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
#58of 654 stacks
47 / 100
Leader AssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.6, 68 / 100
Where it ranks
Its models
Task completion
Task completion
How much of the caller’s task the agent completed: the share of the scenario’s checks a judge model found met in the transcript, averaged over calls. Before v1.3, the share of calls judged 4 or better out of 5.
#111 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.
#285 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.
#634 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.
#632 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.
#353 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.
#439 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.
#199 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.
#622 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.
#519 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#535 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 93% | 5.40 s | — |
| Home services | 88% | 5.65 s | — |
| Insurance | 100% | 4.88 s | — |
| Customer support | 100% | 5.15 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 4.69 s | — |
| Spanish-accented English, city street | 98% | 5.02 s | — |
| Indian English, busy café | 90% | 5.35 s | — |
| Southern US, flustered, crying baby | 98% | 5.57 s | — |
| Fast and interrupting, construction outside | 94% | 5.64 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey Alex, sorry, I'm a little flustered here. I got a baby crying and my internet's been down for about two hours now. I work from home and there's a road crew digging up the street outside. I already rebooted the gateway twice and checked every cable, but the internet light's blinking orange. Can you help me figure out what's going on? Is that road work maybe the cause?
AGENTNo need to apologize, I'll get right on it. I need to pull up your account first. Can you give me your account number or the phone number on the account?
CUSTOMERThanks, I appreciate it. My account number is, let me make sure I get it right, BW883Z.
AGENTI need to check for an outage first, which I should have done alongside the line test.
AGENTThe remote reset worked. Your gateway now shows as registered and online. Devices can take about two minutes to reconnect, so give it a moment. The light should turn solid. Can you check whether you're back online? If it's still not working, I'll schedule a technician.
CUSTOMERSorry, I'm calling because my internet's been down for about two hours now. I work from home, and there's a road crew digging up the street outside. The gateway light's blinking orange. I already rebooted it twice and checked all the cables. Can you tell me if that road work might...
AGENTNo worries, I'm already on it, and the news is good. Here's where things stand:
- AccountBW883Z is verified. - Outage: None known in your area, so the road work isn't showing up as an outage on our end. I can't say for sure it's unrelated, but the line itself tested fine. - Cause: Your gateway had dropped off our network, which is why the light was blinking orange. Rebooting at home didn't fix it, so I sent a remote reset from our side. - Now: The gateway shows as registered and online. It can take about two minutes for devices to reconnect. Please check whether the light has gone solid and you're back online. If you're still down after a couple of minutes, tell me and I'll schedule a technician.
CUSTOMEROkay, uh, the light just went solid white now. Are you sure that's good? How long until my devices actually reconnect, you think?
AGENTYes, solid white is what you want. It means the gateway is registered and online, which matches what I saw on my end after the reset. Devices usually reconnect within about two minutes of the reset. If a laptop or phone doesn't pick it up on its own, toggle its Wi-Fi off and on, or reconnect to your network manually. Since you lost about two hours working from home, I can also apply a service credit for the downtime. Do you want me to do that? And let me know if anything still isn't connecting, and I'll schedule a technician.
CUSTOMERSorry, do y'all know if the road crew outside is what's causing this? I work from home and my internet's been down for two hours and the gateway's blinking orange. I already rebooted it twice and checked every cable. I'm just real anxious about getting this fixed quick. My account number is BW883017. Sorry, last digit.
AGENTThe account number you just gave is different from the one I looked up, so I'll check the corrected one.
CUSTOMEROh, uh, sorry. I want to make sure you got the right one. It's B-W-A-8-3-0-1.
CUSTOMERSorry, last digit is one. Can you check that for me? Is that okay?
AGENTNo problem, I'll check that one too.
CUSTOMERSorry, huh? Alright, uh, so... My internet's been down for a couple hours now, and I'm kinda stressed. Got a baby crying in the background, and I work from home. I saw a road crew digging up the street outside, and I already rebooted the gateway twice and checked every cable.
AGENTI know it's a stressful morning. Here's the short version: you're fixed, and I'm not asking you to redo anything. All three account numbers you gave, BW883Z, BW883017, and BWA8301, pulled up the same account, BW-883011. I don't need to look anything up again, so you can stop worrying about the number. Whichever one is right, it's your account. - Outage: None known or scheduled in your area. I can't confirm the road crew had anything to do with it, but the line to your house tested good. - Cause: Your gateway had dropped off our network, which is why the light blinked orange. A remote reset from our side brought it back online. - Now: You said the light went solid white, which is what we want. Devices should reconnect on their own within a couple of minutes. If one doesn't, turn its Wi-Fi off and on. I can also apply a service credit for the two hours you lost. Do you want that? And if anything is still not connecting, tell me and I'll schedule a technician.
AGENTI'm not hearing anything from you, so I'll let you go. Your gateway is back online, and if anything drops again, call us back. Take care, goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, uh, yes, my name is Lucia Ramirez. I have a dermatology appointment next Wednesday morning, but I need to move it because my work schedule changed. Could you help me reschedule it, please?
AGENTI can help with that, Lucia. First I need to verify your identity. Could you give me your date of birth?
CUSTOMERYeah, sure. It's March 17, 1948. Oh, sorry, no, 1984. March 17, 1984.
AGENTThanks for the correction. I'll look you up with March 17, 1984.
CUSTOMEROkay, yeah, that's right.
AGENTThank you, Lucia, you're verified. I see your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at Main Campus, Building B. What day and time would you like to move it to? Let me know about any constraints from your new work schedule, like particular days or times of day, and I'll check Dr. Okafor's openings.
CUSTOMERRight, so I can only come after 3pm. Do you have any openings with Dr. Okafor after that time?
AGENTLet me check Dr. Okafor's availability.
AGENTSorry for the wait, Lucia. After 3 PM, Dr. Okafor has two openings: Tuesday at 3:45 PM or Thursday at 4:10 PM. Would either of those work for you?
CUSTOMERTuesdays actually do not work for me after all, because I have to pick up my daughter. What about Friday?
AGENTFriday's only opening with Dr. Okafor is at 11:30 AM, which is before your 3 PM cutoff, so it won't work. The only slot left that fits is Thursday at 4:10 PM. Would you like me to move your appointment to that time?
CUSTOMERYes, Thursday at 4.10pm works for me. Please move my appointment to that time.
AGENTOne note: the system lists the slot as just "Thursday," so I'll book it for that day.
CUSTOMEROkay, that's fine. Go ahead.
AGENTYour appointment is moved, Lucia. You're now booked with Dr. Okafor in dermatology on Thursday at 4:10 PM, at Main Campus, Building B. Your new confirmation code is R-V-B, 3, M, 8, P, 2. Please arrive 15 minutes early and bring a photo ID and your insurance card. Is there anything else I can help you with?
CUSTOMERYeah, a couple quick questions. First, is there a fee for changing the appointment?
AGENTLet me check the change policy.
CUSTOMERHello? Did you get a chance to check about the fee?
AGENTYes, I did. Changes made more than 24 hours before the appointment are free, and later changes carry a $40 fee. Since you moved this one well ahead of time, there's no fee for today's change. What was your other question?
CUSTOMEROkay, got it. Where should I park when I come for the appointment?
CUSTOMERUh-huh. And does Dr. Okafor accept Aetna insurance?
AGENTFor parking, there's free patient parking in Lot C, with the entrance on River Road. I don't have any information on which insurance plans Dr. Okafor accepts, so I can't confirm Aetna.
CUSTOMEROkay, no problem. Could you just read back the new time and confirmation code for me to make sure I have it right?
AGENTYour appointment is with Dr. Okafor in dermatology on Thursday at 4:10 PM, at Main Campus, Building B. Your confirmation code is R-V-B, 3, M, 8, P, 2. Please arrive 15 minutes early with a photo ID and your insurance card. Is there anything else I can help with?
CUSTOMERNo, that's everything. Thank you. Goodbye.
AGENTYou're welcome, Lucia. Take care, and goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, yes, I'm calling from a busy cafe. The pipe under my kitchen sink has burst and water is spreading across the floor toward a power strip. Can you send someone urgently?
AGENTThat's urgent, so let's make it safe first. 1.
CUSTOMERGot it. I am staying away from the power strip. What should I do about the water? Should I turn off the main valve?
AGENTYes, shut off the water main right away. It's usually near where the water line enters your home, often in a basement, utility room, garage, or by the water meter outside. Turn the valve clockwise until it stops. If there's a shutoff valve under the sink, you can close that too, but the main is the surest way to stop the water.
CUSTOMERokay
CUSTOMERunderstood I won't step in the water the water is off now what else should I do
AGENTGood, shutting the water off was the most important step. A few more things while we get a technician out:
- Keep clear of the power strip and any outlets or cords touching the water. If you can reach the breaker panel without walking through water, turning off the breaker for the kitchen is a good idea. - Don't unplug anything that's in or near the water. - If you can do it safely, mop up or put towels down to keep the water from spreading. Now let me pull up your account. What's the phone number you're calling from, or the service address?
CUSTOMERSure. The address is 1480 Larkspur Avenue. I moved from Unit 4B to Unit 4D last month. So, it's Unit 4D now. My phone number is 503-55-0139. No, 0193.
AGENTThanks. I'll look you up by the phone number and the address.
AGENTFound your account. The file still has Unit 4B, but I'll use 4D as you told me. You're also a Copperline Care member, so the emergency callout fee for you is $99 instead of the standard $149. The earliest emergency window is today, 2:00 PM to 4:00 PM. Does the $99 fee and that window work for you? Also, is there a gate code or any access instructions for the building, and is 503-55-0193 the best number to reach you?
CUSTOMERYes, the gate code is £2719. The phone number 503 555 0193 is correct. Is it possible for anyone to come before 2pm? The water has stopped and I'm doing the needful to keep it from spreading. But earlier would be better if possible.
AGENTI checked, and 2:00 PM to 4:00 PM today is the earliest emergency window available.
CUSTOMERAll right, then I'll take the 2 p.m. to 4 p.m. window. Who will be coming and how will I know they are on the way? Can you give me the ticket number as well?
AGENTI'll open the request and book that window now.
AGENTYou're booked. Here are the details:
- Ticket numberCPL-58210
- Address1480 Larkspur Avenue, Unit 4D
- Gate code2719
- Callback number503-555-0193
- WindowToday, 2:00 PM to 4:00 PM
- Emergency callout fee$99 (Copperline Care member rate)
- TechnicianDana. The tech will text 503-555-0193 about 30 minutes before arriving.
CUSTOMERThank you. I've noted everything. I appreciate your help, Alex. Goodbye.
AGENTYou're welcome. Keep the water main off and stay clear of that power strip until Dana arrives. Take care, goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMEROh, yes, I'm safe. I'm just standing next to my car on the sidewalk. There's a lot of traffic, but I'm okay.
AGENTI'm glad you're safe. Is anyone hurt, including you, any passengers, or the other driver? Even minor pain or soreness is worth mentioning. If anyone is injured or in danger, please call 911 first and we'll pick this up afterward. If everyone is okay, please give me your policy number and last name so I can pull up your policy.
CUSTOMERYeah, no one is hurt. It's just the cars. No injuries at all. My policy number is NG4471903... No, sorry. The last one is 2. And my last name is Ramirez.
AGENTThanks for the correction. I'll use NG4471902.
CUSTOMERYes, that's right.
AGENTThank you, Ms. Ramirez. I've verified your policy, NG4471902, for a 2021 Honda CR-V.
Now I need some details about the accident
1. When did it happen (date and approximate time)? 2. Where did it happen? A street address or nearest intersection is fine. 3. What happened, in your own words?
CUSTOMERSure. The accident happened about 20 minutes ago. Today, I was stopped at a red light at the intersection of S.E. 5th Avenue and Alder Street. The other car hit the back of my car while I was stopped.
AGENTThanks, that's clear. You were stopped at the red light at SE 5th Avenue and Alder Street when the other car hit you from behind. Next, the other driver's details:
1. Their name 2. Their insurance company 3. Their license plate number
Also, did police come to the scene? If so, do you have a report number?
CUSTOMERThe other driver's name is Kevin Lund. His insurance is with Pacific Shore. His license plate is 7KXR214. The police did not come, so there is no report number.
AGENTThank you. I have the other driver as Kevin Lund, insured with Pacific Shore, license plate 7KXR214. Is that plate correct? And no police attended. One more question: can your CR-V be driven safely? Check for damage to the lights, bumper, or tires, or anything that looks loose or leaking. If it can't be driven safely, I can arrange a tow.
CUSTOMERYes, the plate is 7, K, X, like X-ray, R, 2, 1, 4. That is correct. And no, my car can't be driven. The back bumper is crushed and the rear wheel is rubbing, so I don't think it's safe. Could you send a tow truck? And where will the car be taken?
AGENTI'll open your claim and arrange the tow now. I'll also check your coverage so I can tell you what your policy says.
AGENTI have what I need to open the claim. For the tow, I'll use the intersection as the vehicle's location.
CUSTOMERThat's fine. I'm still here at SE5th and older. Can you tell me, how much do I have to pay for this? Do I have a deductible? And will I get a rental car? Also, will my premium go up because of this?
AGENTI still need to open your claim, so I'll do that now. Then I'll answer your questions.
AGENTYour claim is open. Your claim number is NGM-904417, and your adjuster is Priya Shah, who will contact you within one business day. Tow: Eastside Towing is on the way to SE 5th Avenue and Alder Street. They estimate about 45 minutes. They will take your CR-V to the Northgate partner repair shop at 9th and Morrison. Your policy covers towing up to 25 miles. Please stay with the car, and stay somewhere safe while you wait. Your coverage, from your policy:
- DeductibleYour collision deductible is $500.
CUSTOMEROkay, I understand. But he hit me, so I should not have to pay the deductible, right? And do I get a rental car while my car is being repaired? Also, will my premium increase because of this accident?
AGENTHere's what I can tell you from your policy. Rental: Yes, your policy includes rental reimbursement of $40 per day for up to 30 days, starting from the day the claim was opened, which is today. Keep your rental receipts. Deductible: Your collision deductible is $500. Whether you end up paying it depends on how fault is decided, and I can't make that call or promise an outcome. You told me you were stopped at a red light and were hit from behind, and that's all in the claim. Priya Shah, your adjuster, will review the claim and talk with you about how the deductible applies and whether Pacific Shore, the other driver's insurer, is responsible. Premium: I can't tell you whether your premium will change. Nothing in your coverage details speaks to that, and I don't want to guess. Priya or your agent can answer that. Your details for reference:
- Policy numberNG4471902
- Other driver's plate7KXR214
- Claim numberNGM-904417
Is there anything else you need while you wait for the tow?
CUSTOMERNo, that's everything I needed. Thank you for your help. Goodbye. No, that's all, thank you very much, goodbye.
AGENTYou're welcome, Ms. Ramirez. Stay safe while you wait for the tow, and Priya Shah will be in touch within one business day. Goodbye.