902 - Claim number: NGM-904417 - Tow: Eastside Towing is on the way, and your car is going to the Northgate partner shop at 9th and Morrison. Priya Shah, your adjuster, will contact you within one business day about repairs, the deductible situation, and your rental car options. Take care, and goodbye.