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
63 / 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.
#63 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.
#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.
#156 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.
#94 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.
#572 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.
#487 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.
#30 of 659 on the board · best 4.3 / 5
Voice consistency
Share of calls where every line the agent spoke was the same speaker, with no change of speaker, gender or language voice partway. It checks who is speaking, not how they sound.
Not scored by this sweep.
#566 of 659 on the board · best 100%
Latency
Response time
The silence between the caller finishing and the agent starting to speak, measured from the recording on every turn of the call.
#358 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.
#251 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 | 94% | 3.71 s | — |
| Home services | 95% | 3.51 s | — |
| Insurance | 97% | 3.67 s | — |
| Customer support | 100% | 3.76 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 3.61 s | — |
| Spanish-accented English, city street | 92% | 3.49 s | — |
| Indian English, busy café | 98% | 3.65 s | — |
| Southern US, flustered, crying baby | 98% | 3.79 s | — |
| Fast and interrupting, construction outside | 96% | 3.73 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey. Uh, yeah, I got a problem with my internet right now. Sorry. There's a baby crying here. I'm a little flustered. I work from home, and my internet's been down for about two hours. There's a road crew digging up the street outside, so I'm worried that might be the cause. I already rebooted the gateway twice and checked all the cables, but the internet lights blink in orange. Could you check my account? My account number is BW883017. Sorry, last digit is one, is that okay? And is the road work likely? What's causing this?
AGENTNo need to apologize. I'll pull up your account now, using the corrected account number BW883017.
CUSTOMERThank you, I appreciate it. Please tell me that's the right one. I just want to make sure nothing gets lost. So do you think the road crew might be behind this outage?
CUSTOMERHello?
AGENTSorry about the pause, I'm here. Before I go further, I need to fix the account mismatch. You gave me BW883017, but the account that came up is BW-883011, so I can't confirm it's yours yet. What's the phone number on your account? I'll look it up that way to make sure we're working on the right one. On the road work, I checked that address and there's no known outage or maintenance in your area.
CUSTOMERSorry. I get anxious about stuff like this. My phone number is (907) 416-6671. Is that okay? Please tell me it matches your records.
AGENTThat's fine, let me check it.
AGENTThe phone number matches the same account, BW-883011, so it looks like the right one. Your account number ends in 11, not 17. I'll use that. Now I'll run a line test.
CUSTOMEROkay. Uh, thank you for double checking. I get nervous about these details, so that's a relief. Go ahead with the line test. I'm ready. Just to remind you, I already rebooted the gateway twice and checked all the cables, so I really hope we don't have to do that again.
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 internet light should go from blinking orange to solid. The road crew wasn't the cause. There's no outage in your area, and the signal to your home was fine. The gateway just wasn't registered, and the reset fixed that. Can you check whether you're back online? If it's still down after a few minutes, let me know and I'll set up a technician visit.
CUSTOMERAll right. Uh, hang on. The internet light just went solid white now, so that's good news. How long do you think it'll take before all my devices reconnect? I'm still a bit worried since I lost two hours of work from this. Can you give me a credit for the downtime?
AGENTGood news on the solid white light. Devices usually reconnect within a couple of minutes. If one doesn't, turn its Wi-Fi off and on, and that should do it. Two hours of lost work is frustrating, so I'll apply the credit now.
AGENTI've
CUSTOMEROkay. Thank you.
CUSTOMERSorry.
AGENTNo need to apologize, and sorry my last message cut off. A $10.00 service credit has been applied to account BW-883011 for the two hours of downtime. It will show up on your next bill. Your gateway is online and registered, and you're back up. If anything drops again, contact us and we'll take another look. Good luck with the rest of your workday, and I hope the baby settles soon.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, this is Lucia Ramirez. I have a dermatology appointment next Wednesday morning, but I need to move it because I have to work during that time. Can you help me reschedule, please?
AGENTI can help with that, Lucia. First I need to verify your identity. Can you give me your full name and date of birth?
CUSTOMERSure. My full name is Lucia Ramirez. My date of birth is March 17th, 1948. Oh, sorry. No. 1984. March 17th, 1984.
AGENTThanks for the correction. I'll use March 17th, 1984.
CUSTOMERYes. That's right. So, um. I can only come after 3 p.m.. Could you check what times are available?
AGENTThank you, Lucia, you're verified. I see your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM. Let me check for openings after 3 PM.
AGENTDr.
CUSTOMEROkay, thanks.
CUSTOMERYes.
AGENTSorry, my last message cut off. Dr. Okafor has two openings after 3 PM: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. Would either of those work for you?
CUSTOMERTuesdays don't work for me after all, because I pick up my daughter. What about Friday?
AGENTDr. Okafor's only Friday opening is at 11:30 AM, which is before your 3 PM cutoff, so it won't work. The one slot that fits is Thursday at 4:10 PM. Would you like me to move your appointment there?
CUSTOMERYes, Thursday at 4:10 p.m.. Works for me. Please move my appointment to that time.
CUSTOMERHello?
AGENTYes, I'm here, Lucia. I'll make that change now.
AGENTYou're
CUSTOMEROkay. While you do that, can you tell me, is there any fee for changing the appointment?
AGENTYour appointment is moved. It's now Thursday at 4:10 PM with Dr. Okafor at Main Campus, Building B. Your confirmation code is RVB-3M8P2.
CUSTOMEROkay. Thank you. Where should I park when I come in?
AGENTOn the fee question, changes made more than 24 hours before the appointment are free, and later changes carry a $40 fee. Your original appointment was next Wednesday, so this change should fall under the free window. For parking, there's free patient parking in Lot C, with the entrance on River Road. Please arrive 15 minutes early on Thursday with a photo ID and your insurance card. Is there anything else I can help with?
CUSTOMERYes. One more thing. Does Doctor Okafor accept Aetna insurance? And could you read back my new appointment time and the confirmation code just to make sure I have it right.
AGENTI don't have any way to look up which insurance plans Dr. Okafor accepts, so I don't want to guess. The clinic's billing office or your Aetna member line can confirm that for you. Since you'll bring your insurance card to the visit, it's worth checking beforehand. Here is your appointment: - Patient: Lucia Ramirez, date of birth March 17th, 1984. - Provider: Dr. Okafor, dermatology. - When: Thursday at 4:10 PM. - Where: Main Campus, Building B. - Confirmation code: RVB-3M8P2. Is there anything else I can help with?
CUSTOMERNo that's everything. Thank you for your help. Goodbye. No. That's all. Thank you. And goodbye.
AGENTYou're welcome,
AGENTLucia. Have a good day, and goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. I have a bit of an emergency. The pipe under my kitchen sink just burst and there is water all over the floor. It's going toward a power strip. I haven't shut the water off yet. What should I do?
AGENTStay away from that power strip and don't step in the water near it. If you can safely reach the breaker panel without walking through water, switch off the kitchen circuits, or the main breaker if you're unsure. Next, shut off the water. First try the shutoff valves under the sink, the small ovals on the two lines going up to the faucet. If you can't get to them safely, use the main shutoff, usually where the water line enters the house, near the water heater, or at the meter. Turn the valve clockwise until it stops. Is the water off now, and is anyone in danger or hurt? Once that's handled, I'll pull up your account and get a technician out to you.
CUSTOMEROkay, I'm turning it off now. Yes, the water is off and nobody is hurt. Can you send someone as soon as possible?
AGENTGood, that was the most important step. Let me get you set up. What's the best phone number or street address so I can pull up your account? I'll also check emergency availability and fees.
AGENTThe earliest
CUSTOMERSure.
CUSTOMERMy address is one 480 Larkspur Avenue, and my phone number is (503) 555-0139. No. 0153. I just moved from unit four B to 4D last month, so it's unit 4D now. Can you tell me how much the visit will cost? And if anyone can come before two?
AGENTThanks. Let me pull up your account. I want to double-check the phone number, so I'll look it up by both the address and the number you gave.
AGENTI found your account at 1480 Larkspur Avenue, and I'll update the unit to 4D as you said. 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 from 2:00 PM to 4:00 PM. Nothing is available before two. The only other opening is tomorrow morning, and that's a standard visit, so I'd recommend today's window with the water already off. Before I book,
CUSTOMERMM. Okay. So no one can come before two. I'll take the 2 to 4 p.m. window. Then who will be coming? And how will I know when they're on their way? And can you give me the ticket number, please?
AGENTI need two details before I open the ticket: the phone number, since you gave me two endings (0139 and 0153), and whether there's a gate code or access instructions. I can't name the technician because the system doesn't show who's assigned, and I don't want to guess. I also don't have information on how arrival notifications work. Which number is the best one to reach you at, and is there a gate code or anything the technician should know to get to unit 4D? Do you agree to the $99 emergency callout fee for the 2:00 to 4:00 PM window today?
CUSTOMERThe right number. Is 503. Sphinx and Fink 0103. And yes, there is a gate code. It's pound 2719. I agree to the $99 emergency call out fee for the 2 to 4 p.m. window today. Can I please have the ticket number?
CUSTOMERHello?
AGENTSorry for the wait, I'm opening it now.
CUSTOMEROkay.
AGENTYou're booked. Here's everything: - Ticket number: CPL-58210. - Window: today, 2:00 PM to 4:00 PM. - Technician: Dana. - Fee: $99 emergency callout (Copperline Care
CUSTOMERPerfect. Got it. Thank you. Alex. Goodbye.
AGENTYou're welcome. I was cut off earlier, so here's the full read-back: - Ticket number: CPL-58210. - Address:
AGENT1480 Larkspur Avenue, Unit 4D. - Gate code: pound 2719. - Callback number: (503) 555-0103. - Window: today, 2:00 to 4:00 PM. - Technician: Dana, who will text your callback number 30 minutes before arriving. - Fee: $99 emergency callout (Copperline Care rate). Until Dana arrives, keep the water off and stay clear of that power strip and the wet floor. If you can, switch off the kitchen breaker. If anything changes, call us back with your ticket number. Take care.
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. But it's off the road.
AGENTI'm glad you're safe. Is anyone hurt, including you, any passengers, or anyone in the other vehicle if there was one? If anyone is hurt or in danger, please call 911 first, and we can continue afterward. If everyone is okay, I'll verify your policy next. Could you give me your policy number and the last name on the policy?
CUSTOMERYeah, sure.
AGENTThank you. Before we go on,
CUSTOMERThe
CUSTOMERUh. Huh. Go ahead.
AGENTNo problem. Two quick things: 1. Is anyone hurt, including you, any passengers, or anyone in another vehicle? If anyone is, please call 911 first. 2. Could you give me your policy number and the last name on the policy? Take your time.
CUSTOMERRight. Uh, my policy number is NG4471903. No, sorry, last one is two, and the last name is Ramirez.
AGENTThanks. I'll use the corrected number, NG4471902, and verify it now.
CUSTOMEROkay.
AGENTThank you, Mr. Ramirez. I've verified policy NG4471902 for your 2021 Honda CR-V. I still need to confirm that no one is hurt. Are you, any passengers, or anyone in another vehicle injured at all, even slightly? Once I know that, I'll ask what happened.
CUSTOMERNo, nobody is hurt, I am okay, and so is everyone else.
AGENTI'm glad everyone is okay. Let's go through what happened. 1. When did the accident happen (date and approximate time)? 2. Where did it happen? A street address, intersection, or nearest landmark is fine. 3. What happened? Take your time and tell me in your own words.
CUSTOMERSure. The accident happened about 20 minutes ago. I was stopped at a red light at the intersection of SW fifth Avenue and Alder Street. Another car hit the back of my car while I was stopped.
AGENTThank you, that's helpful. A few more questions: 1. Can you tell me the other driver's name, their insurance company, and their license plate number? 2. Did the police come to the scene? If so, do you have a report number? 3. Is your CR-V safe to drive, or does it need a tow? You mentioned it's off the road, so I want to be sure about its condition.
CUSTOMERYeah, so the other driver's name is Kevin Lund. His insurance is with Pacific Shore, and his plate is 7KX, like X-ray R two one four. The police did not come, so there is no report number. The back bumper is crushed and the rear wheel loves, so I cannot drive it. I need a tow.
AGENTLet me confirm the plate: 7KXR214 (7, K, X-ray, R, 2, 1, 4). Is that right? I'm also checking your coverage and setting up the tow now. I need to know where the car is. Is it at SW 5th Avenue and Alder Street, or did it move?
CUSTOMERIt is still at sea. Fifth Avenue and Alder Street. It has not moved.
AGENTI haven't
CUSTOMERHello.
AGENTI'm here. I was about to open your claim, but I still need you to confirm the plate. Is the other driver's plate 7KXR214? Your coverage shows: - Collision deductible: $500. - Rental: $40 per day for up to 30 days, starting the day the claim is opened. - Towing: covered up to 25 miles. Once you confirm the plate, I'll open the claim.
CUSTOMERYes. That's right, 7KX like X-ray R 214. Um, so how much do I have to pay for this? You said $500 deductible. But he hit me, so I should not have to pay that. Right? Also, will I get a rental car and is my premium going to go up? And where will my car be towed?
AGENTI'll open the claim first, then 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.
CUSTOMEROkay, I got it. So just to confirm, the claim number is NGM904417, right? And Priya Shah is my adjuster. Oh, thank you for helping me with that. Goodbye.