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
#60of 654 stacks
57 / 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.
#83 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.
#246 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.
#287 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.
#377 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.
#548 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.
#643 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.
#160 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.
#361 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.
#452 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#613 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 94% | 3.87 s | — |
| Home services | 95% | 4.13 s | — |
| Insurance | 97% | 3.44 s | — |
| Customer support | 98% | 3.86 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 3.72 s | — |
| Spanish-accented English, city street | 98% | 3.53 s | — |
| Indian English, busy café | 96% | 3.54 s | — |
| Southern US, flustered, crying baby | 98% | 3.86 s | — |
| Fast and interrupting, construction outside | 94% | 3.72 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi. Yeah, I work from home and my internet has been down for two hours now. There's a road crew digging up the street right outside. A lot of noise traffic going by. I already rebooted the gateway twice and checked all the cables. The internet light is blinking orange. My account number is BW883017. Sorry, last digit is one. Is the road crew outside posting this?
AGENTThe caller corrected the last digit to 1, so the account number is BW883011? They said "BW883017.. last digit is one," meaning the final digit should be 1: BW883011.
CUSTOMERYes that's right, the account number is BW883011.
AGENTThanks, I have account BW883011. There's no known outage or maintenance in your area on our end, so I'll skip the reboot and cable checks you've already done and run a line test.
AGENTThe
CUSTOMEROkay go ahead. So just to confirm, the road crew is digging right outside. Could that be affecting the line?
AGENTThe remote reset worked. Your gateway now shows
CUSTOMERThe internet light just went solid white. Now, how long until my devices reconnect?
AGENTA solid white light means the gateway is back online. Devices can take about two minutes to reconnect. If any haven't picked it up by then, toggle Wi-Fi off and on on that device. On the road crew, I can't say they caused this. There's no outage or maintenance on record for your area, and the line test showed a good signal to your gateway. The problem was that the gateway wasn't registered with our network, and the remote reset fixed that. If the light goes back to blinking orange, call us back and I'll send a technician to check the line outside. You were down for two hours, so would you like a service credit applied to account BW883011 for the downtime?
CUSTOMERYes, please. I'd like a service. Credit for the downtime. How much will that be? I lost two hours of work. Can you make it more than that?
AGENTI'll apply that now.
CUSTOMEROkay, so, uh, let me know what the credit amount is, please.
AGENTI applied a $10.00 service credit to account BW883011, and it will appear on your next bill. I can't raise that amount. It's what the system applied for this outage, and I can't set a different figure. I know that doesn't cover two hours of lost work, and I'm sorry about the disruption. If your devices haven't reconnected or the light goes back to blinking orange, call us back and I'll get a technician out to
AGENTyou.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, this is Jordan Ellis. I have a dermatology appointment next Wednesday morning, but I need to move it because I have a work shift. Then. Could you help me reschedule it? I can only come after 3 p.m..
AGENTI can help with that, Jordan. First I need to verify you. Could you give me your full name as it appears on your record and your date of birth?
CUSTOMERSure. My full name is Jordan Ellis. My date of birth is March 17th, 1948. Sorry. No. 1984. March 17th, 1984.
AGENTThanks for the correction. I'll use March 17th, 1984.
AGENTThank
CUSTOMEROkay. That's right.
CUSTOMERSo about moving the appointment. I can only come after 3 p.m..
AGENTThanks, Jordan, you're verified. I see your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM. Let me check for openings after 3 p.m.
CUSTOMEROkay. Go ahead.
AGENTDr. Okafor has two openings after 3 p.m.: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. Which would you like? I'll also confirm the day is the one you want before I move anything.
CUSTOMERTuesday is. Actually don't work after all. I pick up my daughter, then. What about Friday?
AGENTFriday's only opening with Dr. Okafor is at 11:30 AM, which is before your 3 p.m. cutoff, so it doesn't fit. The slots that work after 3 p.m. are: - Thursday at 4:10 PM. - Tuesday at 3:45 PM, which you've ruled out because of daughter pickup. Would Thursday at 4:10 PM work for you? If not, I can check whether there are later openings.
CUSTOMERThursday at 4:10 p.m.. Works for me. Could you go ahead and move my appointment to that time?
AGENTJust to confirm, I'll move your dermatology appointment with Dr. Okafor from next Wednesday at 9:15 AM to Thursday at 4:10 PM. Moving it now.
CUSTOMERRight. That's exactly what I need. Is there a fee for changing the appointment?
AGENTYour appointment is moved. Let me check the change policy for any fees.
CUSTOMEROkay.
AGENTThere's no fee for this change. The policy is that changes made more than 24 hours before the appointment are free, and a later change carries a $40 fee. Your original appointment is next Wednesday, so you're well outside that window. Your new appointment is: - Provider: Dr. Okafor, Dermatology. - When: Thursday at 4:10 PM. - Location: Main Campus, Building B. - Confirmation code: RVB-3M8P2. Please arrive 15 minutes early with a photo ID and your insurance card. Parking is free in Lot C, with the entrance on River Road. Is there anything else I can help you with?
CUSTOMERYes. Where exactly is lot C? And does Doctor Okafor accept Aetna insurance?
AGENTFor Lot C, all I have is that it's free patient parking with the entrance on River Road. I don't have anything more specific on its position relative to Building B, so the front desk can give you directions when you arrive. I also don't have any insurance or network information, so I can't confirm whether Dr. Okafor accepts Aetna. Please call the clinic's front desk or check with Aetna directly before your visit. You'll be bringing your insurance card anyway, and they can verify coverage then. Is there anything else I can help with?
CUSTOMERNo. That covers everything. Thanks for your help. Goodbye.
AGENTYou're welcome, Jordan. Your appointment is Thursday at 4:10 PM with Dr. Okafor, confirmation code RVB-3M8P2. Goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. I need help right away. A pipe under my kitchen sink has burst and water is spreading across the floor. It's heading toward a power strip. I haven't shut the water off yet. Can you tell me what to do? Or send someone?
AGENTLet's get you safe first. 1. Stay away from the power strip and anything plugged into it. Don't touch it or step in water near it. If you can reach your electrical panel without walking through water, switch off the breaker for the kitchen.
CUSTOMEROkay. I won't go near the power strip. Let me check if I can reach the panel. Yeah, I can get to it without stepping in water. I'm switching the breaker off now. What should I do about the water? Should I shut it off somewhere?
AGENTYes, shut the water off now. Try these in order: 1. Under the sink: Look for the two small valves on the pipes beneath the sink and turn them clockwise until they stop. If the burst is right at the valve or you can't reach it safely, skip this. 2. Main
CUSTOMEROkay, I'm looking for the valve under the sink now and turning them clockwise. The water has stopped. What should I do next?
AGENTGood, that was the right move. While you stay on the line, I'll pull up your account and check availability.
AGENTCan I get
CUSTOMERRight. So. Sure. Go ahead. What do you need?
CUSTOMERHello.
AGENTHi, I'm here. I need your phone number or the street address of the problem so I can pull up your account. Which would you like to give me?
CUSTOMERThe address is one 480 Larkspur Avenue. Or my phone number is (503) 555-0139. No. 0193.
AGENTI'll look you up by the corrected phone number and the address.
AGENTI only
CUSTOMEROkay.
CUSTOMERGo ahead.
AGENTI found your account at 1480 Larkspur Avenue, unit 4B. Is that right? I heard "one 480" earlier, so I want to be sure I have the number correct. You're a Copperline Care member, so the emergency callout fee is $99 instead of the regular $149. The earliest emergency window is today, 2:00 PM to 4:00 PM. I need a few things from you: 1. Is the address 1480 Larkspur Avenue, unit 4B? 2. Is there a gate code or any access instructions for the technician? 3.
CUSTOMERActually, I moved last month. I'm in unit four D now, not four B, so it's 1480 Larkspur Avenue. Unit four B. And yes there's a gate code, it's pound 2719. How much will the visit cost? And can anyone come before 2 p.m.?
AGENTYou said both four D and four B, so I want to get it right. I'll use what you told me: you moved, so the unit is 4D. Please confirm that. On cost, since you're a Copperline Care member, the emergency callout is $99 instead of the regular $149. Payment is by card or check when the work is done. On timing, 2:00 PM to 4:00 PM today is the earliest window the system shows. I can't offer anything sooner. The only other opening is a standard visit tomorrow morning, and that wouldn't be an emergency response. Before I book, I need three things from you: 1. Is the unit 4D? 2. What's the best callback number? Earlier you corrected it to (503) 555-0193. Should I use that one? 3. Are you OK with the $99 callout and the 2:00 to 4:00 PM window today? Once you confirm, I'll open the request and book it.
CUSTOMERYes that's right. The unit is 4D. The callback number is (503) 555-0193. And yeah, $99 is fine. I'll take the 2 p.m. to 4 p.m. window today. Please go ahead and book it.
AGENTOpening the request now.
CUSTOMERGuys who will be coming out and. How will I know they're on the way? Also, can you give me the ticket number for this visit?
AGENTYou're booked. A technician named Dana is coming today between 2:00 and 4:00 PM. Dana will text your callback number 30 minutes before arriving, so you'll know when they're on the way. Your ticket number is CPL-58210. Here's what I have: - Address: 1480 Larkspur Avenue, Unit 4D. - Gate code: pound 2719. - Callback number: (503) 555-0193. - Fee: $99
CUSTOMERYes.
CUSTOMERYeah. $99 for the. Emergency call out. That's correct. Thank you for handling this. Goodbye.
AGENTYou're welcome. Until Dana arrives, leave the sink valves and the kitchen breaker off, and stay clear of the power strip and any standing water. If you smell burning or see sparks, call 911. Take care, goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I think so. I'm at home, but my baby's here and she's crying. Sorry, I'm just a little flustered. Is that okay?
AGENTOf course that's okay. Take all the time you need, and please see to your baby first. I'll be right here. Before we go on, I need to ask: is anyone hurt, including you, your baby, or anyone else involved in the accident? If anyone is injured or in danger, please hang up and call 911 right away. When you're ready and everyone is okay, I'll need your policy number and the last name on the policy so I can pull it up.
CUSTOMERYeah. Nobody got hurt. Thank goodness. It's just the cars. And my baby's just upset from all the noise, that's all. Sorry. I know I sound pretty anxious. Um, my policy number is NG4471903. Oh wait no sorry, last one is two. And the last name's Carter. Is that all right?
AGENTThat's all right, and I'm glad everyone is okay. I'll use the corrected number, NG4471902, and look it up now.
AGENTThank you, Ms. Carter. I found
CUSTOMERI. Sorry, it's Mr. Carter, not miss. I just wanted to make sure that's clear. Is that going to be a problem?
AGENTNo problem at all, Mr. Carter, and I apologize for the mix-up. Your policy is verified. It's NG4471902, on a 2021 Honda CR-V. Is that the right policy and vehicle? Whenever you're ready, tell me about the accident. When and where did it happen?
CUSTOMERUh. Yeah, I think that's right. Please tell me that's the right one. It's a 2021 Honda CRV. So, um, about 20 minutes ago, I was stopped at a red light at Southeast fifth Avenue and Alder Street. Another car hit me in the back, the bumpers crushed and the rear wheels rubbing so I can't drive it. Police didn't come. Is that okay?
AGENTYes, that's the right policy, Mr. Carter. NG4471902 is your 2021 Honda CR-V. It's also fine that the police didn't come. I'll note that in the claim. Since the car can't be driven, I'll get a tow arranged. I want to confirm one thing first: is the car still at Southeast Fifth Avenue and Alder Street, and are you at home while it's still there? And what phone number can the tow driver reach you on? I'll also need the other driver's name, their insurer, and their license plate. If you have that information, please give it to me when you're ready.
CUSTOMERYeah. I think that's all right. The car's still at SW Fifth and Alder. I had to come home quick because of the baby. Um, the phone number to reach me is (614) 494-2412. Is that okay? The other driver is Kevin Lund, insured with Pacific Shore, license plate is 7KXR214X, like X-ray. Is that enough?
AGENTI noticed the location changed. Earlier you said Southeast Fifth, and now you said SW Fifth. I'll hold off on the tow until you confirm which one is right, since the driver has to find the car. Which is it? Here's what I have so far, to check: - Other driver: Kevin Lund, insured with Pacific Shore. - License plate: 7KXR214X (7, K, X as in X-ray, R, 2, 1, 4, X as in X-ray). - Your callback number: (614) 494-2412. - Police did not attend. Is all of that correct? Once you confirm the location, I'll arrange the tow and open your claim.
CUSTOMERSorry. I think I got flustered. It's southeast fifth Avenue and Alder Street, not southwest. Please make sure that's the right spot. Southeast. Everything else is correct. Is that okay?
AGENTThank you, Mr. Carter. That's okay, and I'm using Southeast Fifth Avenue and Alder Street. I'll arrange the tow and open your claim now.
AGENTThe claim
CUSTOMERAll right. Thank you. Um, can you tell me where the car will be taken? And, uh, I just need to know. How much do I have to pay for all this? Is there a deductible or anything? Sorry. I'm just worried about the costs.
AGENTNo need to apologize. Those are fair questions. I'll look up your coverage so I can give you exact details.
AGENTYour claim is open, and the tow is on its way. Claim and tow. -
CUSTOMERI. Okay. Thank you. Uh, can you tell me what my claim number is? And, um, will I get a rental car while mine's being fixed? Also, I just want to check if there's a deductible. Since he hit me. I shouldn't have to pay that, right? And is my premium going to go up? Sorry. I know that's a lot.
AGENTThat's not too many questions, Mr. Carter. Here is what I have. Claim number: NGM-904417. Your adjuster is Priya Shah, and she will contact you within one business day. Tow: Eastside Towing is on the way to Southeast Fifth Avenue and Alder Street, about 45 minutes out. They'll take your CR-V to our partner repair shop at 9th and Morrison. The driver can reach you at (614) 494-2412. Towing is covered up to 25 miles on your policy.
CUSTOMERI. All right. That helps. Thank you. Uh, so about the rental car and the deductible. Do I get a rental while mine's in the shop? Since he hit me. I really shouldn't have to pay a deductible. Right? Also, I'm worried about the premium. Is it going to go up because of this? Sorry again. I just need to know what to expect.
AGENTNo apology needed. Here is what your policy says. Rental: Yes. Your policy covers a rental at $40 per day for up to 30 days, starting from the day the claim was opened. If a rental costs more than $40 a day, you'd cover the difference. Deductible: Your collision deductible is $500. Whether you end up paying it depends on how fault is decided, and I can't tell you that. Priya Shah, your adjuster, will go over it with you. I don't want to promise you won't owe it when I can't know that yet.
CUSTOMERI. All right. I appreciate you explaining. I just, uh, I'm really hoping I don't have to.
AGENTI understand, Mr. Carter. It's natural to hope for that, and you did the right things today: you got to safety, got the other driver's details, and reported it quickly. Those details will help Priya when she looks at fault. She's the best person to tell you where the deductible stands. Two more things I should have said earlier. I can't speak to whether your premium might change, because I don't have anything that tells me that. Priya can point you to the right place for that question. Your tow is about 45 minutes out, so the driver will call (614) 494-2412 when they're near. If you can't be at the car, the driver may want to know that, so keep your phone handy. Is there anything else I can help with right now? If
CUSTOMEROkay. That's helpful. Thank you. I'll keep my phone close, and I'll wait for Priya to call about the deductible and the premium claim numbers NGM904417, right? I.
CUSTOMERThink that's everything I needed. Thank you for walking me through it and for being patient with me. Goodbye.
AGENTYes, that's right, Mr. Carter. Your claim number is NGM-904417.
AGENTPriya Shah will call within one business day about the deductible, your premium, and the rental. Your policy number is NG4471902, and the other driver's plate is 7KXR214X. Eastside Towing should reach you in about 45 minutes. Please give your little one a hug for me. Take care, and goodbye.