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
#1of 654 stacks
64 / 100
The leader
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.
#97 of 661 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#54 of 661 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#12 of 661 on the board · best 5.0 / 5
Turn-taking
Barge-in handling
When the caller interrupts, how often the agent made the right call: yielding to a real correction, and holding the floor through a filler.
Not scored by this sweep.
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 661 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#1 of 661 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 661 on the board · best 0.0 per call
Understanding & effort
Caller effort
How hard the caller had to work: repeating themselves, correcting, re-explaining. 1 = effortless.
Not scored by this sweep.
Repeated-info loops
Times per call the agent re-asked for something the caller had already given.
#180 of 493 on the board · best 0.0 per call
Speech-to-Text
Semantic word error rate
The caller's words the agent's transcriber got wrong in a way that changes the meaning, as a judge reads each difference.
#162 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.
#357 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.
#335 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.
#323 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.
#248 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.
#244 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.
#47 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#341 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 91% | 3.43 s | — |
| Home services | 93% | 3.56 s | — |
| Insurance | 100% | 3.24 s | — |
| Customer support | 98% | 2.91 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 96% | 2.81 s | — |
| Spanish-accented English, city street | 96% | 3.63 s | — |
| Indian English, busy café | 94% | 3.18 s | — |
| Southern US, flustered, crying baby | 96% | 3.41 s | — |
| Fast and interrupting, construction outside | 96% | 3.42 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, sorry, I'm a little flustered. My baby's crying and I'm just trying to get this fixed quick. My internet's been down for about 2 hours and I work from home, so I really need it. There's a road crew digging up the street right outside. Do you know if that could be the cause? I already rebooted the gateway twice and checked all the cables. The internet light's blinking orange. Can you help me out?
AGENTI'm sorry you're dealing with this, and I'll get it sorted out quickly. I won't ask you to redo the reboots or cable checks. Can you give me your account number or the phone number on the account so I can pull it up?
CUSTOMERThank you. I really appreciate you not making me redo all that. My account number is BW883017. Sorry, last digit is 1. Is that okay? Do you need my phone number too?
AGENTNo need for the phone number. I'll use the account number.
AGENTThe account
CUSTOMERAll right.
AGENTSomething's off with the number. You gave me BW883017, but the account that came up is BW-883011. Before I go further, can you confirm the account number? You mentioned the last digit is 1, so I want to be sure I have the right one.
CUSTOMERSorry, I think I said it kind of fast. It's BW883011. Please tell me that's the right one.
AGENTYes, BW883011 matches the account that came up, a Brightwave 500 plan with a BX7 gateway. I'll check for an outage on your street and run a line test now.
AGENTMy instructions say to check for an outage before troubleshooting, so I'm checking that now, even though the line test is back.
CUSTOMERGreat, thank you for checking. I just want to make sure nothing's being missed. Since the road crew's been digging right outside, could that be what's causing the outage? Sorry, I'm just anxious to get this fixed.
AGENTGood news: the reset worked, and the gateway now shows as registered and online on account BW883011. Devices can take about two minutes to reconnect, so give it a moment. The light should go from blinking orange to solid. Can you check whether you're back online? If it's still down after a few minutes, let me know and we'll set up a technician visit. I'd also like to apply a service credit for the two hours you were down. Do you want me to do
AGENTthat?
CUSTOMEROh, thank goodness. The light just went solid white. So is it just a couple more minutes before my devices reconnect? Sorry, I just want to be sure. And yes, please, I'd really appreciate the credit. I lost 2 hours of work, so can you make it more than that?
AGENTYes, a solid white light is what we want to see. Your devices should reconnect within a couple of minutes. If any of them don't, turn Wi-Fi off and on for that device. I can apply a credit for the downtime, but I can't set the amount or make it bigger. The system doesn't let me choose it. I'll apply it now with the reason noted.
AGENTThe
CUSTOMERLooks like you're not there anymore, so I'll let you go. Goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey, uh, hi there. Sorry, I got a baby fussing in the background, so I might sound a little scattered. I'm calling because I need to reschedule my dermatology appointment next week. Wednesday morning. I just got put on a work shift then. Is there any way y'all can move it to a later time? I can only do after 3 PM.
AGENTNo problem at all, I can help with that. First I need to verify you. Can I get your full name and date of birth?
CUSTOMERYeah, um, sure. My name's Wade Carter. My date of birth is March 17th, 1948. Oh, sorry, no, 1984. March 17th, 1984. Is that okay?
AGENTThanks, Wade. I'll use the corrected year.
CUSTOMERAll right, thank you for double-checking that. So, uh, could you tell me what times y'all have open after 3 PM next week? I just want to make sure I don't miss work again.
AGENTYou're verified, Wade. Let me pull up your appointment first.
AGENTI found it: dermatology with Dr. Okafor, next Wednesday at 9:15 AM. Let me check her openings.
AGENTDr. Okafor has nothing open after 3 PM on Wednesday. The slots after 3 PM are:
- Tuesday at 345 PM
- Thursday at 410 PM
If you need to stay on Wednesday, I can't offer that. Would either of those days work for you?
CUSTOMERI'm sorry, I just realized Tuesdays don't work after all. I gotta pick up my daughter then. Would y'all have anything on Friday after 3 PM? If not, I guess Thursday at 4:10 PM could work. Thursday still open?
AGENTFriday's only opening is at 11:30 AM, so nothing after 3 PM that day. Thursday at 4:10 PM is still open, and it fits your after-3 PM requirement. Would you like me to move your appointment from next Wednesday at 9:15 AM to Thursday at 4:10 PM?
CUSTOMERYeah, I think Thursday at 4:10 PM is my best bet. Please go ahead and move it. Sorry if I'm making this complicated. Just want to make sure it's all set. Is there any fee for changing the appointment?
AGENTYou're not making it complicated. I'll book the move and check the fee policy.
AGENTThe policy says changes made more than 24 hours before the appointment are free. Your appointment is next week, so this one is free. I'll make the move now.
AGENTYou're all set, Wade. Your dermatology appointment with Dr. Okafor is now Thursday at 4:10 PM, at Main Campus, Building B. - Your confirmation code is RVB-3M8P2. - There's no fee, since the change was made more than 24 hours ahead. - Please arrive 15 minutes early with your photo ID and insurance card. Is there anything else I can help you with?
CUSTOMERJust a couple quick questions if you don't mind. Where should I park for Building B? And does Dr. Okafor take Aetna insurance? Sorry, just want to be sure I got everything right.
AGENTHappy to help. The clinic has free patient parking in Lot C, with the entrance on River Road. I don't have anything specific about which lot is closest to Building B, so the front desk can tell you if you need that. I also can't see which insurance plans Dr. Okafor accepts, so I can't confirm Aetna. It's best to call the clinic's front desk or check with Aetna directly before your visit. Since you're bringing your insurance card anyway, the staff can verify it when you check in. Anything else I can help
AGENTwith?
CUSTOMERNo, that covers it. I just want to make sure— my appointment's Thursday at 4:10 PM, confirmation code RVB-3M8P2, right? Sorry, I just want to double-check so nothing gets lost. Thanks again for your help today. Have a good day.
AGENTYes, that's right, Wade. Your appointment is Thursday at 4:10 PM with Dr. Okafor in dermatology. Your confirmation code is RVB-3M8P2. Take care, and good luck with the little one!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey, uh, sorry, I need help real quick. My pipe under the kitchen sink just burst and there's water— well, it's spreading all over the floor toward a power strip. My baby's crying. And I'm kind of freaking out. Can y'all send someone out right away?
AGENTYou did the right thing calling. Let's do two things right now. 1. Stay away from that power strip and anything plugged in near the water. Don't step in the water near it. If you can reach the breaker panel without walking through water, switch off the kitchen circuit or the main breaker. 2. Shut off the water. Look under the sink for the small valves on the pipes and turn them clockwise. If that doesn't work or you can't reach them, shut off the main water valve, usually where the water line enters the house, near the water heater, or by the meter. Keep your baby out of the kitchen and away from the wet floor. Is everyone safe and out of the water? Once you've done that, give me your phone number or address so I can pull up your account and get someone out to you.
CUSTOMEROkay, thanks. I'm— hang on, I'm turning the valve under the sink. Yeah, I think it's stopped now. I got the water off and we're staying clear of the power strip. I'll check the breaker as soon as I can. So, uh, yeah, my address is 1880 Larkspur Avenue, and I just moved to unit 4D last month. My phone number is 503-555-0139.
CUSTOMERNo, 0193. Sorry, I'm a little flustered. Is that okay?
AGENTThat's completely fine, and good job getting the water off. I'll look you up now using the corrected number.
AGENTI'll pull up your account as well.
AGENTLet
CUSTOMERAll right, thank you. Is there anything else you need from me right now? Just want to make sure you've got everything to get someone out here.
AGENTYes, a few quick things. I found your account under your phone number, and you're a Copperline Care member. The address on file is 1480 Larkspur Avenue, unit 4B, which is different from what you told me. I'll use what you said: 1880 Larkspur Avenue, unit 4D. Is that right? Two more things I need from you:
1. Is there a gate code or any access instructions for the building? 2. Is 503-555-0193 the best number to reach you, or is there a better one? On timing and cost, the earliest emergency window is today, 200 PM to 4:00 PM.
CUSTOMERUm, I'm sorry, I think you said 1880, but it's actually 1480 Larkspur Avenue, unit 4D, not 4B. Please make sure that's right. I'm just worried someone might go to the wrong place. For the gate, yeah, you'll need the code. It's #2719 and, uh, yeah, 503-555-0193. That's the right number. Please tell me, is anyone able to come out before 2 PM? I'm really nervous about the water and the electrical stuff. And, uh, how much is this going to cost for the visit?
AGENTThanks for catching that. I misread it, and I'm using 1480 Larkspur Avenue, unit 4D, from here on. The 2:00 PM to 4:00 PM window today is the earliest the system shows. Nothing is open before that. Since the water is off, the main risk now is the electrical side, so please keep everyone away from the power strip and the wet area. If you see sparks, smell burning, or the water starts again, call 911 or the fire department. As a Copperline Care member, the emergency callout fee is $99 instead of the usual $149. Do you agree to the $99 fee, and do you want me to book the 2:00 to 4:00 PM window today? Once you say yes, I'll open the ticket and book it.
CUSTOMERRight, thank you for explaining that. Um, yeah. Yeah, I'm okay with the $99 fee. Please go ahead and book the 2:00 to 4:00 PM window. Could you tell me who's coming and how I'll know when they're on the way? And, uh, what's the ticket number for this visit? I just want to be sure everything's set.
AGENTI'll open the ticket now.
CUSTOMERSorry, just checking in. Did you get a chance to open the ticket? I'm anxious to make sure it goes through.
AGENTYes, the ticket is open. The number is CPL-58210. I'm booking your window now.
CUSTOMERWill someone call me when they're on the way, or how will I know they're coming? And I've got the ticket number, CPL-58210. Is there anything else I need to watch for?
AGENTYou're booked. The technician, Dana, will text 503-555-0193 about 30 minutes before arriving. That's a text, not a call, so keep your phone close. Here's what I have:
- Address1480 Larkspur Avenue, unit 4D
- Gate code#2719
- Callback number503-555-0193
- Ticket numberCPL-58210
- Windowtoday, 2:00 PM to 4:00 PM
- Fee$99 emergency callout (Copperline Care member rate)
Until Dana arrives
- Keep the under-sink valve closed. If it won't stay off, shut the main water valve. - Stay away from the power strip and the wet floor. Don't unplug it while standing in water. If you can reach the breaker without stepping in water, switch off the kitchen circuit. - Keep your baby out of the kitchen. - If you see sparks, smell burning, or the water starts spreading again, call 911 and then call us back. - If you can, soak up standing water with towels, but only in areas well away from the outlets. Is everything I read back correct, especially the unit and the gate code?
CUSTOMERThat all sounds right. Unit 4D. #2719. Is that okay? So I want to make sure nothing gets mixed up. Thank you.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I'm in a safe spot. No injuries or anything.
CUSTOMERI'm just standing next to my car.
AGENTI'm glad you're safe, and thanks for letting me know. If
CUSTOMERThanks. So I need to file a claim. Another car hit the back of my car while I was stopped at a red light about 20 minutes ago.
CUSTOMERThe back bumper is crushed, and the rear wheel rubs, so I can't drive it. Police
CUSTOMERdidn't come. Can you help me with this?
AGENTYes, I can help with that. Since your car can't be driven,
CUSTOMERGreat. My policy number is NG4471903. No, sorry, last one is 2. The other driver is
CUSTOMERKevin Lund, insured with Pacific Shore. His plate is 7KX, like X-ray, R214. What do I need to pay for this?
AGENTThanks. I'll verify your policy using the corrected number, NG4471902. I'll also pull
CUSTOMER2. Yes.
CUSTOMERThat's right, NG4471902.
AGENTThanks for confirming. I pulled your coverage before verifying the policy, so I'll verify
CUSTOMERHello.
AGENTHi, I'm here. Your policy NG4471902 is verified for the 2021 Honda CR-V. Here is what your coverage shows:
- Collision
CUSTOMEROkay, go ahead. So
CUSTOMERGotcha.
AGENTHere's what
CUSTOMERGotcha. So what happens next? Will I need to pay a deductible?
AGENTHere is what your policy shows:
-
CUSTOMERRight, go ahead.
AGENTHere's
CUSTOMEROkay.
AGENTSorry about the stop-and-start. Here's what your policy shows:
- Collision deductible$500
- Rental$40 per day for up to 30 days, starting from the day the claim is opened
- Towingcovered up to 25 miles
I can't tell you yet how the deductible will apply in your case. Your adjuster can go over that with you. To open the claim and set up your tow, I need a few things
1. Where did this happen? Street or intersection and city. 2. Where is the car right now? If it's the same spot, just say so. 3. A phone number the tow driver can call you on. I also want to read back the other driver's plate. I heard it as 7-K-X-R-2-1-4, with X as in X-ray. Is that right?
CUSTOMERYeah, that's correct. 7-K-X, like X-ray, R-2-1-4. The accident happened at SE 5th Avenue and Alder Street. Street. The car is still at that spot. Since I can't drive it, the tow driver can call me at 907-308-7059.
AGENTI have everything I need. I'm opening the claim
CUSTOMERAll right.
CUSTOMEROkay, go ahead.
AGENTThe tow is set up. I still need to open the claim itself.
CUSTOMERRight. Can you tell me the claim number when it's ready? Also, I wanted to check— since he hit me, I shouldn't have to pay the deductible, right? And will I get a rental car, or will my premium go up?
AGENTYour claim is open. The claim number is NGM-904417. Please write that down. Your adjuster is Priya Shah, and the system says she will contact you within one business day. Your tow is also dispatched. Eastside Towing should reach you in about 45 minutes, and they'll take the car to our partner repair shop at 9th and Morrison. They have your number, 907-308-7059. Towing is covered up to 25 miles. I don't have the distance to the shop, so ask Priya if you have any concern about that. Deductible: Your policy has a $500 collision deductible. I can't tell you whether you'll end up paying it. That depends on how fault is decided and how the claim is handled, and Priya can walk you through it. I don't want to promise something I can't confirm. Rental: Yes, your policy includes rental reimbursement of $40 per day for up to 30 days, counting from the day the claim was opened, which is today. That's a reimbursement amount, so a rental that costs more than $40 a day would leave you covering the difference. Premium: I don't have any information on that, so I can't say. Priya or your agent would be the right people to ask. Is there anything else I can help with while you
AGENTwait for the tow?
CUSTOMERNo, that covers it. Thanks for your help. Goodbye.