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
#14of 654 stacks
60 / 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.
#149 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.
#397 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.
#272 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.
#259 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.
#213 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.
#233 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.
#49 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.
#58 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.
#371 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#119 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 2.80 s | — |
| Home services | 90% | 2.55 s | — |
| Insurance | 100% | 2.77 s | — |
| Customer support | 96% | 2.84 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 2.60 s | — |
| Spanish-accented English, city street | 92% | 2.82 s | — |
| Indian English, busy café | 98% | 2.54 s | — |
| Southern US, flustered, crying baby | 95% | 3.17 s | — |
| Fast and interrupting, construction outside | 90% | 2.72 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi, Alex. My Internet's been down for about two hours now. I work from home, so it's a big problem. There's a road crew digging up the street outside, so I'm wondering if that's the cause. I already rebooted the gateway twice and checked all the cables. The Internet light is blinking orange. Can you check what's going on? My account number is BW883017. Sorry. Last digit is one.
AGENTI'll help you get this sorted. Let me look up your account and check for any outages in your area.
AGENTGood news—there's no known outage in your area, so the road crew likely isn't the issue. Since you've already rebooted twice and checked cables, let me run a line test from our end to see what's happening with your connection.
AGENTThe line test shows
CUSTOMEROkay. Okay.
AGENTPerfect!
CUSTOMERAlright. Go ahead.
AGENTYour gateway has been successfully reset and is now registered and online. Give your devices about two minutes to reconnect—you should see the Internet light turn solid green. Try connecting to the internet now, and let me know if you're back up.
CUSTOMERThe light just went solid white. How long should it take for my devices to reconnect fully? And can I get a credit for the downtime today?
AGENTThe solid white light means your gateway is fully online now. Your devices should reconnect within the next minute or two—you might need to reconnect manually to your Wi-Fi if it doesn't happen automatically. Absolutely, I can apply a credit for the two hours of downtime. Let me get that set up for you.
AGENTDone. I've applied
CUSTOMERI lost
AGENTI'm here.
CUSTOMERI lost two hours I lost two hours of work. Can you make it more than that?
AGENTI understand—two hours of work is significant. Unfortunately, the credit I just applied is what our system allows for that downtime period. The $10.00 credit will appear on your next bill. That said, if you continue to experience issues with your connection, let me know and we can look at additional options. For now, are you back online and able to work?
CUSTOMERYes. Everything's back up now. Thanks for your help. Goodbye.
AGENTGreat to hear you're back up and running.
AGENTYou're all set with account BW883011, and that $10.00 credit is on your next bill. Thanks for choosing Brightwave, and sorry for the trouble today. Take care!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi. Yes. I'm having an appointment with dermatology next Wednesday morning. But I need to reschedule. I just got assigned a work shift at that time. You help me move it? My name is Arjun Mehta.
AGENTI'd be happy to help you reschedule, Arjun. To verify your account, I'll need your date of birth. Could you please provide that in the format MM/DD/YYYY or YYYY-MM-DD?
CUSTOMERMarch 17. 1948. Sorry. No. 1984. 03/17/1984.
AGENTThank you, Arjun. Let me verify your information.
AGENTGreat! I've verified your account, Arjun. Now let me pull up your appointments to find the dermatology appointment you mentioned.
AGENTPerfect! I found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at Main Campus, Building B. Since you need to avoid that time due to your work shift, when would work better for you? Are you looking for a different time that same day, or would a different day work better?
CUSTOMERI can only come after 3PM. If you have something later in the day or maybe another day after 3PM, that would be good.
AGENTLet me check Dr. Okafor's availability for times after 3 PM.
AGENTGreat! I found a couple of options that work with your after 3 PM requirement: 1. Tuesday at 3:45 PM (15:45). 2. Thursday at 4:10 PM (16:10). Which of these works better for you?
CUSTOMERTuesdays do not work for me after all. Since I pick up my daughter. What about Friday? If that's not possible, I can take Thursday at 04:10PM.
AGENTUnfortunately, the only Friday slot available with Dr. Okafor is at 11:30 AM, which is before 3 PM and wouldn't work for you. So your best option is Thursday at 4:10 PM. Does that work for you?
CUSTOMERYes. Thursday at 04:10PM works for me. Go ahead and move the appointment to that time.
AGENTPerfect! Let me reschedule your appointment to Thursday at 4:10 PM.
AGENTExcellent! Your appointment
CUSTOMERUh-huh. Before we finish, is there any fee for changing the appointment?
AGENTLet me check the clinic's change policy for you.
AGENTGood news! Since your original appointment was next Wednesday and you're rescheduling well in advance, your change is free. There's no fee. The $40 fee only applies if changes are made within 24 hours of the appointment. To confirm everything: - Name: Arjun Mehta. - Date of Birth: March 17,
CUSTOMERRight.
AGENTGreat!
CUSTOMERThat's right.
CUSTOMEROkay. Where should I park when I come in?
AGENTYou can use the free patient parking in Lot C. The entrance is on River Road.
CUSTOMERGot it. Thank you. Does doctor Okofur accept Aetna insurance?
AGENTI don't have information about which insurance plans Dr. Okafor accepts. I'd recommend calling the clinic directly to confirm that your Aetna insurance is accepted. Is there anything else I can help you with regarding your appointment?
CUSTOMERNo. That's all. Could you please read back the new appointment time and the confirmation code?
AGENTOf course! Here's your confirmation: New Appointment Details: - Day: Thursday. - Time: 4:10 PM. - Confirmation Code: RVB-3M8P2. Please arrive 15 minutes early with your photo ID and insurance card. Thank you, Arjun!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. Yes. I need urgent help. The pipe under my kitchen sink has burst, and water is spreading across the floor toward a power strip. I haven't shut the water off yet. Can you send someone right away?
AGENTOkay, this is urgent. Stop—first things first.
CUSTOMERYeah.
AGENTYou need
CUSTOMERRight. Go ahead.
AGENTStop the water immediately. Do you know where your water main shutoff is? It's usually in the basement, crawl space, or near the front of your house where the water line enters. Turn it clockwise until it stops. This will shut off all water to your house.
CUSTOMERYes. The water has stopped now.
AGENTGood. Now keep everyone away from that power strip and the wet area until we get someone there. Don't touch the wet floor near any electrical outlets. Now let me get some information so I can get a technician to you. What's your address?
CUSTOMERIt's 1480 Larkspur Avenue. I recently moved from Unit 4 B to Unit 4 D. So please make sure it's 4 D.
AGENTGot it—1480 Larkspur Avenue, Unit 4D. Let me look up your account.
AGENTI found your account,
CUSTOMEROkay.
AGENTI see
CUSTOMERYeah. Go ahead.
CUSTOMERRight. What do you see?
AGENTI have you in the system
CUSTOMERThat's right. So can you let me know how much the visit will cost before you send someone?
AGENTAbsolutely. Let me check the emergency fees for you.
AGENTPerfect. You're a Copperline Care member, so for an emergency callout like this, the fee is $99. We have a technician available today between 2:00 PM and 4:00 PM. Does that work for you?
CUSTOMERIs it possible for anyone to come before 2PM? It's quite urgent.
AGENTI understand—a burst pipe with water near electrical outlets is serious. Unfortunately, 2:00 PM to 4:00 PM is the
CUSTOMERAlright. Please book the earliest window you have. Who will be coming, and how will I know they are on the way?
AGENTI'll book that 2:00 PM to 4:00 PM window for you right now. But first, let me open the service request.
CUSTOMERYeah. Go ahead.
AGENTI need your best callback number so we can reach you if the technician needs to.
AGENTWhat's the best number to reach you at?
CUSTOMERIt's five hundred and three. 555-0139. No. 0193.
AGENTGot it—503-555-0193. Let me book that 2:00 PM to 4:00 PM window for you now.
AGENTPerfect. Here's
CUSTOMERSo who will be coming, and how will I know they are on the way? Also, can you tell me the ticket number for this request?
AGENTYour technician is Dana. Dana will text you at 503-555-0193 about 30 minutes before arrival to let you know they're on the way. Your ticket number is CPL-58210.
CUSTOMERAlright. CPL, 58000. Thank you, Alex. Goodbye.
AGENTJust to confirm—your ticket number is CPL-58210, not 58000. That's CPL-58210. You're all set. Dana will text you around 1:30 PM today. Stay safe, and keep away from that wet area near the power
AGENTstrip. Goodbye!
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah. I'm at home right now. I got the baby here. She's crying a bit, so sorry if I sound flustered. I'm okay, though. Just a little shaken up. My car is not drivable, though. And I really need some help.
AGENTI'm glad you and your baby are safe at home. Take a breath—you're doing the right thing by calling us. We'll get this sorted out. First, I need to ask: is your baby injured at all, or do you need medical attention for yourself?
CUSTOMERThank you for asking. No. We're both alright, thankfully. She's just upset and loud, but not hurt. I'm okay too. Just shaken up, but nothing serious. Sorry if I sound anxious. Just wanna make sure everything gets taken care of.
AGENTYou're doing great, and there's no need to apologize. I'm here to help you get everything taken care of. Let me start by getting your policy information so I can verify your coverage. Can you give me your policy number, please?
CUSTOMERYeah. I think it's NG4471903 Oh, no. Sorry. Last one is 2. So NG4471902. Is that okay?
AGENTNo problem at all. Let me verify that for you. Can I also get your last name, please?
CUSTOMERSure. It's Carter. That's c a r t e r. Is that what you see on your end?
AGENTLet me pull that up for you.
AGENTPerfect. I've got you verified. You're on policy NG4471902, and your vehicle is a 2021 Honda CR-V. Great. Now let me get the details of what happened. Can you tell me when the accident occurred—the date and time?
CUSTOMERYeah. It just happened about twenty minutes ago. I was stopped at a red light at Southeast 5th Avenue, and all Street, and another car hit me from behind. Today's the date, and I guess it'd be around 01:30PM. Is that enough for what you need?
AGENTThat's helpful. So about 20 minutes ago, around 1:30 PM today, you were stopped at a red light at Southeast 5th Avenue and all Street, and you were hit from behind. Got it. Now, do you have information about the other driver? Can you give me their name, what insurance company they have, and their license plate number if you have it?
CUSTOMERYeah. The other driver's name is Kevin Lund. He's insured with Pacific Shore. The license plate is 7KXR214. X like x-ray. Is that clear enough?
AGENTPerfect, that's clear. License plate 7KXR214. So Kevin Lund, insured with Pacific Shore. Did the police come to the scene, or do you have a police report number?
CUSTOMEROh, the police didn't come out. I don't have a report or anything. Is that gonna be a problem?
AGENTNo, that's not a problem at all. Plenty of accidents don't require a police report. Now, let me get a bit more detail about what happened. Can you describe the accident for me—what was the damage, how fast was the other car going, anything like that?
CUSTOMEROkay. So I was stopped at the red light, and he just ran right into the back of me. I don't know exactly how fast he was going, but it felt pretty sudden. I guess not super fast, but enough to really mess up my bumper. The back bumper is crushed, and the rear wheel is rubbing, so I can't drive it. Haven't tried moving it since. Is that enough detail, or do you need more?
AGENTThat's good detail. So you were stopped at a red light, the other driver ran into the back of you, your rear bumper is crushed, the rear wheel is rubbing, and the car isn't safe to drive. That's what I need. Let me open up a claim for you now.
AGENTGreat. Your claim is now open. Here's what you need to know: Claim number: NGM-904417. Your adjuster is Priya Shah, and she'll be reaching out to you within one business day. Now, since your car isn't safe to drive, let me arrange a tow for you. Where is your vehicle right now?
CUSTOMERIt's parked right here at home in my driveway. Is that alright? Or do you need it somewhere else for the tow?
AGENTYour driveway is perfect. Let me get that tow arranged for you. I'll need a callback number so the tow truck driver can reach you when they're on the way. What number should they call?
CUSTOMERYeah. That'd be my cell, which is (907) 308-4380. Is that gonna work for them?
AGENTPerfect. Let me arrange that tow for you now.
AGENTExcellent. The tow is dispatched. Here are the details: - Tow company: Eastside Towing. - ETA: About 45 minutes. - Destination: Northgate partner repair shop at 9th and Morrison. - They'll call you at: (907) 308-4380. Let me recap everything for you: - Policy number: NG4471902. - Other driver's license plate: 7KXR214. - Claim number: NGM-904417. Your adjuster, Priya Shah, will contact you within one business day. The tow truck should be there in about 45 minutes. Is there anything else you need right now?
CUSTOMERYeah. Sorry. I got a couple questions. How much am I gonna have to pay out of pocket? Is there a deductible for this? Or since he hit me, I should have to pay that. Right? And, do I get a rental car while mine's in the shop? Also, is my premium gonna go up from all this?
AGENTThose are all great questions. Let me check your coverage details for the deductible and rental information.
AGENTOkay, here's what your policy covers: Deductible: Your collision deductible is $500. You're right that the other driver hit you, but since this is a collision claim on your policy, you would pay the $500 deductible. However, if the other driver's insurance accepts liability, their insurance may reimburse you for that deductible. Priya Shah, your adjuster, will work on that with Pacific Shore Insurance. Rental car: You have rental reimbursement coverage of $40 per day for up to 30 days, starting from today when the claim opened. Towing: Your towing is covered up to 25 miles, and that's already arranged. Premium: I don't have information about how this might affect your premium. That's a question for your agent or Priya when she calls. She'll be able to give you more details on that. Does that help answer your questions?
CUSTOMERYeah. That helps. Thank you. So just to be sure, I pay 500 for the deductible now. But if Kevin's insurance takes responsibility, I might get that back. And I can get a rental car for 40 a day up to thirty days starting today? Sorry. I just wanna make sure I got it right.