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
#385of 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.
#199 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.
#518 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.
#346 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.
#341 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.
#488 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.
#385 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.
#207 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.
#494 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.
#568 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 | 93% | 4.27 s | — |
| Home services | 95% | 4.07 s | 100% |
| Insurance | 95% | 4.06 s | — |
| Customer support | 93% | 4.77 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 4.05 s | — |
| Spanish-accented English, city street | 98% | 5.04 s | — |
| Indian English, busy café | 98% | 3.71 s | — |
| Southern US, flustered, crying baby | 96% | 4.95 s | — |
| Fast and interrupting, construction outside | 80% | 4.09 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi, Alex. My Internet's been down for about two hours now. I work from home, so this is a big problem. There's a road crew digging up the street outside. And I'm wondering if that has something to do with it. I already rebooted the gateway twice, and checked every cable. The Internet light is blinking orange. Can you check what's going on? My account number is BW883017. Sorry. Last digit is one.
AGENTThanks for the details—that helps a lot.
CUSTOMEROh. Yeah. That's right. BW883011. So can you see if the outage is related to the road crew outside?
AGENTI’ve got you under account BW883011, and I don’t see any area outage or maintenance reported at your address, so nothing official tied to that road work right now. I ran a line test a moment ago and your signal to the gateway looks good. Your gateway had dropped off our system (“not registered”), so I sent a remote reset. It’s now showing as registered and online, which means:
- The outside line to your home is working from our side. - Whatever the road crew is doing hasn’t fully cut your connection, at least not at this moment. Your devices may take up to about two minutes to reconnect after that reset. Can you check from a computer or phone (preferably over Wi‑Fi first, then wired if you can) and tell me
1. Do you see your Wi‑Fi network name? 2. If you connect, do websites load now? If it’s still down, I’ll dig deeper into your local connection and wiring inside the home, since the outside plant and account both look healthy right now.
CUSTOMERThe Internet light just went solid white. So that looks better. How long until my devices reconnect? And can I get a credit for the downtime? I lost two hours of work.
AGENTSolid white is exactly what we want—that means the gateway is online again. Most devices should reconnect within 1–2 minutes on their own. If something doesn’t:
- On Wi‑Fi devicestoggle Wi‑Fi off and back on, then select your network again. - On wired devices: they should come back automatically; if not, unplug/replug the Ethernet cable once. About the credit: I’ve added a $10.00 service credit on account BW883011 for roughly two hours of downtime. It will appear on your next bill. If anything is still not coming online after a couple of minutes, tell me which device(s) and how they’re connected (Wi‑Fi or Ethernet), and I’ll walk you through quick, targeted checks.
CUSTOMERI lost two hours of work. Can you make it more than that?
AGENTI understand why you’re asking, especially if those two hours were critical for work. On account BW883011 I’ve already applied a $10.00 credit, which is the standard amount we’re allowed to issue for a short interruption like this. I’m not able to increase that amount from here—there isn’t an override I can use. What I can do is document clearly on your account that this impacted work-from-home time due to an unplanned outage of about two hours. If you’d like to pursue a larger adjustment, customer care or billing can review that note and see if anything additional is possible under your plan’s terms. In the meantime, are all your devices back online now, or is anything still having trouble connecting?
CUSTOMERAlright. Thanks for documenting that. My devices are reconnecting, so I think I'm set. Appreciate your help. Goodbye.
AGENTYou’re welcome—glad everything’s back up and running. On account BW883011 I’ve documented the roughly two‑hour work-from-home impact along with the $10.00 credit that’s already been applied and will show on your next bill. If anything acts up again—especially with that road work going on—contact us right away. Take care, and goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHello. This is Arjun Mehta. I am having one dermatology appointment next Wednesday morning. But I got scheduled for a work shift at that time. Kindly help me move the appointment to a later time. I can only come after 3PM.
AGENTI can help with that. To pull up your chart and find your appointment, I need to verify you. Please provide:
1) Your full name as it appears on your ID (I have “Arjun Mehta,” please confirm or correct), and
2) Your date of birth (YYYY-MM-DD). Once I have that, I’ll look up your dermatology appointment next Wednesday and then check for later same‑day openings after 300 PM.
CUSTOMEROkay. Yes. That's right. Arjun Mehta. My date of birth is 03/17/1948. Sorry. No. 1984. 03/17/1984.
CUSTOMERTuesdays do not work after all. I'm picking up my daughter. What about Friday?
AGENTRight now I see these openings with Dr. Okafor after 3 PM, avoiding Tuesdays:
- Thursday at 410 PM
- Friday at 1130 AM (this one is before 3 PM)
There are no Friday slots after 3 PM currently. Would you like me to move your dermatology appointment from next Wednesday at 915 AM to Thursday at 4:10 PM, or would you prefer to keep your current appointment for now?
CUSTOMERPlease move my dermatology appointment to Thursday, at 04:10PM. That will work for me.
AGENTYou’re all set, Mr. Mehta. I’ve moved your dermatology visit with Dr. Okafor from next Wednesday at 9:15 AM to Thursday at 4:10 PM.
CUSTOMERUh-huh. Can you please read back the confirmation code for my new appointment?
AGENTYes.
CUSTOMEROkay.
CUSTOMERGo ahead.
AGENTYour new appointment confirmation code is RVB-3M8P2.
CUSTOMERGot it. RVB3M8P2. Is there any fee for changing the appointment?
AGENTThanks for reading that back: I have your confirmation code as RVB-3M8P2 (with the dash after “RVB”). Regarding fees: according to our policy, changes made more than 24 hours before the appointment are free; changes made less than 24 hours before carry a $40 fee. Your move to Thursday at 4:10 PM was done more than 24 hours in advance, so there is no fee for this change.
CUSTOMERThat's right. No fee. Where should I park when I come for the appointment?
AGENTFor your appointment with us:
- Patient parking is free. - Please park in Lot C.
- The entrance to Lot C is on River Road. Plan to arrive about 15 minutes early to allow time for parking and check‑in, and bring a photo ID and your insurance card.
CUSTOMERUnderstood. Does doctor Okafor accept Aetna insurance?
AGENTI don’t have access to Dr. Okafor’s current insurance panel, so I can’t safely confirm Aetna participation from here. To get an accurate answer, I recommend one of these:
1. Call the clinic’s main line and ask
- “Can you confirm whether Dr. Okafor is in network with Aetna for dermatology visits?” 2. Check Aetna’s website/app
- Use the “Find a doctor” tool. - Search for “Riverbend Health Clinic” and “Dr. Okafor” under Dermatology. - Make sure you select your exact Aetna plan name (e.g., HMO/PPO, employer plan). If you tell me the exact name of your Aetna plan (as printed on your card), I can outline exactly what to click and look for on Aetna’s site to verify Dr. Okafor there.
CUSTOMERI do not have my card in front of me right now. That covers everything. Thank you for your help. Goodbye.
AGENTYou’re welcome, Mr. Mehta. We’ll see you Thursday at 4:10 PM—please remember your photo ID, insurance card, and to park in Lot C off River Road. Goodbye, and take care.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey. Sorry. There's a lot of noise out here. I've got a burst pipe under my kitchen sink. Water everywhere. Heading toward a power strip. I need someone out fast. What do I need to do?
AGENTUnder the sink, stay as calm and quick as you can. First, safety:
1. Stay away from the power strip and any outlets the water is near.
CUSTOMERMhmm.
CUSTOMERYeah.
CUSTOMERI get it. I'm staying clear. What's next? How soon can someone get here?
AGENTGood, stay clear of that power strip. Don’t touch it or anything plugged into it.
CUSTOMERYep. I'm clear. Look, I really need someone out. How quickly can you send somebody? And what's the cost for the visit?
AGENTUnderstood—this is urgent, and we’ll treat it as an emergency. First, two quick safety steps, then I’ll get your details and check the fastest arrival and cost. 1. If you can reach it safely, unplug that power strip from a dry area only.
CUSTOMERRight. I know. My details are ready. Get me the earliest emergency window and the price, please.
AGENTI can get you the earliest emergency window today, 2:00 PM to 4:00 PM. Emergency call‑out fee options:
- Standard emergency call‑out$149
- If you’re a Copperline Care member$99
Before I book it, two quick things while we talk
1. Shut off the water to the sink if you can reach it safely
- Look under the sink for two small valves (one on the hot, one on the cold). - Turn both clockwise until they stop. 2.
CUSTOMEROkay.
CUSTOMERYep.
CUSTOMERI know how to shut it off. I'm doing it now. Alright. Water stopped. Can anyone come before two? I need someone as soon as possible.
AGENTGood job getting the water stopped—that’s the most important thing. I’ve checked our emergency schedule: the earliest emergency arrival window I can book for you is today, 2:00 PM to 4:00 PM. There’s nothing sooner showing as available in the system right now.
CUSTOMERYeah.
CUSTOMERAlright.
CUSTOMERTwo to 4PM. That'll work. Who's coming, and how will I know they're on the way? Can you give me the ticket number?
AGENTYou’re all set; I’ve got you on the schedule as an emergency.
CUSTOMERYeah.
CUSTOMERGot it. Right.
CUSTOMERGo ahead.
CUSTOMERRight.
CUSTOMEROkay. That's fine. Can I get the ticket number, please? Who's coming out?
AGENTI’ve got everything set up for you.
CUSTOMEROkay.
CUSTOMERWait. That's not right. I moved to Unit 4 D last month. So it's 1480 Larkspur Avenue, Unit 4 D. Everything else is correct.
AGENTThanks for the correction—I’ve got your service request updated with the right unit. Here’s everything for you:
- Service address1480 Larkspur Avenue, Unit 4D
- Ticket numberCPL-58210
- Arrival windowtoday, 2:00 PM to 4:00 PM
- Emergency call‑out fee (you’re a Copperline Care member)$99
A licensed plumber will be dispatched for the burst pipe under your kitchen sink. You’ll get a text about 30 minutes before arrival to the callback number we have on file; the tech will also knock and can call if needed.
CUSTOMERRight.
CUSTOMERYep. I understand. I'll keep it clear. Thanks for your help. Goodbye.
AGENTYou’re welcome.
CUSTOMERGot it.
AGENTTake care, and we’ll see you between 2 and 4.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes. I am safe. I'm standing next to my car in a busy cafe parking lot.
AGENTI’m glad you’re safe. Is anyone injured or in danger—either in your car or the other vehicle?
CUSTOMERNo. Nobody is hurt. Both drivers are okay.
AGENTGood, thanks for letting me know. Let’s get your claim started. I’ll need your auto policy number and your last name to look up your policy.
CUSTOMERSure. My policy number is NG4471903. No. Sorry. Last one is two. My last name is Mehta.
AGENTThank you, Ms. Mehta. I’ve pulled up your policy ending in 1902 for your 2021 Honda CR‑V.
CUSTOMERThat's right. Go ahead. I am ready.
AGENTGreat.
CUSTOMERRight. Plea
CUSTOMERokay. So about the accident. Do you need any more details from me?
AGENTYes, I do need some details so we can open the claim properly. I’ll walk you through it step by step. 1) When did the accident happen? - Date and approximate time. 2) Where did it happen? - Name of the city and state, and anything more specific you can give (like the cafe name or the street address / intersection). 3) What happened? - Just describe in your own words how the accident occurred and what parts of your car are damaged. 4) Information about the other driver:
- Their name (as much as you have)
- Their insurance company (and policy number if you got it)
- Their license plate number and state
5) Did the police come to the scene? - If yes, do you have a report number or officer’s name? Also, can your Honda be driven safely, or is it not drivable (or unsafe to drive)?
CUSTOMERAlright. The accident happened about twenty minutes ago. I was stopped at a red light at Essie 5th Avenue and Alders Street. In Portland, Oregon. The other car hit the back of my car. The back bumper is crushed. And the rear wheel is rubbing. So I cannot drive it. The police did not come. The other driver is Kevin Lund. He's insured with Pacific Shore. His plate is 7KX like X-ray, R214. Origin. I do not have his policy number. Kindly let me know how much I have to pay for this. And if I'm getting a rental car. Will my premium go up? I also need a tow truck, please. And where will the car be taken?
AGENTI’ve got everything I need to get this started, thank you for the details.
CUSTOMERYes. That's right. Kindly confirm the claim number, please.
AGENTI’ve opened your claim now. - Policy number: NG4471902
- Other driver’s plate7KXR214
- Your claim numberNGM-904417
Please write that claim number down. Your assigned adjuster is Priya Shah; she’ll contact you within one business day.
CUSTOMEROkay. Got it. Claim number is NG904417. Priya Shah is the adjuster. Will you send a tow truck? And where will my car be taken? Also about the deductible, since he hit me, I should not have to pay that. Right?
AGENTLet me clear a few things up and then I’ll answer your questions.
CUSTOMERAlright.
CUSTOMERYes. Please go ahead.
AGENTLet me walk through each thing for you.
CUSTOMERSure.
CUSTOMERYes. Please continue.
AGENTThanks for your patience, Ms. Mehta. Here’s where things stand and what I can tell you from your policy.
CUSTOMEROh,
CUSTOMERYes. That's correct.
AGENTLet me go through each of your questions one by one. First, just to confirm the key details we have on file:
- Policy numberNG4471902
- Other driver’s plate7KXR214
- Your claim numberNGM-904417
Please notethe full claim number is NGM-904417 (with the “M” in there).
CUSTOMERAlright. Which tow company is coming, and where will my car be taken?
AGENTA tow truck has already been arranged for you. - Tow company: Eastside Towing
- ETAAbout 45 minutes
- DestinationA Northgate partner repair shop at 9th and Morrison in Portland
If you’d prefer the car taken somewhere else (like a shop you already use), tell me where and I can update the destination.
CUSTOMERNo. That location is fine. 9th And Morrison is good. Can you tell me about the deductible? Since he hit me, I should not have to pay that. Right? And do I get a rental car? Also, will my premium go up?
AGENTHere’s what I can see on your policy, and what I’m allowed to tell you:
1) Your deductible
- Your policy shows a $500 collision deductible. - Whether you actually end up paying that depends on fault and recovery from the other insurance (Pacific Shore). - If the repair is handled under your collision coverage, the shop/estimate will reflect your $500 deductible. - If Pacific Shore accepts full liability and pays directly, or we recover from them, your out‑of‑pocket may be reduced or reimbursed. Your adjuster, Priya Shah, will review fault and how the claim is being paid and can tell you if and when that $500 will really come out of your pocket. 2) Rental car coverage
Your policy includes rental reimbursement$40 per day, up to 30 days, from the day the claim is opened. - That means we’ll reimburse (or set up direct bill, depending on the rental company) up to $40 per day while your car is down for covered repairs, up to 30 days total. - Priya can help you with the actual rental setup and timing once she speaks with you. 3) Will your premium go up? I’m not able to see or predict future premium changes or rating decisions. - Any change to your premium would depend on fault, state rules, and your overall policy history. - Your adjuster can explain how the claim is classified on your record; underwriting uses that, but they are separate from claims, so no one on the claims side can promise that your premium will or will not go up. To recap the key numbers:
- Policy numberNG4471902
- Other driver’s plate7KXR214
- Claim numberNGM-904417
Next stepPriya will contact you (typically **within one business day**) to go over fault, how the deductible will apply in your situation, set up the rental details, and keep you updated on repairs. Is there anything else you’re worried about right now—like getting updates from the repair shop or what to do when the tow truck arrives?