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
#387of 654 stacks
47 / 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.
#137 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.
#465 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
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.
#407 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.
#308 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.
#480 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.
#391 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.
#435 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.
#566 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.
#533 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.
#323 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#535 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 97% | 4.59 s | — |
| Home services | 93% | 4.22 s | — |
| Insurance | 97% | 4.57 s | — |
| Customer support | 93% | 4.34 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 96% | 5.12 s | — |
| Spanish-accented English, city street | 98% | 4.27 s | — |
| Indian English, busy café | 91% | 4.05 s | — |
| Southern US, flustered, crying baby | 100% | 4.28 s | — |
| Fast and interrupting, construction outside | 89% | 4.53 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, uh, sorry. I'm a little frazzled here. My baby's been crying and I'm working from home. My internet's been down for about two hours now. There's a road crew digging up the street outside. I'm not sure if that's connected or not. I already rebooted the gateway twice and checked all the cables, but the internet light's blinking orange. Can you check what's going on? My account number is BW883017. Sorry, last digit is one. Is that enough to pull up my account?
AGENTYes,
CUSTOMERHello?
AGENTthat’s
CUSTOMERAll right, thank you
AGENTI’ve got
CUSTOMERSorry, I just want to make sure you got the account number right. BW883011. Is that okay? So, uh, like I said, my internet's been out for two hours, and I've got a road crew right outside the house. I already restarted the gateway twice and checked all the cables, but the light's still blinking orange. Could the road work be the cause?
CUSTOMERSorry, I didn't catch that. Could you repeat what you were saying? I just want to make sure I don't miss anything, since I really need the internet back up for work.
AGENTI’ve got you under account BW883011, yes—that’s the one I’m working on. I ran tests on your line and did a remote reset of your Brightwave BX7 gateway from our side. It came back as registered and online, and there’s no area outage showing for your address. A few key points, repeating clearly:
1. Your service from our side looks good now. - Signal to the gatewaygood - Gateway status: online and registered after the reset
2. That blinking orange light Right after a reset, the light can blink while it’s reconnecting. - It can take up to about 2 minutes for everything to settle and for your devices to reconnect. 3. What you should do right now Wait a full 2 minutes after that last reset I sent. - Then on a device (laptop/phone)- Turn Wi‑Fi off and back on, or unplug/replug the Ethernet cable if it’s wired. - Try going to a website you don’t have cached, like `news.bbc.co.uk` or `nytimes.com`. 4. About the road crew If they had cut our line, my test would normally show a bad signal to the gateway or no signal at all. - Since I’m seeing good signal and your gateway online, the road work is probably not the cause at this moment. If, after 2–3 minutes, you still: - don’t see a solid “online/internet” light, or - can’t load any websites,
tell me exactly what the lights on the gateway look like (power, internet, Wi‑Fi), and I’ll take the next step—either more targeted checks or getting a technician scheduled if needed.
CUSTOMERHuh?
AGENTYou’re okay on the account
CUSTOMERAll right, uh, thanks for explaining all that. The internet light just went solid white, so I guess it finally connected up! How long should it take for my devices to actually reconnect? I really need to get back to work as soon as possible. And, uh, since I lost two hours of work, can I get a credit for the downtime? Sorry, I just want to make sure I'm covered.
CUSTOMERYeah, I think so. Please tell me that's the right one. BW883011. Is that what you've got? Sorry, I just want to double check everything's set.
AGENTI’ve got you under account BW883011 — that’s exactly what I’m working on. Good news that the internet light is solid white now. At this point:
1. Device reconnect timing - Most devices should reconnect within 1–3 minutes on their own. - To speed it up
- On laptops/phones/tabletstoggle Wi‑Fi off and back on, then reconnect to your usual Wi‑Fi name. - On wired devices: if anything still looks offline, unplug and replug the Ethernet cable once. 2. Credit for the downtime - I’ve applied a $10.00 service credit on account BW883011. - It will show on your next bill as a credit for the downtime while you were out and we reset the line. Before we wrap up, can you quickly try loading a couple of sites (maybe one work site and one regular site) and tell me if everything’s working normally now?
CUSTOMEROkay, uh, sorry, is $10 the most you can do? I lost two hours of work, so can you make it more than that? I just want to make sure that's fair, since I really rely on the connection for my job. And yeah, let me check the sites real quick.
AGENTI understand why you’re asking, especially if you lost billable time. On my side, I’m limited to applying a standard outage credit based on the service downtime, not lost work time. I’ve already applied the maximum I’m allowed to do directly: a $10.00 credit on account BW883011, which will appear on your next bill. If you feel that still isn’t fair, the next option is to contact Billing/Customer Care, who can review your account history and see if anything additional is possible. I can’t promise they’ll increase it, but they’re the only ones who can go beyond what I’ve already applied. How are those sites loading now—both your work site and a regular site—are they back to normal speed?
CUSTOMERSorry, I get you. Thanks for explaining. The sites are loading fine now. Everything seems back to normal. I appreciate your help today, and I'll reach out to billing if I need to follow up. Alright, thanks again, and goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey, uh, hi. Sorry, I got a baby crying in the background so I might sound a little flustered. I need to reschedule my dermatology appointment for next Wednesday morning. I just got assigned a work shift then, and I can only come after 3pm now. Can you help me move it?
AGENTI can help with that. We’ll first verify your record, then I’ll look up your appointment and check what’s available after 3 pm. Please tell me:
1) Your full name 2) Your date of birth (YYYY-MM-DD)
CUSTOMERYeah, uh, my name's Wade Carter. My date of birth is March 17, 1948. Oh, sorry, no, that's not right. I got distracted. It's actually 1984. March 17, 1984. Is that okay?
AGENTThanks, Wade. I’ve got you as Wade Carter, born 1984-03-17. I see your dermatology visit with Dr. Okafor is next Wednesday at 9:15 am at Main Campus, Building B. For moving it to a time you can do, here are the next available options with Dr. Okafor that are 3 pm or later:
- Tuesday at 345 pm - Thursday at 4:10 pm
Friday’s opening is at 1130 am, so that won’t work with your “after 3 pm” constraint. Which of these would you like to switch to—Tuesday at 3:45, or Thursday at 4:10?
CUSTOMERSorry, Tuesdays actually don't work after all. I pick up my daughter then, so I can't make it. Could you check if Thursday at 4.10pm is still available? And what about Friday? Do you have anything later in the day?
AGENTI’ve checked Dr. Okafor’s current schedule:
- Thursday at 410 pm is still available. - On Friday, the only opening is 11:30 am; there’s nothing later in the day with Dr. Okafor right now. Do you want me to move your appointment from next Wednesday at 9:15 am to Thursday at 4:10 pm with Dr. Okafor?
CUSTOMERYeah, Thursday at 4 10 p.m.? Sounds good. Sorry if I'm being a bother. Just want to make sure that's okay. Can you switch it to Thursday at 4 10 p.m. for me, please? And is there a fee for changing the appointment?
AGENTYou’re not a bother at all, and thanks for hanging in there with everything going on in the background. I’ve moved your dermatology appointment with Dr. Okafor from next Wednesday at 9:15 am to Thursday at 4:10 pm at Main Campus, Building B. Your new confirmation code is RVB-3M8P2. Please arrive 15 minutes early with a photo ID and your insurance card. About fees: the clinic’s policy
CUSTOMERBoom.
CUSTOMERThank you. I really appreciate it. So, uh, just to double-check, my new appointment's Thursday at 4.10 p.m., main campus, Building B, and the confirmation code is RVB3M8P2, right? Is there a fee for changing the appointment, or am I all right there? And, uh, where do I sign up?
AGENTAlmost perfect—you’re
CUSTOMERHow do I park when I get there?
CUSTOMERSorry, I didn't catch that. Could you repeat what you were saying? I just want to make sure I've got everything right. Is there a fee for changing? And where should I park at the main campus?
AGENTHere’s everything, nice and clear: 1) Appointment details - Name: Wade Carter - Date of birth: 1984-03-17 - New appointment: Thursday at 4:10 pm - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2 (that’s R–V–B–3–M–8–P–2) 2) Fee for changing the appointment The clinic’s policy is: - Changes made more than 24 hours before the appointment are free. - Changes made less than 24 hours before the appointment have a $40 fee. You rescheduled this more than 24 hours in advance, so there is no fee for this change. 3) Parking at the main campus - There is free patient parking in Lot C. - The entrance to Lot C is on River Road. If you’d like, I can also go over clinic hours or anything else you’re unsure about.
CUSTOMEROh, all right. That's a relief. So, no fee since I changed it ahead of time. Thank you for explaining it. And, uh, free patient parking in Lot C, entrance on River Road. Got it. Just one last thing. I wanted to double check. Does Dr. Okafor accept Aetna insurance? I'm a little nervous about that part.
AGENTI don’t have access to the clinic’s insurance panel, so I can’t safely confirm specific insurance plans like Aetna. To be sure about Dr. Okafor and Aetna, you have two good options:
1. Call the front desk/billing at Riverbend Health Clinic and ask specifically- Can you confirm that Dr. Okafor is in-network with Aetna for my plan?” Have your Aetna card handy—they may ask for the plan name or group number. 2. Check with Aetna: - Log into your Aetna member portal or app and use the provider search. - Search for “Riverbend Health Clinic” and “Dr. Okafor” and confirm they’re listed as in-network.
I’d definitely verify before your visit so there are no surprise bills.
CUSTOMERAlright, I'll make sure to call and double check with the front desk and Aetna, just to be safe. Thank you for walking me through all that, and for being patient with me. That's everything I needed. Goodbye.
AGENTYou’re all set, Wade. To recap quickly: - Appointment: Thursday at 4:10 pm - Provider: Dr. Okafor, Dermatology - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2 - Parking: Free patient parking in Lot C, entrance on River Road - No fee for the change, since you rescheduled more than 24 hours in advance. Calling the front desk and Aetna about insurance is exactly the right move. Take care, and goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, Alex. I have an emergency. A pipe under my kitchen sink just burst and water is spreading across the floor. It's heading toward a power strip. I haven't been able to shut the water off yet. Can you help me?
AGENTStay clear of that power strip and any outlets near the water—don’t touch them or anything plugged into them. Let’s do two quick safety steps right now:
1. Kill power near the water (if you can do it safely)If your main electrical panel is in a dry area you can reach without stepping in water, go there and switch off the breakers for the kitchen. - If you’re not sure which breaker it is, and you can still reach the panel safely without crossing wet floor, switch off the main breaker. - If you would have to cross wet flooring to get to the panel, do not go there—stay where you are and keep away from the water. 2. Shut off the water: - First, look under the kitchen sink: do you see two small shutoff valves (usually one for hot, one for cold) on the pipes? If yes, try turning them clockwise until they stop. - If you can’t find or turn those, we’ll need the main water shutoff:
- Often it’s where the water line enters the house (basement, utility room, garage wall, or a closet), or outside by a main shutoff valve or meter box near the street. - It may be a lever handle (turn so it’s perpendicular to the pipe) or a round knob (turn clockwise). Tell me- Are you able to safely reach your breaker panel without stepping in water? - Do you see any shutoff valves under the sink or know where your main water shutoff is? While you check, keep everyone (people and pets) away from the water and that power strip. If the water is already at the strip and it’s live and you can’t safely reach the panel, you may need to call 911 for fire department assistance because of the electrical hazard. Once we have the water and/or power situation under control, I’ll get an emergency plumber out to you right away.
CUSTOMERI can reach my breaker panel without stepping in water, so I'll switch off the kitchen breakers now. As for the water, I do see two shut-off valves under the sink. I'm turning them clockwise. Okay, the water has stopped. I'll keep clear of the power strip and outlets. My address is 1480 Larkspur Avenue, Unit 4D. I moved from 4B to 4D last month. Before I agree, can you tell me how much the emergency visit will cost? And can anyone come before 2 p.m.?
AGENTYou did exactly the right things—killing the kitchen power and shutting off those valves. Since the water’s stopped, keep the area clear and avoid plugging/unplugging anything near that strip until an electrician or our tech says it’s safe. You’re in our system at 1480 Larkspur Avenue, previously Unit 4B. I’ll use Unit 4D as your correct unit going forward. Here’s what I can offer you and the cost:
- Earliest emergency arrival windowtoday, 2:00 PM to 4:00 PM - Next option (non‑emergency): tomorrow, 8:00 AM to 10:00 AM
You’re a Copperline Care member, so your emergency callout fee today would be $99. That covers the emergency dispatch and diagnosis; any repair work or parts would be quoted on site before they proceed. Payment is by card or check on completion. So
- No, we don’t have anything earlier than 200 PM for emergency today. - Cost for an emergency visit today: $99 for you as a member. Would you like me to book the 2:00–4:00 PM emergency window today for Unit 4D? If yes, I’ll just need:
- The best callback phone number for you - Any gate code or special access instructions for the building
CUSTOMERYes, go ahead and book the 2 o'clock to 4 o'clock p.m. emergency window today for Unit 4D. My callback number is 503-555-0139. No, 0193. The building gate code is pound two seven one nine. Who will be coming out and how will I know they're on the way? Could you give me the ticket number as well?
AGENTYou’re all set—I’ve got you booked. Here’s what I’ve done and what to expect:
- Service address1480 Larkspur Avenue, Unit 4D - Gate code: #2719 - Callback number: 503-555-0193 - Urgency: Emergency - Arrival window: today, 2:00 PM to 4:00 PM - Ticket number: CPL-58210
You’ll get a text about 30 minutes before arrival to that callback number so you know the technician is on the way. They’ll also call if there’s any issue finding parking or getting through the gate. I’m not able to promise a specific person by name, but it will be one of our emergency-qualified plumbers, and they’re aware there was water near a power strip, so they’ll also keep an eye on the electrical safety around that area. While you’re waiting
- Keep the sink valves closed and the kitchen breakers off. - Keep people and pets away from the wet area and the power strip. - If you can do it safely, you can start mopping up or using towels to dry the floor—but don’t touch the strip or outlets. Let me quickly read everything back to be sure nothing’s offService to 1480 Larkspur Avenue, Unit 4D, gate code pound two seven one nine, callback 503-555-0193, ticket CPL-58210, emergency plumbing today between 2:00 and 4:00 p.m., emergency callout fee $99 as a Copperline Care member, plus any approved repairs. Is all of that correct?
CUSTOMERYes, that's exactly right. The address, unit, gate code, callback number, and ticket number CPL 58210 are all correct. Emergency plumbing today between 2 o'clock and 4 o'clock p.m. $99 for the call-out plus any approved repairs. Thank you for confirming everything, Alex. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERUh, yes.
AGENTI’m
CUSTOMERSorry, I am at home now. I was out earlier, but I got the car back here. I just... I can't drive it. Is that okay?
AGENTThat’s okay, and I’m glad you’re home safe. Before we go further: was anyone injured in the accident—either in your car or the other vehicle? - If anyone is hurt or in any danger right now, please hang up and call 911 first.
CUSTOMERNo, nobody got hurt, thankfully. I was real worried at first, but everyone's okay. Is that alright, or do y'all need anything else about that?
AGENTThat’s absolutely alright—no injuries is always good news, and that’s all we need on that point. We’ll get your claim started and also look at a tow since you can’t drive the car. First, I need to pull up your policy. 1) What’s your auto policy number? 2) And the policyholder’s last name as it appears on the policy?
CUSTOMERUh, yeah, sorry. Let me get that for you. The policy number is NG4471903... No, sorry, last one is 2. And the last name should be Carter. Is that okay, or do y'all need anything else for that?
AGENTThanks, I’ve got your policy pulled up now under number NG4471902, last name Carter, for a 2021 Honda CR‑V. Next I’ll open the claim and then we can talk about a tow since you can’t drive the car. Let’s start with the accident details:
1) When did the accident happen? 2) Where did it happen? 3) Can you tell me what happened, in your own words? Then I’ll also need4) The other driver’s name (as best you remember), their insurance company, and their license plate, if you were able to get it. 5) Did the police come to the scene, and is there a report number, if you have one?
CUSTOMERLet me try to get everything for you. The accident happened about 20 minutes ago. It was at S.E. 5th Avenue and Alder Street, so I was stopped at a red light, and another car hit the back of mine. The bumper is crushed, and the rear wheel is rubbing, so I can't drive it. The other driver's name is Kevin Lund. His insurance company is Pacific Shore, and his plate is 7K, X like X-ray, R214. Police did not come, so there's no report number. Is that alright, or do you need anything else for the claim?
AGENTYou’ve given me exactly what I need, thank you. I’ve opened your claim and set up a tow since the car isn’t safe to drive. Let me walk you through what’s in place and read back the key details. First, confirming your policy:
- Policy numberNG4471902
- Name on policyCarter
- Vehicle2021 Honda CR‑V
Accident details on the claim
- WhenAbout 20 minutes ago
- WhereIntersection of SE 5th Avenue and Alder Street
- What happenedYou were stopped at a red light and were rear‑ended. Rear bumper is crushed and the rear wheel is rubbing, so the vehicle is not safely drivable. - Other driver: Kevin Lund, insured with Pacific Shore
- Other vehicle plate7KXR214
- PoliceDid not attend; no report number
Here’s your new claim
- Claim numberNGM-904417
- Assigned adjusterPriya Shah
- ContactYou should hear from Priya within one business day. Coverage information for this policy:
- Collision deductible$500
- Rental car$40 per day for up to 30 days, starting today (the day the claim is opened). - Towing: Covered up to 25 miles. Tow details:
- Tow companyEastside Towing
- StatusDispatched
- Estimated arrivalAbout 45 minutes
- DestinationNorthgate partner repair shop at 9th and Morrison
You mentioned the plate as7K, X like X-ray, R214 — I have it recorded as 7KXR214. Please double‑check: is 7KXR214 correct, or should any of those characters be different? Also, do you already have a rental car, or will you need help arranging one once the vehicle is at the shop? Finally, I want to read back the three key numbers so you have them handy:
- Policy numberNG4471902 - Other driver’s plate (as I have it): 7KXR214 - Your claim number: NGM-904417 If anything I read back isn’t right, tell me and I’ll correct it on the claim.
CUSTOMERThank you for double-checking. The plate is 7K, X like X-ray, R214. So, yeah, that sounds right. I don't have a rental car yet, so I'll need help arranging one when it's at the shop. Uh, can I ask about that deductible? But he hit me, so I should not have to pay that, right? And, um, is my premium going to go up because of all this? Sorry, I just want to make sure I understand everything. Hello?
AGENTYou’re not bothering me at all—it’s good you’re asking these now. First, I’ve got your details as: - Policy number: NG4471902 - Other driver’s plate: 7KXR214 - Claim number: NGM-904417 On the plate: you confirmed “7K, X like X‑ray, R214,” which matches 7KXR214, so we’re good there. RENTAL CAR You do have rental coverage: - Up to $40 per day - For up to 30 days - Starting today (the day we opened the claim) Once your car is at the shop, you can: - Ask the repair shop to help set up the rental through your policy, or - Wait for your adjuster, Priya Shah, to call (within one business day) and they can help coordinate it. If you prefer, you can also book a rental yourself and give them your claim number NGM-904417 so they can bill us directly up to your limits. ABOUT THE DEDUCTIBLE From your coverage: - Collision deductible: $500 How this usually works in a rear‑end situation like you described: - For now, your claim is under your collision coverage, which does have a $500 deductible. - If the other driver (Mr. Lund / Pacific Shore) is found at fault and they accept liability, one of two things usually happens: - They may pay for your damages directly (no deductible from you), or - If we pay first under your collision, we will often pursue reimbursement from Pacific Shore. If we recover the full amount from them, your $500 deductible is typically reimbursed to you. Your adjuster, Priya, will: - Confirm fault based on statements, any photos, and any later police or witness info. - Let you know whether your deductible will apply up front and what the chances are of getting it back from the other insurer. ABOUT YOUR PREMIUM I can’t see or predict specific premium changes from here. Whether your rate goes up depends on: - Final fault determination (if you’re found not at fault, that often helps), - Your prior claims/accident history, - State rules and our underwriting guidelines. Your adjuster can go over how this
AGENTclaim will be coded (at‑fault vs. not‑at‑fault) and then customer service can answer how that might affect your premium once the claim is resolved. I’m not allowed to promise no increase or quote future pricing. NEXT STEPS FOR YOU - Tow: Eastside Towing is still set to arrive in about 45 minutes to take your Honda CR‑V to the partner shop at 9th and Morrison. - When the car reaches the shop: tell them you have Northgate Mutual claim NGM-904417 and that you have rental coverage ($40/day, up to 30 days). They can help you get into a rental. - Adjuster call: Watch for a call from Priya Shah within one business day. She’ll: - Go over fault, - Explain exactly how the deductible will work in your situation, - Talk through repair steps and timing. Is there anything else you’re worried about right now—like how long repairs might take, or whether it’s okay to drive a rental out of state, or anything along those lines?