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
#248of 654 stacks
51 / 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.
#266 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.
#511 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.
#537 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.
#561 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.
#577 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.
#598 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.
#78 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.
#67 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.
#347 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#55 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 89% | 2.89 s | — |
| Home services | 95% | 3.21 s | — |
| Insurance | 100% | 2.63 s | — |
| Customer support | 87% | 2.69 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 3.07 s | — |
| Spanish-accented English, city street | 96% | 2.89 s | — |
| Indian English, busy café | 96% | 3.22 s | — |
| Southern US, flustered, crying baby | 86% | 2.75 s | — |
| Fast and interrupting, construction outside | 87% | 2.38 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 has been down for about two hours now, so I was wondering if that's the cause.
CUSTOMERI work from home, so it's been pretty disruptive. The internet light on my gateway is blinking orange. I already rebooted it twice and checked all the cables, but nothing changed. Can you help me figure out what's going on?
AGENTI checked your line and there’s no area outage at your address, and your account is BW-883011. Your gateway had dropped its registration on our side, so I just pushed a remote reset. It’s now showing as registered and online again. Over the next 1–2 minutes: - The internet light should turn solid (not blinking orange). - Your devices may briefly disconnect and then reconnect to Wi‑Fi. Please check: 1. Is the internet light now solid on the BX7? 2. Can you get online on your work computer or phone (maybe try a quick website)? If it’s still not working after a couple of minutes, tell me what the gateway lights are doing and whether it’s just Wi‑Fi devices or also anything plugged in by Ethernet.
CUSTOMERThe internet light just went solid white. How long until my devices reconnect?
AGENTGood—that means the connection is back up on our side. Most devices will reconnect within about 1–2 minutes on their own. If something doesn’t: - On Wi‑Fi devices: toggle Wi‑Fi off/on and reconnect to your network. - On wired devices: unplug the Ethernet cable and plug it back in, or disable/enable the network adapter. If anything is still offline after a couple of minutes, tell me which device it is and what error you see, and we’ll sort that out.
CUSTOMEROkay.
CUSTOMERGot it. Since I lost two hours of work. Can I get a credit for the downtime?
AGENTYes, I can do that. I’ve applied a $10.00 credit on account BW-883011 for about two hours of downtime. You’ll see it on your next bill as a service interruption credit. If the connection drops again or you notice anything odd (frequent blinking orange, random disconnects), let me know and we’ll dig deeper.
CUSTOMERI lost. Two hours of work. Can you make it more than that?
AGENTI understand why you’re asking, especially if that time wasn’t recoverable. I’m limited to the standard outage credit, and I’ve already applied the maximum I can on my side: $10.00 on account BW-883011, which will show on your next bill. If you’d like to request an additional adjustment beyond what I’m authorized to give, I can note the account with what happened and you can: - Contact Billing through your Brightwave account portal, or. - Call in and ask for a supervisor to review the situation. I’m sorry for the impact on your work—if you want, I can also help you set up a quick connection check (like monitoring drops or logging events) so if this happens again, there’s a clear record for billing or support to reference.
CUSTOMEROkay. Understood. Thanks for your help. Alex.
CUSTOMERGoodbye.
AGENTYou’re welcome—glad we got you back online. Before you go, just to recap:
AGENTthere’s a $10.00 credit on account BW-883011 that will show on your next bill. If you have issues again, just reach out and we’ll take another look. Goodbye, and take care.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey.
CUSTOMERYeah. Sorry. I've got a baby hollering in the background, so I might talk kind of quick.
CUSTOMERI need to move my dermatology appointment next Wednesday morning. I just found out I've got a work shift then.
CUSTOMERMy name's Wade Carter.
AGENTI can
CUSTOMERCan you help me with that?
AGENTI can help you reschedule that.
CUSTOMERLa.
AGENTI can help with that. I’ll just need a couple details to get started. 1.
CUSTOMERThat's good. Thank you.
CUSTOMERI'm a little worried. This.
CUSTOMERWill mess things up. So please tell me if there's any issue.
CUSTOMERI can only come after 3 p.m., if that's all right.
CUSTOMERAll right.
CUSTOMERSorry if I sound frazzled.
CUSTOMERI just want to make sure this gets taken care of.
CUSTOMERGo ahead. What do you need from me?
AGENTNo problem at all, we’ll take care of this step by step. To look you up and see that dermatology appointment for next Wednesday morning, I need: 1. Your full date of birth (YYYY-MM-DD). 2. Just to confirm: is the appointment with Dermatology at Riverbend Health Clinic next Wednesday morning, and you’d like to move it to any day/time after 3:00 p.m.? Once I have your date of birth, I’ll: - Verify your chart. - Find that Wednesday appointment. - Look for dermatology openings after 3 p.m. - Tell you what’s available and move it if you like. Go ahead with your date of birth when you’re ready.
CUSTOMERYeah. It's March. 17th, 1948.
CUSTOMEROh, wait. Sorry. That's not right.
CUSTOMERIt's 1984.
CUSTOMERMarch 17th, 1984.
CUSTOMERIs that okay?
AGENTThanks, Wade, and no worries—you’re all good so far. I’ve got you verified as Wade Carter, date of birth March 17, 1984, and I do see your dermatology appointment next Wednesday at 9:15 a.m. with Dr. Okafor at the Main Campus, Building B. You said you can only come after 3:00 p.m. Here are the next available options with Dr. Okafor that meet that: - Tuesday at 3:45 p.m. - Thursday at 4:10 p.m. There’s also a Friday 11:30 a.m. slot, but that’s before 3 p.m, so it doesn’t fit what you asked for. Which one would you like to move your appointment to: Tuesday at 3:45 p.m. or Thursday at 4:10 p.m.?
CUSTOMERSorry. Tuesdays don't work out.
CUSTOMERAll. I pick up my daughter, then.
AGENTGot it—no Tuesdays. The dermatology options with Dr. Okafor that are after 3 p.m. and not on Tuesday are: - Thursday at 4:10 p.m. Right now, that’s the only after‑3 p.m. slot I see that fits what you’ve told me. Do you want me to move your next Wednesday 9:15 a.m. appointment to Thursday at 4:10 p.m. with Dr. Okafor?
CUSTOMERYeah, I think
AGENTTotally understand—you’ve
CUSTOMERso. Sorry to be a bother,
CUSTOMERbut. I.
AGENTYou’re not a bother at all—this is exactly what I’m here for. Right now I see only one after‑3 p.m. option with Dr. Okafor that isn’t on Tuesday: - Thursday at 4:10 p.m. You mentioned you pick up your daughter then and “yeah, I think so,” so before I change anything, I want to be sure: Do you definitely want me to move your dermatology appointment from next Wednesday at 9:15 a.m. to Thursday at 4:10 p.m. with Dr. Okafor, or would you rather: - Keep the current Wednesday 9:15 a.m. slot, or. - Have me look for later options on a different day or with a different dermatologist after 3 p.m.? Tell me which you prefer, and I’ll take care of it.
CUSTOMERI'm sure. Thursday at 4:10. P.m. with Doctor Okafor is what I need.
CUSTOMERThat's the only time that works for me. Is there any fee for changing the appointment.
AGENTThanks for confirming, Wade. I’ve gone ahead and moved your appointment. Here’s what you have now—let me read it back clearly: - Name: Wade Carter. - Date of birth: March 17, 1984. - New appointment: Thursday at 4:10 p.m. - Provider: Dr. Okafor, Dermatology. - Location: Main Campus, Building B. - Confirmation code: RVB-3M8P2. Arrival instructions: please arrive 15 minutes early with a photo ID and your insurance card. About fees for changing the appointment: The clinic’s policy is: changes made more than 24 hours before the appointment are free; later changes carry a $40 fee. You’re changing this more than 24 hours in advance, so there is no fee for this change. Anything else you want me to check or clarify about this new Thursday 4:10 p.m. appointment?
CUSTOMERAll right. That's a relief. Thank
AGENTYou’re welcome, Wade. Just to recap one last time so you know it’s all set: your dermatology visit is now on Thursday at 4:10 p.m. with Dr. Okafor, confirmation code RVB-3M8P2, and there’s no fee for the change. If anything else comes up—timing, directions, or questions about the visit—just let me know and we’ll sort it out.
CUSTOMERyou. Um, could you tell me where to park for the main campus? Sorry.
CUSTOMERI just want to be sure. Where should I park for the main campus.
CUSTOMERDoes Doctor Okafor accept Aetna insurance?
AGENTFor parking at the Main Campus: You can park in Lot C, which has free patient parking. The entrance to Lot C is on River Road. About your insurance: I don’t have a tool that shows provider-specific insurance panels, so I can’t safely confirm whether Dr. Okafor currently accepts Aetna. To be 100% sure, you should either: - Call the main clinic line and ask if Dr. Okafor is in-network for Aetna, and/or. - Call the number on the back of your Aetna card and ask them to verify Dr. Okafor at Riverbend Health Clinic. If you’d like, I can help you draft exactly what to say when you call so it’s quick and easy.
CUSTOMERIt's all. Right. I'll call and check myself.
CUSTOMERYou've been real helpful and I appreciate
AGENTI’m glad I could help, Wade. One last quick recap so you don’t have to wonder later: - Appointment: Thursday at 4:10 p.m. - Provider: Dr. Okafor, Dermatology. - Location: Main Campus, Building B. - Confirmation code: RVB-3M8P2. - Parking: Free patient parking in Lot C, entrance on River Road. If you think of anything else—directions, timing, or questions before the visit—just reach out. Good luck with the work shift and I hope things are a little calmer with the baby soon.
CUSTOMERit. I think that covers everything.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. Yeah.
CUSTOMERI have an emergency. The pipe under my kitchen sink just burst.
CUSTOMERAnd water is spreading across the floor toward a power strip. Oh, I haven't shut the water off yet.
CUSTOMERCan you send someone out?
AGENTThanks for telling me right away—let’s get you safe first. 1. Stay away from that power strip and any outlets the water is near. Don’t touch it. 2. If you can safely reach it without stepping in water, either: - Unplug the power strip from the wall by the plug, with dry hands and feet on a dry surface, or. - If it has a switch, flip it off. If there’s any chance you’d be standing in water or getting splashed, do not touch it. 3. If it’s not safe to reach the strip, the next safest step is to shut off power to that area at your breaker panel: - Stand on something dry (like a rubber-soled shoe or a dry mat). - Open your electrical panel and flip off the breaker(s) for the kitchen or that outlet circuit, or the main breaker if you’re unsure. 4. Next, let’s shut off the water: - Do you know where your main water shutoff is? It’s often: - In a basement, utility room, or garage, or. - On an outside wall where the water line enters the house. - Look for a lever handle (turn it 90° so it’s across the pipe) or a round valve (turn clockwise until it stops). - If you can’t find the main, check under the kitchen sink for local shutoff valves and turn those clockwise. Please tell me: - Are you able to stay clear of the water near that power strip right now? - Have you turned off either the power to that outlet or the main breaker, and. - Were you able to shut off the water or at least slow it down? Once I know you’re safe, I’ll get an emergency technician dispatched.
CUSTOMEROh, yes.
CUSTOMERI'm staying away from the power strip. I can't reach it safely, so I won't touch it. I just flipped off the main breaker. So the power is off now.
CUSTOMERAnd I'm turning the water off. Okay. Yeah. The water has stopped, so I think I'm safe now. Can you send someone out?
AGENTGood job getting everything shut off—that was exactly the right move. Yes, we can send someone. We can do an emergency visit today, 2:00 PM to 4:00 PM. The emergency callout fee is $149, due on completion by card or check. That’s just for the visit/diagnosis; any repair costs would be approved with you first. Does that time window and fee work for you? If so, I’ll just need to get you booked: - Your service address (including unit, if any). - Any gate code or access instructions. - Your best callback number. While we set that up, please: - Keep the main breaker off until our technician tells you it’s safe to turn it back on. - Keep everyone (kids, pets) away from the kitchen area and that power strip and any damp outlets. - If you have towels or a mop, you can carefully soak up standing water, but only in areas you know are well away from any outlets or cords.
CUSTOMERCan anyone come before 2 p.m.? I really need the earliest window possible. And, yeah, my address is 1480 Larkspur Avenue. I just moved.
CUSTOMERI'm in unit 4D now, not four B. The gate code is pound 2719. My call back number is 503.
CUSTOMER5550139.
CUSTOMERNo, 0193. Can you tell me who will be coming and how I'll know they're on the way? Also, I'd like to hear the ticket number for this visit.
AGENTThanks for all the details, and good job catching that phone number correction. Right now, the earliest emergency window I can see is today, 2:00 PM to 4:00 PM. There’s nothing available earlier showing in our system, and with the water and electrical risk you described, I’ve already set this up as an emergency priority so you’re in the first available slot. Since you’re a Copperline Care member, your emergency callout fee is $99 (instead of $149). That’s due on completion by card or check; any repair costs will be discussed and approved by you before work is done. Before I finalize the booking, can you confirm you agree to: - Emergency visit today, 2:00–4:00 PM. - Emergency callout fee: $99. Here’s what I have on file for this ticket: - Service address: 1480 Larkspur Avenue, Unit 4D. - Gate code: #2719. - Callback number: 503-555-0193. - Ticket number: CPL-58210. Please confirm that all of that is correct. Regarding who’s coming and how you’ll know: - A Copperline Home Services plumbing technician will be dispatched on this ticket. I don’t have their individual name in this system, but they’ll be a uniformed Copperline tech with ID. - You’ll get a call or text at 503-555-0193 when the technician is on the way, and the arrival will be within the 2:00–4:00 PM window. Until we arrive: - Keep the main breaker off and stay away from the power strip and any outlets in the wet area. - You can continue soaking up water with towels or a mop in areas away from outlets and cords. Once you confirm the window and fee, I’ll consider this visit fully booked under ticket CPL-58210.
CUSTOMERYes that's correct.
CUSTOMERI confirm that 2 p.m. to 4 p.m. window.
CUSTOMERAnd the emergency call out fee of $99.
CUSTOMERThe address unit gate code, and callback number you read out are right.
CUSTOMERAnd I got the ticket number CPL 58,270 for your help. Goodbye!
AGENTI’m glad you’re safe and all set for today. One quick correction before you go: your ticket number is CPL-58210 (five-eight-two-one-zero), not 58,270. You’re booked for today, 2:00–4:00 PM, with the $99 emergency callout fee confirmed, at: - 1480 Larkspur Avenue, Unit 4D. - Gate code: #2719. - Callback: 503-555-0193. Please keep the main breaker off and stay clear of that power strip and any wet outlets until our technician arrives and says it’s safe. We’ll call or text when we’re on the way.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes.
CUSTOMERI'm standing next to my car.
CUSTOMERI am at a cafe.
CUSTOMERSo it is safe here.
AGENTI’m glad you’re safe. Is anyone injured or in any danger at the scene—either in your car, the other car, or nearby? If anyone is hurt or in danger, please hang up and call 911 right away before we continue.
CUSTOMERNobody is hurt.
CUSTOMERAnd there is no danger.
CUSTOMERIt is just the damage to the back of my car. Can we proceed?
AGENTYes, we can proceed. I’m going to get some details so we can open a claim for you. First, I need to locate your policy. 1. Do you have your Northgate Mutual auto policy number handy? 2. And what is the policyholder’s last name as it appears on the policy?
CUSTOMERYes.
CUSTOMERI have the policy number.
CUSTOMERIt is n g.
CUSTOMER4471903. No. Sorry.
CUSTOMERLast one is two. The last name is Mehta.
AGENTThank you, I’ve verified your policy as NG4471902 under the name Mehta, covering a 2021 Honda CR‑V. Next, I’ll collect the accident details so we can open your claim. 1. When did the accident happen? 2. Where did it happen? 3. Please briefly describe what happened to the back of your car. 4. Was another vehicle involved? If yes: - The other driver’s name. - Their insurance company (if you have it). - Their license plate number. Also, did the police come to the scene or was any report taken?
CUSTOMERThe accident happened. About 20 minutes ago at the intersection of SW fifth Avenue and Alder Street.
CUSTOMERI was stopped at a red light when another car hit the back of my car.
CUSTOMERThe back bumper is crushed and the rear wheel is rubbing.
CUSTOMERSo I cannot drive
AGENTThanks for explaining what happened, and I’m glad you’re okay. Since the rear wheel is rubbing, please don’t try to drive the car—it’s not safe. I need just a few more details
CUSTOMERit. Another vehicle was involved.
CUSTOMEROkay.
CUSTOMERGo ahead.
AGENTThanks. I’ll get the rest of the details and then we’ll open your claim and arrange a tow. First about the other driver and police: 1. What is the other driver’s name? 2. Do you know their insurance company? 3. What is their license plate number? 4. Did the police come to the scene, and if
CUSTOMERThe other driver's name is Kevin Lund.
CUSTOMERHis insurance company is Pacific Shore. The license plate number is seven K.
CUSTOMERX, like X-ray.
CUSTOMERR.
CUSTOMER214. The police did not come to the scene, and no report was taken.
AGENTI’ve got everything I need to get this started, and I’m sorry this happened to you. Here’s what I’ve set up: 1. Policy and accident details (for your records). - Verified policy number: NG4471902 under Mehta. - Location: Intersection of SW 5th Avenue and Alder Street. - What happened: You were stopped at a red light when Kevin Lund, insured with Pacific Shore, rear‑ended your 2021 Honda CR‑V. - His license plate: 7KXR214. - No injuries, and police did not attend and no report was taken. 2. Your claim is now open. - Claim number: NGM-904417. - Assigned adjuster: Priya Shah. - She will contact you within one business day to go over next steps, coverage, and repairs. 3. Tow truck details. Since your rear wheel is rubbing, please do not drive the car. - I’ve arranged a tow through Eastside Towing. - ETA: about 45 minutes to your location at SW 5th & Alder. - Destination: a Northgate partner repair shop at 9th and Morrison. While you’re waiting for the tow: - Turn on your hazard lights if you’re still near the intersection. - Remove any valuables you can easily carry from the vehicle. Before we wrap up: - Is NG4471902 the correct policy number as you understand it? - Is 7KXR214 the correct license plate for the other driver? Also, what is the best phone number for you, in case the tow driver or your adjuster needs to reach you?
CUSTOMERYes. That's correct.
CUSTOMERN. G.
AGENTThank
CUSTOMER4471902 is my policy
AGENTGot it, thank
CUSTOMERnumber. The other drivers plate is seven.
CUSTOMERK.
AGENTThank you for the correction. Let me read these back clearly so we have them right: - Your policy number: NG4471902. - The other driver’s license plate begins with: 7K (seven K). I have it recorded as 7KXR214. If anything after the 7K is different (the X, R, or the 214), let me know and I’ll fix it. Also, I’ve confirmed your coverage on policy NG4471902: - Collision deductible: $500. - Rental coverage: $40 per day for up to 30 days, starting from the day the claim is opened. - Towing: Covered up to 25 miles. Your claim number is NGM-904417. Your adjuster will be Priya Shah, and she’ll contact you within one business day. Two quick things to finish up: 1. Can you confirm the full license plate for the other driver (after “7K”)? 2. What is the best phone number for you, in case the tow driver or your adjuster needs to reach you?
CUSTOMERYes. The full license plate is. Seven.
CUSTOMERK.
CUSTOMERX like X-ray. R.
CUSTOMER214.
CUSTOMERThe best phone number is 1320.
CUSTOMER3222543.
AGENTThank you, I’ve updated everything with your corrections. Here’s what we have on file now: - Your policy number: NG4471902. - Other driver’s license plate: 7KXR214. - Best phone number to reach you: 1320‑322‑2543. Your claim is NGM-904417. Your assigned adjuster is Priya Shah; she’ll contact you within one business day to go over repairs, next steps, and any payments. The tow has been dispatched to SW 5th Ave & Alder St, with an ETA of about 45 minutes, going to our partner shop at 9th and Morrison. Please don’t drive the car, since that rear wheel is rubbing. While you wait, remove any valuables from the car if you can do so safely. Is there anything else you’re worried about right now—like getting to work, picking up kids, or arranging a rental—so I can note it for your adjuster?
CUSTOMERYes. I
AGENTI’ll note any concerns for your adjuster. What is it you’re most worried about right now?
CUSTOMERwould like. To know about the deductible.
CUSTOMERHe hit
AGENTOn your policy NG4471902,
CUSTOMERme. So I should. Not have to pay
CUSTOMERthe. Deductible.
AGENTOn your policy NG4471902, the collision deductible is $500. Because this was a rear‑end accident caused by the other driver, there are two possible paths: 1. Through your own policy (collision coverage). - Your claim moves forward right away with Northgate. - Your $500 deductible applies up front. - If we later recover money from the other driver’s insurer (Pacific Shore), your deductible may be reimbursed in whole or in part, depending on what we recover. 2. Through the other driver’s insurance (Pacific Shore). - If
AGENTthey accept full responsibility, you may not have to pay a deductible at all, because you’d be going through their policy instead of your collision coverage. - This can sometimes take longer while they investigate. Your adjuster, Priya Shah, will talk with you about which route makes the most sense and whether it’s better to push the claim through Pacific Shore to avoid paying your deductible, or to proceed under your policy for speed and then seek reimbursement. For now, all we know for sure is: - Your collision deductible: $500. - Whether you actually end up out‑of‑pocket that $500 depends on how liability is resolved with Pacific Shore. Would you prefer that I note for Priya that you want to avoid paying the deductible if at all possible and are willing to go through the other driver’s insurance if that works?