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
#168of 654 stacks
53 / 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.
#32 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.
#654 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.
#374 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.
#476 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.
#463 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.
#466 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.
#390 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.
#387 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.
#566 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#496 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 94% | 3.92 s | — |
| Home services | 97% | 3.89 s | — |
| Insurance | 100% | 3.96 s | — |
| Customer support | 98% | 3.66 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 96% | 3.93 s | — |
| Spanish-accented English, city street | 96% | 3.84 s | — |
| Indian English, busy café | 98% | 3.87 s | — |
| Southern US, flustered, crying baby | 95% | 3.96 s | — |
| Fast and interrupting, construction outside | 100% | 3.96 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi, Alex.
CUSTOMERI'm calling from a cafe because my internet at home has been down for two hours.
CUSTOMERI work from home, so it's a big issue. There's a road crew digging up the street outside, and I'm wondering if that's causing the outage. I already rebooted the gateway twice and checked every cable. The internet light is blinking orange. My account number is BW883017.
CUSTOMERSorry.
CUSTOMERLast digit is one.
CUSTOMERCan you check what's happening?
AGENTThe caller corrected the last digit, so the account number is BW883011.
CUSTOMERYes that's right b w.
CUSTOMEREight. Eight.
CUSTOMER3011.
CUSTOMERCan you see if the roadwork outside is affecting my service?
AGENTThanks, I have your account as BW883011. There's no known outage or maintenance in your area, so nothing is reported for the roadwork. I'll run a line test now to see if the line itself has a fault.
CUSTOMEROkay.
CUSTOMERGo ahead and check.
CUSTOMERJust to confirm. I already rebooted the gateway twice and checked all the cables.
CUSTOMERSo the issue is not inside my home. Aha!
CUSTOMERPlease do the line test.
CUSTOMERLike I said, I already restarted the gateway two times and checked every cable. So kindly check from your
AGENTThe remote reset worked. Your gateway is now registered and online on our network. Devices can take about two minutes to reconnect, so your internet should be back shortly. The internet light should also turn solid. Your account number is BW883011. Can you check from home or have someone there confirm it's working? If it isn't back after a few minutes, let me know and I'll set up a technician visit.
CUSTOMERend. Aha!
CUSTOMERThe internet light just went. Solid white.
CUSTOMERHow long until my devices reconnect fully? I'm not at home right now, so I can't check every device.
CUSTOMERBut I'll ask someone there to confirm.
CUSTOMERAlso, I lost two hours of work.
CUSTOMERCan you give me a credit for the downtime?
AGENTSolid white means the gateway is fully connected. Devices usually reconnect within about two minutes of the reset. If one doesn't, power-cycling just that device will normally bring it back. I'll apply the downtime credit now.
CUSTOMERRight.
CUSTOMERGot
CUSTOMERit. How much is the credit going to be? I lost two hours of.
AGENTA $10.00 credit has been applied to account BW883011 for the downtime. It will appear on your next bill. Your service is back, so I don't need to schedule a technician. If the connection drops again or someone at home finds a device that won't reconnect, call us back and we'll take another look. Is there anything else I can help with?
CUSTOMERI lost two hours of work.
CUSTOMERCan you make it more than that?
AGENTThe credit is $10.00, and it will show up on your next bill. I'm sorry about the lost work time, I know how disruptive that was. I can't increase it. The tool I have applies a set credit and doesn't let me enter a different amount, and I won't promise something I can't apply. If you want to ask for more, you can contact Brightwave's billing team and request a review of the credit for the two-hour outage. Your service is back online on account BW883011. Is there anything else I can help with?
CUSTOMERNo.
CUSTOMERThat's all. Thank you for your help.
CUSTOMERGoodbye.
AGENTYou're welcome, and sorry again for the disruption. Take care, goodbye.
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.
CUSTOMERI just got scheduled for a work shift. Then can you help me reschedule?
AGENTI can help with that, Lucia. First I need to verify you. Could you give me your full name as it appears on your record and your date of birth?
CUSTOMERMy full name is Lucia Ramirez. My date of birth is March 17th, 1948.
CUSTOMERSorry. No. 1984. March 17th.
AGENTThanks for the correction. I'll use March 17th, 1984.
CUSTOMERThat's right.
CUSTOMERSo I can only come after 3 p.m.. Is there anything available then?
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.
CUSTOMEROkay.
CUSTOMERSo. I didn't. Catch that. Could you repeat? There's a lot of traffic noise here.
AGENTOf course.
CUSTOMERRight.
CUSTOMERYes. That's right. Only after 3 p.m. works for me.
AGENTSorry about the noise, Lucia. Here are the openings with Dr. Okafor that are after 3 PM:
1. Tuesday at 345 PM
2. Thursday at 410 PM
Which would you like? Note that Tuesday comes before your current Wednesday appointment, and Thursday comes after it.
CUSTOMERTuesdays actually don't work for me, after all. I pick up my daughter. What about Friday? Are there any sports then?
AGENTI assume "sports" means "slots." The only Friday opening is at 11:30 AM, which is before your 3 PM cutoff, so it doesn't fit. With Tuesdays ruled out and after 3 PM required, the one option left is Thursday at 4:10 PM with Dr. Okafor. 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.
AGENTLet me book that for you.
AGENTYou're all set, Lucia. Your dermatology appointment with Dr. Okafor is now on Thursday at 4:10 PM at Main Campus, Building B. Your new confirmation code is RVB-3M8P2. That's R-V-B, 3, M, 8, P, 2. Please arrive 15 minutes early with a photo ID and your insurance card.
Is there anything else I can help you with?
CUSTOMERYes. Just a couple. Quick things.
CUSTOMERIs there any fee for changing the appointment?
AGENTLet me check the change policy.
CUSTOMEROkay.
AGENTChanges made more than 24 hours before the appointment are free, and later changes carry a $40 fee. Since your original appointment was next Wednesday, this change should fall in the free window. You mentioned a couple of quick things. What else can I help with?
CUSTOMERAll right. Thanks for clarifying. Next. Where can I park for the appointment?
AGENTFree patient parking is in Lot C, with the entrance on River Road. Is there anything else you need?
CUSTOMERLast thing.
CUSTOMERDoctor. Okafor.
CUSTOMERAetna insurance.
AGENTI don't have any information about which insurance plans Dr. Okafor accepts, so I can't confirm whether Aetna is covered. The best way to find out is to call the number on the back of your insurance card or check Aetna's provider directory. You can also ask the front desk when you arrive, but I'd confirm beforehand so there are no surprises. Is there anything else I can help with?
CUSTOMERNo. That covers everything. Thanks for your help. Goodbye.
AGENTYou're welcome, Lucia. Your appointment is Thursday at 4:10 PM with Dr. Okafor, confirmation code RVB-3M8P2. Take care, goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, Alex.
CUSTOMERA pipe under my kitchen sink just burst and water's spreading across the floor toward a power strip. I haven't shut the water off yet.
CUSTOMERCan you help me with this?
AGENTYes, I can help. First, please do these things right now:
1. Stay away from the power strip and anything plugged into it while there's water near it.
CUSTOMERGot it.
CUSTOMERUnder.
AGENTSounds like you may have been cut off. To finish the safety steps:
1. Don't touch the power strip or any cords or outlets near the water. If you can reach your breaker panel without stepping through water, turn off the kitchen circuits. 2. Shut off the water. Check under the sink for a small shut-off valve on the burst pipe and turn it clockwise. If that doesn't work or you can't reach it, shut off the main water valve, usually where the water line enters your home or near the water meter. 3. If you Is the water off now, and is everyone safe? While you do that, give me your phone number so I can pull up your account.
CUSTOMEROkay, I'm staying clear of the power strip and outlets. I'll check the breaker panel and shut off the kitchen circuits if I can reach them. Now I'm turning the shut off valve under the sink clockwise.
CUSTOMERThe water has stopped. My phone number is 503.
CUSTOMER555.
CUSTOMER0139.
CUSTOMERNo. 0193.
AGENTGlad the water is stopped. I'll use 503-555-0193 as you corrected it.
CUSTOMERThat's right. Everyone's safe here.
CUSTOMERSo what's the next step for getting a plumber out?
AGENTI found your account. Before I book, I need to confirm a few things. Is the service address 1480 Larkspur Avenue, Unit 4B? Is there a gate code or any access instructions for the technician? Is 503-555-0193 the best number to reach you? The earliest emergency visit is today, 2:00 PM to 4:00 PM. As a Copperline Care member, your emergency callout fee is $99, instead of the standard $149. Would you like me to book that window at $99?
CUSTOMERThe address is. Correct, but I moved from unit four B to unit four D last month. The gate code is pound 2719, and yes.
CUSTOMER503 5550193 is the best number to reach me. Is there any way someone can come before 2 p.m.? If not, I'll take the 2 to 4 p.m. window before confirming. Can you tell me who's coming and how I'll know they're on the way? Also, could you repeat the ticket number for this visit?
AGENTI'll use Unit 4D, since that's where you are now. I'll open the request now.
CUSTOMERRight. Go ahead. So just confirming.
CUSTOMERI'll take the earliest emergency window. If nothing sooner is available, let me know who's coming and how I'll know they're on the way. And the ticket number when you have it.
AGENTUnderstood. The earliest emergency window available is today, 2:00 PM to 4:00 PM, and nothing earlier is offered. I'll book it now at the $99 member rate.
CUSTOMEROkay. I'll take the 2. P.m. to 4 p.m. window. Who will be coming and how will I know they're on their way? And could you give me the ticket number for this visit?
AGENTYou're booked.
CUSTOMERAll right.
CUSTOMERCould you tell me?
CUSTOMERGot it. Could you tell me the. technician's name and how I'll know they're on the way? Also, what's the ticket number for this visit?
AGENTHere are the details:
- TechnicianDana
- Arrival windowToday, 2:00 PM to 4:00 PM
- On-the-way noticeDana will text 503-555-0193 about 30 minutes before arriving. - Ticket number: CPL-58210
- Service address1480 Larkspur Avenue, Unit 4D
- Gate codepound 2719
- Callback number503-555-0193
- Fee$99 emergency callout, the Copperline Care member rate
Until Dana arrives, keep the sink valve closed and stay clear of the power strip and any wet outlets. If the kitchen circuits are still on and the area is wet, leave them off. If water starts flowing again, shut off the main valve. If you see sparks or smell burning, get out and call 911. Is there anything else I can help you with?
CUSTOMERUnder.
AGENTI'm not sure what you meant by "Under." Did you want to ask something about the area under the sink, or was that a stray word from the call? If you're asking about the pipe, leave the sink valve closed and don't touch anything under there until Dana arrives. If you need anything else, I'm here.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes.
CUSTOMERI'm safe.
CUSTOMERI'm standing next to my car. Nobody is hurt.
CUSTOMERYeah, I'm safe at the moment.
CUSTOMERI'm just standing next to my car. No injuries.
AGENTI'm glad you're safe and that no one was hurt. I'll help you get a claim started. Can you give me your policy number and the last name of the policyholder so I can verify the policy?
CUSTOMERSure.
CUSTOMERMy policy number is NG4471903.
CUSTOMEROh, sorry.
CUSTOMERLast one is two.
CUSTOMERThe last name is Mehta.
AGENTYou corrected the last digit, so the policy number is NG4471902. I'll verify that with the last name Mehta.
CUSTOMERYes. That's right.
CUSTOMERMehta is the last name.
CUSTOMERAnd the policy number ends with two.
AGENTThank you, Mr. or Ms. Mehta. I've verified policy NG4471902 for your 2021 Honda CR-V. To confirm, that's N-G-4-4-7-1-9-0-2. Now I need some details about the accident:
1. When did it happen (date and approximate time)? 2. Where did it happen (street, intersection, or address)? 3. What happened?
CUSTOMERIt happened about 20 minutes ago.
CUSTOMERI was stopped at a red light at SW Fifth Avenue and Alder Street.
CUSTOMERAnother car hit the back of my car. The back bumper is crushed and the rear wheel is rubbing.
CUSTOMERSo I cannot drive it. No one is hurt.
CUSTOMERPolice did not come.
AGENTThank you, that helps. It sounds like the car isn't safe to drive with the rear wheel rubbing, so I'll set up a tow for you in a moment. First, I need the other driver's information:
1. Their name
2. Their insurance company
3. Their license plate number
Also, what's the best phone number for the tow driver to reach you?
CUSTOMERThe other driver's name is Kevin Lund.
CUSTOMERHe's insured with Pacific Shore. The license plate is seven.
CUSTOMERK.
CUSTOMERX, like X-ray. Are.
CUSTOMER214.
CUSTOMERThe best phone number for the tow driver is 907.
CUSTOMER416.
CUSTOMER6654.
AGENTLet me read back the plate to make sure I have it right: 7-K-X-R-2-1-4, as in 7, K, X-ray, R, 2, 1, 4. I'll arrange the tow and check your coverage while I open the claim. I don't have an exact date and time, so I'll note it as about 20 minutes before this call.
AGENTThe claim is open. Now I'll arrange the tow and check your coverage.
CUSTOMEROkay. Can you tell me where the car will be taken? Also, will I get a rental car? And how much do I have to pay for this claim?
AGENTHere are the answers to all three questions, plus the claim details. Where the car is going: Eastside Towing is on the way to you at SW Fifth Avenue and Alder Street and should arrive in about 45 minutes. They'll take your CR-V to our partner repair shop at 9th and Morrison. They have your number, 907-416-6654, if they need to reach you. Towing is covered up to 25 miles. Rental: Yes, your policy includes rental reimbursement of $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 pay the difference. What you pay: Your collision deductible is $500. I can't say what the final cost will be or how the other driver's insurance, Pacific Shore, will factor in. Your adjuster will go over that with you. Claim details:
- Claim numberNGM-904417
- Policy numberNG4471902
- Other driverKevin Lund, Pacific Shore, plate 7-K-X-R-2-1-4
- AdjusterPriya Shah, who will contact you within one business day
Is there anything else I can help you with?
CUSTOMERThat's clear.
CUSTOMERBut he hit
AGENTYour message seems to have cut off after "But he hit." Go ahead and finish your thought. Is there something about how the accident happened that you'd like to add or correct?
CUSTOMERme. So I should not have to pay. The deductible, right? Also.
CUSTOMERNo.
CUSTOMERThat's accurate.
CUSTOMERI was stopped at the red light and he hit me from behind.
CUSTOMERJust wanted to confirm.
CUSTOMERSince he hit me, I should not have to pay the deductible. Right.
CUSTOMERAnd will my premiums go up because
AGENTYour message cut off again after "will my premiums go up because," so I'll answer the deductible question first and you can finish the second one. I can't say whether you will or won't have to pay the deductible. Your policy has a $500 collision deductible, and that's all I can confirm. Who is at fault, and whether the deductible is recovered from Pacific Shore, is for your adjuster, Priya Shah, to determine. What you've told me is on the claim: you were stopped at a red light and were hit from behind. I'd bring up the deductible when she contacts you within one business day. Please finish your question about premiums. I can't see anything in your policy about how a claim affects your rates, so I may have to send that to your adjuster as well.
CUSTOMERof this?
CUSTOMERGot it. My question was just whether my premium will
CUSTOMERgo up.
CUSTOMEROkay.
AGENTI can't tell you whether your premium will go up. Nothing in your coverage details speaks to rates, and I don't want to guess. Please ask Priya Shah when she contacts you within one business day, or call Northgate Mutual and ask about your rates. Here is what I have on the claim: you were stopped at a red light and were hit from behind. The tow is on its way, and you have rental coverage while the car is being repaired. Is there anything else I can help you with today?
CUSTOMERNo. That's everything.
CUSTOMERThank you for your help. Goodbye.
AGENTYou're welcome, Mr. or Ms. Mehta. Your claim number is NGM-904417, and Priya Shah will contact you within one business day. Eastside Towing should reach you in about 45 minutes. Please stay somewhere safe while you wait. Take care.