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.
#269 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.
#357 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.
#172 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.
#363 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.
#498 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.
#559 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.
#332 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.
#167 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.
#376 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#391 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 94% | 3.67 s | — |
| Home services | 78% | 2.28 s | — |
| Insurance | 98% | 3.23 s | — |
| Customer support | 100% | 3.57 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 3.07 s | — |
| Spanish-accented English, city street | 90% | 3.48 s | — |
| Indian English, busy café | 90% | 2.63 s | — |
| Southern US, flustered, crying baby | 96% | 4.11 s | — |
| Fast and interrupting, construction outside | 94% | 3.30 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi Alex, my internet has been down for about 2 hours now. There's a road crew digging up the street outside, so I'm wondering if that might be the cause. I already rebooted the gate gateway twice and checked all the cables, but the internet light is blinking orange. My account number is BW883017. Sorry, last digit is 1. Can you check if there's an outage in my area or if the roadwork is affecting the connection?
AGENTYou’re right, the account number is BW883011 — got it. Here’s what I see on my side: - No area outage or maintenance is showing for your address, so nothing official tied to that roadwork. - Your line signal to the gateway looks good. - A moment ago your gateway wasn’t registered, so I sent a remote reset. - After the reset, your gateway is now registered and online. Devices may take up to 2 minutes to fully reconnect. Please check: 1.
CUSTOMEROkay.
CUSTOMERThe internet light just went solid white. How long until my devices reconnect? And since I lost 2 hours of work, can you add a credit for the downtime?
AGENTSolid white is exactly what we want—that means the gateway is online again. Timing for your devices: - Most phones, laptops, and tablets should reconnect within 1–2 minutes. - If anything doesn’t come back on its own after about 2–3 minutes, toggle Wi‑Fi off/on on that device, or briefly forget/rejoin the network. No need to reboot the gateway again. About the credit: I’ve added a $10.00 service credit for the 2 hours of downtime. It will appear on your next bill under service adjustments. Before we wrap up, can you confirm at least one device (like your phone or computer) is back online and able to load a website?
CUSTOMERYeah, my laptop just came back online and I can load websites now. About the credit, I lost 2 hours of work. Can you make it more than $10?
AGENTYour connection looks good now, and I’m glad your laptop is back online. On the credit: I’ve already applied a $10.00 service credit to account BW883011, which will show on your next bill. That’s the standard amount I’m
CUSTOMEROkay.
AGENTI get why you’re asking, especially after losing actual work time. I’ve already applied the $10.00 credit to account BW883011
AGENTand that’s the maximum I’m allowed to issue directly. I don’t have the ability to increase it from here. If you want to push for more, you have two options: - Use the “Billing/Adjustments” section in your Brightwave account portal to request a review, or. - Call in and ask for a supervisor or billing specialist and mention the roadwork and 2+ hours of downtime. Is there anything else with the connection itself you want to check while we’re on the line—speed, specific apps, or work VPN?
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, uh, yes, I'm calling because I need to move my dermatology appointment next Wednesday morning. I just got a work shift for that time, so I can't make it. My name is Lucia Ramirez. Can you help me reschedule?
AGENTI can help with that. To pull up your chart and appointments, I need to verify you first. Please tell me your full date of birth (YYYY-MM-DD), and I’ll look up your account and then find your dermatology appointment for next Wednesday morning.
CUSTOMERYeah, sure. March 17th, 1948. Sorry, no, 1984. March 17th, 1984.
AGENTThanks, Ms. Ramirez. I’ve found your dermatology visit with Dr. Okafor next Wednesday at 09:15. What time of day works for you instead so I only offer slots that fit? - Still on Wednesday, but later in the day? - Or a different day (and if so, which days
CUSTOMEROh yeah, so I can only come after 3 PM. Do you have anything later in the day on Wednesday, or maybe another day after 3?
AGENTI checked Dr. Okafor’s schedule starting next Wednesday for times after 3 PM. Here’s what’s available that fits what you asked for: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. There’s also a Friday at 11:30 AM, but that’s before 3 PM, so it doesn’t match your constraint.
CUSTOMEROkay, Tuesday doesn't work for me after all because I pick up my daughter then. What about Friday? Do you have anything after 3 PM on Friday? Or Thursday at 4:10 PM could work too.
AGENTRight now I’m only seeing one late-day option that fits what you’ve told me: - Thursday at 4:10 PM with Dr. Okafor. On Friday, the only slot I see is 11:30 AM, and there’s nothing after 3 PM. Would you like me to move your appointment from next Wednesday at 9:15 AM to Thursday at 4:10 PM with Dr. Okafor?
CUSTOMERYes, that's exactly right. Please move it to Thursday at 4:10 PM with Dr. Okafor. Oh, is there any fee for changing the appointment?
AGENTYou’re all set, Ms. Ramirez. I’ve moved your dermatology appointment with Dr. Okafor from next Wednesday at 9:15 AM to Thursday at 4:10 PM at the 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:
CUSTOMEROkay, go ahead. What about the fee for changing the appointment? Is there any charge?
AGENTThere’s no charge for this change. Our policy is: changes made more than 24 hours before the appointment are free; only changes within 24 hours carry a $40 fee. Since we rescheduled your visit well in advance, you won’t be charged anything for moving it to Thursday at 4:10 PM.
CUSTOMERThat's good to know, thank you. Oh, where can I park when I come to the clinic?
AGENTYou can park for free in Patient Lot C. The entrance to Lot C is on River Road. From there, follow the signs for Main Campus, Building B for your dermatology appointment.
CUSTOMERGot it. And, uh, does Dr. Okafor accept Aetna insurance?
AGENTI don’t have access to up‑to‑date insurance panel details for individual providers, so I can’t safely confirm that for you. To be sure about Aetna coverage with Dr. Okafor, please either: - Call our front desk so they can check your specific Aetna plan against Dr. Okafor’s billing profile, and/or. - Check with Aetna (website or member services) using “Riverbend Health Clinic / Dr. Okafor” as the provider. I recommend having your Aetna member ID handy and confirming: - Whether Dr. Okafor is in‑network for your exact plan, and. - Any copay, deductible, or referral requirements for dermatology.
CUSTOMEROkay, I'll do that. So just to confirm, my new appointment is Thursday at 4:10 PM with Dr. Okafor, and the confirmation code is RVB3M8P2. Is that correct?
AGENTAlmost—just one small detail on the code. Your new appointment is: - Day/Time: Thursday at 4:10 PM. - Provider: Dr. Okafor.
CUSTOMERYes, that's right. Thursday at 4:10 PM, Dr. Okafor. Confirmation code: RVB3M8P2. Thank you for your help. Goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi Alex, I have a burst pipe under my kitchen sink and water is spreading across the floor heading toward a power strip. I need someone to come out urgently. Can you help with this?
AGENTYes, I can help, and we’ll treat this as an emergency. First, let’s keep you safe:
CUSTOMERAll right.
CUSTOMEROkay, go ahead.
AGENTThanks. Let’s handle safety first. 1. Stay away from that power strip. Don’t touch it, the outlets, or anything plugged into it if there’s water nearby. 2. Unplug the power strip only if it’s 100% dry and you can reach the plug without stepping in water. - If there’s any doubt, don’t touch it. - If water is already at the strip or outlets, go to your breaker panel and switch off power to the kitchen (or the whole house if you’re unsure which breaker it is). 3. Shut off the water: - Look under the kitchen sink for two small shutoff valves (one for hot, one for cold) on the pipes going to the faucet. Turn both clockwise until they stop. - If they won’t turn or water keeps flowing, go to your main water shutoff (often in the basement, garage, or outside near the street) and turn that clockwise to shut water to the whole house. Please let me know: - Have you turned off the water (under the sink or main)? - Is the power strip in or touching any water right now? Once you’ve done what you safely can, I’ll get this set up as an emergency visit.
CUSTOMERI've just turned off the water under the sink and the flow has stopped. The power strip is not submerged, but water was getting close. I have moved away from it and not touched any Can you tell me how much the emergency visit will cost? And is it possible for someone to come before 2 PM?
AGENTGood job getting the water shut off and staying away from that power strip.
CUSTOMERHello?
AGENTI’m here—thanks for hanging on. Here’s what I can tell you: - The earliest emergency arrival window
CUSTOMERAha, right.
AGENTThanks for your patience, and I’m glad you got the water stopped. On your questions: 1) Cost
CUSTOMERCan anyone come before 2 PM?
AGENTI’ve checked our emergency schedule: the earliest emergency arrival window
CUSTOMEROkay, what will the visit cost and who will—
AGENTThanks for sticking with me.
CUSTOMERCould you let me know the cost for the emergency visit and who will be coming?
AGENTI checked our schedule
CUSTOMERThat's right. So about the emergency visit, how much will it cost and who will be coming?
AGENTI’ve got
CUSTOMERAll right, can you confirm the cost and who will be coming for the emergency visit?
AGENTI’ve got the details on cost;
CUSTOMEROkay, go ahead.
AGENTThanks for waiting. Here’s what I can confirm from our system: - Emergency visit fee:
CUSTOMERAll right, please let me know the cost
AGENTThanks for hanging in there. Here’s what I can see in our system right now: -
CUSTOMERRight, what is the emergency visit fee?
AGENTThe emergency visit fee I’m seeing in our system is:
CUSTOMEROkay, go ahead.
AGENTThanks for your patience. Here’s what I can see in our system right now: - Emergency visit fee:
CUSTOMERAll right, could you tell me the exact
AGENTThanks for sticking with me. Here’s the exact info from our system: - Emergency
CUSTOMEROkay, what is the emergency visit fee?
AGENTThe emergency visit fee in our system is:
CUSTOMERRight, please go ahead.
AGENTThe emergency visit fee is $149 for the call-out. If you’re
CUSTOMERUh-huh. Kindly tell me
AGENTThanks for bearing with all that back-and-forth. From our system, the emergency
CUSTOMEROkay, so $149.
AGENTCorrect, the emergency call-out fee is $149.
CUSTOMERRight, so I understand the emergency visit fee is one—
AGENTYes, the emergency
CUSTOMERYes, that's clear. $149 for the emergency call-out. Can someone—
CUSTOMERUh-huh. So can anyone come before 2 PM?
AGENTNo—based
CUSTOMERHello?
AGENTI’m here. I’ve
CUSTOMERAll right, what is the earliest time someone can come for this emergency visit?
AGENTThe earliest emergency arrival window
CUSTOMEROkay, what is the earliest emergency window available?
AGENTThe earliest emergency arrival window I see
CUSTOMERRight, what time is the earliest emergency arrival?
AGENTThe earliest emergency arrival window I see is today from 2:00
CUSTOMERGo ahead. What is the earliest emergency arrival window?
AGENTThe earliest emergency arrival window I see is today
CUSTOMERUh-huh. What time is that window?
AGENTfrom
AGENTThe earliest emergency arrival window I see is today from 2:00
CUSTOMEROkay, what time today is the earliest emergency arrival?
AGENTThe earliest emergency arrival window today is
CUSTOMERRight, what is the time for that window today?
AGENTThe earliest emergency arrival window today is from 2:00 PM
CUSTOMEROkay, please tell me the time for the earliest emergency
AGENTThe earliest emergency arrival window today is
CUSTOMERAll right, I'll take the 2:00 PM emergency window. Who will be coming?
CUSTOMERUh-huh. Please tell me the time for the earliest emergency arrival window today.
AGENTThe earliest emergency arrival window today is from 2:00 PM to 4:00 PM. Before I lock that
CUSTOMERHello?
AGENTI’m here. Let me lay everything out clearly. 1) Earliest emergency arrival
CUSTOMERAll right.
CUSTOMERWho will be coming?
AGENTThanks for sticking with this; I know you’ve got a lot going on with that leak.
CUSTOMEROkay, to confirm, I'll take the earliest emergency
AGENTPerfect, I’ve got you set
CUSTOMERUh-huh. So who will be coming for the emergency visit, and how will I know?
CUSTOMERWho will be coming and how will I know they are on the way? Also, can you provide the ticket number for this visit?
AGENTYou’re all set for this afternoon. Here are the details: - Technician: Dana will be
CUSTOMERHello?
AGENTYou’re all set, and I’ll summarize everything clearly: 1) Who is coming and how you’ll know.
CUSTOMERAll right, Dana will be the tech—
AGENTYou’ve got it. Let me confirm everything cleanly: 1) Who
CUSTOMERRight, so Dana is coming.
AGENTCorrect—Dana is the technician scheduled for
CUSTOMEROkay, go ahead.
AGENTHere are the key details for your emergency visit: - Technician:
CUSTOMERYes, that's right. Dana is the technician
AGENTThat’s right—Dana
CUSTOMERAll right.
AGENTis
CUSTOMERDana, correct. And how will I know they are on the way?
AGENTYes,
CUSTOMERuh-huh. How will I know Dana is on the way? And could you give me the ticket number for this visit?
CUSTOMEROkay, will I get a call or a text when Dana is on the way? And may I have the ticket number for this emergency visit?
AGENTYou’ll get a text when Dana is on the way. Here are the details: - How you’ll know they’re coming: Dana will text your callback number about 30 minutes before arrival, letting you know they’re on the way and giving an ETA. - Ticket number: Your emergency visit is booked under ticket CPL-58210. While you’re waiting, keep the water shut off under the
AGENTsink and stay clear of that power strip and any outlets near the wet area.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I'm somewhere safe. I'm standing next to my car. Nobody is hurt.
AGENTI’m glad to hear no one is hurt. Let’s get your claim started. I’ll just need a few details and then I’ll open the claim for you. 1) What’s your auto policy number, and the policyholder’s last name?
CUSTOMERMy policy number is NG4471903. No, sorry, last one is 2. The policyholder's last name is Ellis.
AGENTThanks, I’ve pulled up your policy ending in 1902 under Ellis. Next I’ll collect the accident
CUSTOMEROkay.
AGENTFirst,
CUSTOMERSure, go ahead.
AGENTAlright, thank you. 1) When did the accident happen? 2) Where did it happen (city and street or intersection)? 3) Please briefly tell me what happened.
CUSTOMERThe accident happened about 20 minutes ago. It was at the intersection of SE 5th Avenue and Alder Street here in town. I was stopped at a red light and another car hit the back of my car. The driver was Kevin Lund, insured with Pacific Shore. Nobody is hurt, but my back bumper is crushed and the rear wheel rubs, so I can't drive it. Police did not come.
AGENTI’ve got everything I need to open the claim, and we’ll get your car taken care of. Here’s what I have so far—stop
CUSTOMERAll right.
AGENTI’ll walk
CUSTOMERRight, go ahead.
AGENTHere’s what I’ve set up and what happens next. 1) Policy and claim details. - Your policy number: NG4471902 under Ellis. - I’ve opened a claim: NGM-904417. - Assigned adjuster: Priya Shah – she’ll contact you within one business day. 2) Accident details I recorded. - Time: About 20 minutes before you called. - Location: Intersection of SE 5th Avenue and Alder Street. - What happened: You were stopped at a red light and were rear‑ended. - Damage: Rear bumper crushed and rear wheel rubbing, not safe to drive. - Other driver: Kevin Lund, insured with Pacific Shore. - Police: Did not
CUSTOMERYes.
AGENTThanks
CUSTOMERThat's correct. Police did not come.
AGENTThanks for confirming that the police did not come. I have your details recorded as: - Policy number: NG4471902. - Claim number: NGM-904417. - Other driver: Kevin Lund, insured with Pacific Shore. - No police on scene and no report taken. One thing I don’t have yet is the other car’s license plate. Do you happen to have that now (maybe from a photo or exchange of info), or is it still unknown?
CUSTOMERYes, I have it. The plate is 7KX, like X-ray, R214.
AGENTGot it, thank you. I’ve updated the claim with the other vehicle’s plate number. Let me read back the key details so you can confirm everything is right: - Policy number: NG4471902 - Claim number: NGM-904417 - Other driver: Kevin Lund, insured with Pacific Shore - Other vehicle license plate: 7KXR214 - Police did not attend; no report filed That’s what I have on file now. Is all of that correct, or is there anything I should fix?
CUSTOMERYes, that's all correct. Nothing needs to be fixed. Can you tell me how much I have to pay for this? Will I get a rental car, and is my premium going to go up? Also, I need a tow truck since I can't drive the car. Where will it be taken?
AGENTHere’s what I can tell you based on your policy and what’s already been set up. First, reading back your key info: - Policy number: NG4471902. - Claim number: NGM-904417. - Other vehicle license plate: 7KXR214. Coverage details from your policy: - Collision deductible: $500. - This is the amount you’re responsible for toward the repairs on your Honda. - If we’re able to collect from the other driver’s insurer (Pacific Shore), some or all of that may be reimbursed later, but that part will be handled by your adjuster. - Rental coverage: $40 per day, up to 30 days, starting from the day the claim was opened. - So yes, you do have rental coverage. Your adjuster, Priya Shah, will help you set up a rental through one of our partner rental companies, or explain how reimbursement works if you arrange it yourself. - Towing coverage: Covered up to 25 miles. - You’re within that limit for the tow we’ve arranged. About your premium going up: - I don’t have access to rating or renewal decisions, so I can’t say if or how your premium will change. - What I can say is: your adjuster will review fault, the police/non-police info, and the other driver’s insurance. Any premium impact is determined later by underwriting and state rules, not at the claims intake stage. Tow truck details: - A tow has already been dispatched for you. - Tow company: Eastside Towing. - Estimated arrival: about 45 minutes from dispatch. - Destination: a Northgate partner repair shop at 9th and Morrison. If you’d prefer the car to go somewhere else (for example, a shop you trust or your home), tell me now and I can note that for the adjuster, but the current destination on the order is our partner shop at 9th and Morrison. Do you want the vehicle to stay going to that partner shop, or would you like it to be towed somewhere different?
CUSTOMERThe partner shop at 9th and Morrison is fine. Please leave it as is.
AGENTOkay, we’ll leave the tow as set to the partner shop at 9th and Morrison. Here’s a quick recap of what you have in place: - Policy number: NG4471902. - Claim number: NGM-904417. - Tow: Eastside Towing, going to the Northgate partner repair shop at 9th and Morrison. - Coverage (from your policy): - Collision deductible: $500. - Rental: $40/day, up to 30 days, from today. - Towing: Covered up to 25 miles (your tow fits within this). Next steps: - The tow truck should arrive roughly within the original 45‑minute ETA. - Adjuster: Priya Shah will contact you within one business day to go over repairs, rental setup, and any questions about costs or possible reimbursement from the other driver’s insurer. Is there anything else you want to know about what happens after the car gets to the shop, or anything you want me to note for your adjuster (like preferred contact number or times)?
CUSTOMERNo, that covers everything I needed. My preferred contact number is the one I'm calling from: 907-416-4884. No special times. Anytime works. Thank you for your help. Goodbye.