Roark Live Bench · Suite v1.3 · Sweep of 23 October 2026
Voice AI models, ranked on live phone calls.
Every speech-to-text, language model and text-to-speech model, run in every combination on the same real call to the same agent. A model is ranked on every stack it runs in; the stacks are the evidence.
Our picks
Task completionMedian responseCost per minute- Best overallAssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.697%3.9 s$0.055
- Best valueAssemblyAI Universal-3.5 Pro + Google Gemini 3.8 Flash + Cartesia Sonic-3.597%4.3 s$0.048
- FastestOpenAI Whisper-1 + Google Gemini 3.8 Flash + OpenAI TTS-1 HD88%0.5 s$0.023
- Best speech-to-speechgrok-voice-think-fast-2.082%2.1 s$0.083
- Best in customer supportAssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + ElevenLabs v4 Turbo100%3.9 s$0.096
- Best in healthcareAssemblyAI Universal-3.5 Pro + Google Gemini 3.8 Flash + Cartesia Sonic-3.696%4.4 s$0.041
- Best in home servicesAssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.596%4.0 s$0.058
- Best in insuranceAssemblyAI Universal-3.5 Pro + OpenAI GPT-4o + Cartesia Sonic-3.698%3.2 s$0.042
The read
- 430 of 642 cascades complete the task in at least 90% of calls, and the top 10 sit within 1 point of each other. What separates the top stacks is speed and cost.
- Median response time runs from 0.5 s to 6.0 s on the same agent and the same caller, a spread of 5.5 s that comes entirely from the models behind it.
- No stack wins everything. The fastest, OpenAI Whisper-1 + Google Gemini 3.8 Flash + OpenAI TTS-1 HD at 0.5 s, ranks 530 of 642 on task completion; the most complete is Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD at 99%.
- The language model matters most: swapping it moves task completion by 7 points, against 3 for the speech engine and 2 for the transcriber.
Cascade vs Speech-to-Speech
The first choice to make. A cascade chains three models: one transcribes, one decides what to say, one speaks. A speech-to-speech model does all three at once. Both run the same agent on the same calls here.
- Cascades lead on task completion, tool use and time to first word; speech-to-speech leads on response time and cost per task. Neither wins outright, so the right choice depends on what your calls need.
- The biggest difference is task completion: 95% for cascades against 77% for speech-to-speech.
| Measure | Cascade | Speech-to-speech |
|---|---|---|
| Task completion | 95% (leads) | 77% |
| Tool use | 72% (leads) | 55% |
| Time to first word | 0.7 s (leads) | 1.3 s |
| Response time | 3.6 s | 2.6 s (leads) |
| Cost per task | $0.15 | $0.15 (leads) |
The three strongest of each, averaged. Cascades: Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.5; AssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Rime Coda; Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + Rime Coda. Speech-to-speech: grok-voice-think-fast-2.0; gemini-3.8-live; amazon.nova-2-sonic-v1:0. Each measure is scored 0 to 100 on its own scale, further out is better; the table gives the same figures in their own units.
Which to use
- Choose speech-to-speech when the pause matters more than the outcome: short transactional calls, callers who interrupt, queues where every half second costs you callers. Expect to pay more, and choose the model carefully (gpt-live-1 (backend gpt-6.1-sol) leads here).
- Choose a cascade when the call has to complete, when cost matters, or when you need to see which stage to fix. It is 13 points ahead on task completion here.
- Costs are what each stack’s providers charged for these calls, at the rates in effect when they ran. Telephony and hosting are not included.
Speech-to-Text
The transcriber turns the caller's speech into text. It decides what the agent thinks it heard, and nothing after it can start until it finishes.
- AssemblyAI Universal-3.6 Pro, AssemblyAI Universal-3.5 Pro, Deepgram Nova-3 and Speechmatics Enhanced (realtime) are level: none leads by more than the margin of error. Of them, AssemblyAI Universal-3.6 Pro costs least, at $0.030 a call. Avoid Speechmatics Linden-1 (own VAD): last on semantic word error rate (2.2%).
- Speechmatics Linden-1 (own VAD) delivers its transcript in 0.49 s, OpenAI Whisper-1 in 1.93 s: 1.44 s added to every turn of the call.
- AssemblyAI Universal-3.6 Pro is the most accurate: it changes the meaning of 0.9% of the caller's words, against 2.2% for Speechmatics Linden-1 (own VAD).
- In 341 of 648 cascades the transcriber is the slowest step of the turn, whichever model runs it.
Open a model to see where it ranks and the stacks it works best in.
Language model
The language model decides what the agent says and does. It has the most influence on whether the task gets done, and usually takes the largest share of each turn.
- Pick OpenAI GPT-6.1 Sol: it leads on task completion (95%), tool use (71%) and instruction following (4.2 / 5). If speed matters more, Anthropic Claude Haiku 4.5 is the quickest, at 0.36 s, and completes 91%. Avoid OpenAI GPT-5.1: last on tool use (33%) and instruction following (4.1 / 5).
- Anthropic Claude Haiku 4.5 starts answering in 0.36 s, Google Gemini 3.8 Flash in 1.47 s: 1.11 s added to every turn of the call.
- OpenAI GPT-6.1 Sol uses its tools most reliably: it handles its tools without a mistake on 71% of calls, against 33% for OpenAI GPT-5.1.
- In 161 of 648 cascades the language model is the slowest step of the turn, whichever model runs it.
Open a model to see where it ranks and the stacks it works best in.
Text-to-Speech
The speech engine is the voice the caller hears, and the last step before they hear anything.
- Cartesia Sonic-3.6, Cartesia Sonic-3.5 and ElevenLabs v4 Turbo are level: none leads by more than the margin of error. Of them, Cartesia Sonic-3.5 costs least, at $0.165 a call. Avoid OpenAI TTS-1 HD: last on readback accuracy (80%), word error rate (8.7%) and time to first audio byte (2.09 s).
- ElevenLabs v4 Turbo starts speaking in 0.11 s, OpenAI TTS-1 HD in 2.09 s: 1.97 s added to every turn of the call.
- Cartesia Sonic-3.6 is the most accurate: it reads codes, amounts and dates back correctly 87% of the time, against 80% for OpenAI TTS-1 HD.
- Cartesia Sonic-3.6 sounds the most human: 3.8 / 5, against 3.4 / 5 for ElevenLabs Flash v2.5.
- In 99 of 648 cascades the speech engine is the slowest step of the turn, most often with OpenAI TTS-1 HD (54 of them).
Open a model to see where it ranks and the stacks it works best in.
Speech-to-Speech models
One model listens, reasons and speaks, so there is nothing to swap and no stages to split. Each is judged on the whole call, with the same calls and the same scoring as every cascade.
- The model matters as much as the architecture: gpt-live-1 (backend gpt-6.1-sol) completes 86% of tasks, ElevenLabs Realtime v1 Mini 42%.
- grok-voice-think-fast-2.0 answers in 2.1 s against 4.1 s for gemini-2.5-flash-native-audio-preview-12-2025.
- Price varies as much as quality: $0.06 per completed task for amazon.nova-2-sonic-v1:0, $0.69 for gpt-realtime-2.
Open a model for its full report, every figure it was scored on and the calls behind them.
Every stack
The evidence behind the model boards: each combination on its own calls, scored on the same recipe. Open a stack for its full report, every figure it was scored on and the calls behind them.
Each score carries its 95% margin of error. A rank is the best place a stack could hold once every margin is allowed for, so stacks the calls cannot tell apart share one and are listed by the low end of their margin; hover a rank for the worst place it could hold. 92 stacks are level with the leader: their calls cannot tell them apart. Among them, 31 Google Gemini 3.8 Flash, 29 OpenAI GPT-6.1 Sol, 19 Anthropic Claude Sonnet 5.5, 9 Anthropic Claude Haiku 4.5, 2 OpenAI GPT-4o mini, 1 OpenAI GPT-4.1 and 1 speech-to-speech; 48 AssemblyAI, 23 Deepgram and 20 Speechmatics; 48 Cartesia, 33 ElevenLabs, 9 Rime and 1 OpenAI. A cascade's figures are 25% its own calls and 75% what every other stack shows about its transcriber, language model and voice.
Not ranked here for missing data: Speechmatics Linden-1 + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD (no response time or tool use or human-likeness or readback accuracy or voice consistency).
By industry
Each industry ranked on its own calls: the same five callers, its own tasks and tools. A stack has a handful of calls in each, so a cascade is ranked on what its transcriber, language model and voice show across every stack in that industry, and a speech-to-speech model on its own calls there. Pairings show on the main board. Every panel is on one scale, so a bar reads against the other industries as well as its own.
Healthcare
Reschedule an appointment. A patient moves a dermatology appointment around a work schedule, corrects their date of birth, narrows the times twice, and asks about the change fee, parking and insurance.
Home services
Urgent repair: triage and booking. A caller with a burst pipe needs safety advice first, then an emergency visit. The unit on file is out of date, the callback number gets corrected, and the caller pushes for an earlier visit.
Insurance
Report a new auto claim. A driver who was just rear-ended reports a claim, corrects the policy number, spells the other car’s plate, asks about the deductible, a rental and their premium, and needs a tow.
Customer support
Internet outage troubleshooting. A technical caller who has already rebooted the gateway pushes back on scripted steps, wants the line fixed, and asks for a bigger credit for the downtime.
How it works
Every number on this page comes from real phone calls, placed and scored the same way for every stack.
Real calls, four industries, five callers
Roark places real phone calls over the public phone network to a reference agent for each of four industries: rescheduling a clinic appointment, booking an urgent home repair, opening an auto insurance claim and fixing an internet outage. Each agent has its own prompt and tools, identical for every stack. The tasks carry the details real calls trip on: a corrected date of birth, a policy number spelled out, a constraint added halfway through.
Every industry is called by the same five simulated callers: a quiet US English line, a Spanish-accented caller on a city street, an Indian English caller in a busy café, a flustered Southern caller with a baby crying, and a fast caller who interrupts over construction noise. They are equally clear about what they want, so a call fails because of the agent, not the caller. Only the models change, so any difference on the board comes from them.
Each caller rings each industry once for a cascade and four times for a speech-to-speech model. A cascade's figures also draw on its parts, heard in dozens of other stacks; a speech-to-speech model has only its own calls, so it takes more of them.
That makes industries comparable over the same callers, and callers over the same tasks, and the board can be re-ranked by either. One caller within one industry is too few calls to judge, so the board never shows it.
655
stacks
20
calls per stack
13,876
calls scored
Every model, in every combination
9 transcribers, 8 language models and 9 voices are run in every combination with each other, beside 13 speech-to-speech models. A model's own figures pool every stack it runs in, adjusted for its partners in each one, so every model is compared as if it ran with the same partners. A transcriber's figure rests on hundreds of calls with every language model and every voice, not on one lucky pairing.
That measures a model where it actually works: inside a running agent, on live phone audio, through interruptions, corrections and real turn-taking. A test that feeds a model clean audio files or one prompt at a time never sees any of that.
One score, weighted by what matters on a call
Each section ranks on a Roark score. Every figure scores 0 to 100 between two published points: full marks where doing better makes no difference to the caller, zero where the call breaks down. Each then counts at its weight, and the weights follow one order everywhere: whether the caller got what they rang for, then whether the agent got it right, then speed.
A stack, cascade or speech-to-speech, is scored on the outcome and the reply first, then on what each of its components got right on its own calls: the words its transcriber got wrong in a way that changes the meaning, whether its voice read codes and amounts back right, how human it sounded, and whether its tools were handled. A component that leads its section lifts every stack that carries it, by the same recipe for every stack. A figure a stack cannot carry, such as a semantic word error rate for a speech-to-speech model with no transcript, is credited at the field median, so the stack is neither flattered nor punished for it.
On a full sweep each cascade's figure is 25% what its own calls measured and 75% what every other stack shows about its transcriber, language model and voice, fitted across the whole sweep. The split is the same for every stack, so a lucky run does not lead and a stack's score does not move with how noisy its calls were. In an industry a stack has a handful of calls, so a cascade's figure there is what its transcriber, language model and voice show across every stack in that industry's calls, and a speech-to-speech model's is its own calls there. How a particular pairing beats or misses its parts shows on the main board, where each stack has all of its calls. The best overall pick, on the main board and in each industry, is the stack whose score is highest at the low end of its margin of error, so a few lucky calls cannot carry a stack past one whose score rests on hundreds. Stacks that share a rank are listed the same way, so the first row is the pick.
That order comes from real-world voice agent calls, where getting the conversation right predicts how a call ends more strongly than speed does. The latency points come from the same calls: replying faster than about 2 seconds made no measurable difference, and calls went measurably worse once the agent took more than about 3 seconds to reply.
Stacks and speech-to-speech
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Task completionscenario_adherence_check | 21% | 100% | 80% |
| An agent that completes fewer than four calls in five is not fit to deploy. On a full sweep, a cascade's figure is 25% what its own calls (20 or more) measured and 75% what every other stack shows about its transcriber, language model and voice, the same split for every stack, so a lucky run does not lead. Where the sweep is too small for that, and for a speech-to-speech model, the figure is the stack's own. In an industry a stack has a handful of calls, so a cascade's figure there is what its transcriber, language model and voice show across every stack in that industry's calls, and a speech-to-speech model's is its own calls there. How a particular pairing beats or misses its parts shows on the main board, where each stack has all of its calls. | |||
Response timeresponse_time | 17% | 2.0 s | 6.0 s |
| In real calls, replying faster than 2 s made no measurable difference, and calls went worse past 3 s. | |||
Instruction followinginstruction_follow | 13% | 5.0 / 5 | 3.0 / 5 |
| Every model scores between 3 and 5 on the judge's 1 to 5 scale, so that is the range. | |||
Semantic word error ratestt_semantic_word_error_rate | 13% | 0.5% | 3% |
| At 0.5% the best transcribers change the meaning of one word in two hundred on phone audio; at 3% one word in thirty sends the agent the wrong way. | |||
Tool usetool_use | 13% | 100% | 50% |
| An agent that mishandles its tools on half its calls cannot be trusted with the systems it runs on. | |||
Human-likenessvoice_human_likeness | 8% | 4.5 / 5 | 2.5 / 5 |
| 4.5 out of 5 is close to a person on the phone; 2.5 sounds plainly synthetic. | |||
Time to first wordtime_to_first_word | 4% | 1.0 s | 4.0 s |
| A greeting within 1 s sounds natural; 4 s of silence sounds like a dead line. | |||
Readback accuracytts_entity_readback_accuracy | 4% | 100% | 60% |
| Reading a code, amount or date wrong breaks the task it was for; the weakest voices get two in five wrong. | |||
Word error ratetts_word_error_rate | 4% | 2% | 12% |
| At 2% the voice says what it was given; at 12% one word in eight comes out wrong. | |||
Voice consistencyvoice_consistency_check | 4% | 100% | 80% |
| A voice that changes speaker on one call in five is not one a business can put its name to. | |||
Shown, not scored: Turn budget, Barge-in handlingbarge_in_yield_appropriateness
Counted only with price factored in: Cost per task
Language model
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Task completionscenario_adherence_check | 36% | 100% | 80% |
| An agent that completes fewer than four calls in five is not fit to deploy. | |||
Tool usetool_use | 27% | 100% | 50% |
| An agent that mishandles its tools on half its calls cannot be trusted with the systems it runs on. | |||
Instruction followinginstruction_follow | 18% | 5.0 / 5 | 3.0 / 5 |
| Every model scores between 3 and 5 on the judge's 1 to 5 scale, so that is the range. | |||
Time to first tokenllm_time_to_first_token | 18% | 0.50 s | 2.00 s |
| Under 0.5 s is not noticeable; at 2 s the first token alone takes two thirds of the 3 s past which real calls go worse. | |||
Shown, not scored: Prompt cache hitsllm_prompt_cache_hit_rate
Counted only with price factored in: Cost per call
Speech-to-Text
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Semantic word error ratestt_semantic_word_error_rate | 71% | 0.5% | 3% |
| At 0.5% the best transcribers change the meaning of one word in two hundred on phone audio; at 3% one word in thirty sends the agent the wrong way. | |||
Time to final transcriptstt_time_to_final_transcript | 29% | 1.00 s | 2.50 s |
| The fastest transcribers finish in about 1 s; past 2.5 s the transcript alone uses most of a natural reply time. | |||
Shown, not scored: Word error ratestt_word_error_rate
Counted only with price factored in: Cost per call
Text-to-Speech
| Figure | Weight | Full marks | Zero |
|---|---|---|---|
Readback accuracytts_entity_readback_accuracy | 32% | 100% | 60% |
| Reading a code, amount or date wrong breaks the task it was for; the weakest voices get two in five wrong. | |||
Word error ratetts_word_error_rate | 21% | 2% | 12% |
| At 2% the voice says what it was given; at 12% one word in eight comes out wrong. | |||
Time to first audio bytetts_time_to_first_byte | 21% | 0.20 s | 1.50 s |
| Under 0.2 s is not noticeable; 1.5 s is half the point where calls go worse. | |||
Human-likenessvoice_human_likeness | 16% | 4.5 / 5 | 2.5 / 5 |
| 4.5 out of 5 is close to a person on the phone; 2.5 sounds plainly synthetic. | |||
Voice consistencyvoice_consistency_check | 11% | 100% | 80% |
| A voice that changes speaker on one call in five is not one a business can put its name to. | |||
Counted only with price factored in: Cost per call
Factor in price and cost takes 25% of the score; the other weights keep their proportions. Price is scored on a log scale, so each doubling costs the same points.
A figure listed as shown, not scored is on the section’s boards and outside its score. Where a section has not collected a scored figure yet, the others share its weight.
Every call recorded and judged
Every call is recorded. Judge models score each transcript for the outcome and the conversation, and the timings come from the recording. Every figure links to the calls behind it.
Roark is on both sides of every call: it plays the caller, so it keeps the exact text its caller said, and it runs the agent under test, so it sees what the agent’s transcriber heard and what its model wrote for its voice. The transcript and voice figures come from lining those up, with no hand-made transcript in between. Each carries a margin from the synthetic voice or Roark’s transcriber in the loop. Every model faces the same ones under the same conditions, so the figures compare models on the same calls through the same voice and the same ear, though those slips need not fall evenly on each model. The rates will not match a vendor’s figure on a curated set; read them against each other.
An example: one call from this sweep
Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD, 23 October 2026. Highlighted turns are the ones that affected a score. Every stack's report links to its calls.
See how your own agent compares
Roark runs the same kind of calls against your agent, on your scenarios, with the same scoring.
Rank on Roark score
#1of 654 stacks
64 / 100
The leader
Where it ranks
Its models
Task completion
Task completion
How much of the caller’s task the agent completed: the share of the scenario’s checks a judge model found met in the transcript, averaged over calls. Before v1.3, the share of calls judged 4 or better out of 5.
#60 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.
#311 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.
#59 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.
#98 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.
Not scored by this sweep.
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.
#506 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.
#435 of 659 on the board · best 4.3 / 5
Voice consistency
Share of calls where every line the agent spoke was the same speaker, with no change of speaker, gender or language voice partway. It checks who is speaking, not how they sound.
Not scored by this sweep.
#566 of 659 on the board · best 100%
Latency
Response time
The silence between the caller finishing and the agent starting to speak, measured from the recording on every turn of the call.
#207 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.
#516 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#391 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 98% | 3.49 s | — |
| Home services | 93% | 3.24 s | — |
| Insurance | 100% | 3.14 s | — |
| Customer support | 95% | 3.60 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 3.58 s | — |
| Spanish-accented English, city street | 93% | 3.06 s | — |
| Indian English, busy café | 98% | 3.24 s | — |
| Southern US, flustered, crying baby | 96% | 3.32 s | — |
| Fast and interrupting, construction outside | 98% | 3.52 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 has been down for about two hours. I work from home, so I really need it up and running. There's a road crew digging up the street right outside, and I think that might be 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.
AGENTThanks. I'll use the corrected account number, BW883011, and pull it up now.
CUSTOMEROkay. So about the road crew, could they be the reason my Internet is down?
AGENTThat's possible, so I'll check for an outage at your address now.
AGENTThere's no known outage or maintenance in your area, so nothing is reported on our side. That doesn't rule out the road crew damaging a line at your address, so I'll run a line test to see.
CUSTOMERAlright.
CUSTOMERGo ahead and run the line test. Just to confirm, I've already restarted the gateway twice and checked every cable. The Internet light is still blinking orange.
AGENTThe remote reset worked. Your gateway now shows as registered and online on account BW883011. Devices can take about two minutes to reconnect, so give it a moment. Can you check whether the Internet light is solid and whether you're back online? If it's still down after a few minutes, let me know and I'll get a technician scheduled.
CUSTOMERThe Internet light just went solid white. How long until my devices reconnect?
AGENTA solid white light means the gateway is connected. Your devices should reconnect within about two minutes of the reset. If one doesn't, turn its Wi-Fi off and back on, or restart that device. Since you work from home and lost about two hours, I can apply a service credit for the downtime if you'd like.
CUSTOMERYes. I'd like to take a credit for the downtime. How much will it be?
AGENTI'll apply it now. I can't tell you the amount ahead of time, so I'll read back what the system confirms.
AGENTA $10.00
CUSTOMEROkay. Go ahead. So I lost two hours of work. Can you make it more than that?
AGENTI'm sorry about the lost work time. My tools only let me apply the standard downtime credit. I can't raise the amount or choose a different one, so the $10.00 credit on account BW883011 is what I can do. It will appear on your next bill. If you want to ask for more because of the work you lost, you'd need to take that up with Brightwave's billing team. I can't promise how they'd respond. Are your devices back online? If anything is still not connecting, tell me and I'll help.
CUSTOMERAlright. That's clear. My devices are reconnecting now. Thanks for your help, Alex. Goodbye.
AGENTYou're welcome.
AGENTTo recap, your gateway is back online after the remote reset, and a $10.00 credit is on account BW883011 for your next bill. Good luck with the rest of your workday. Goodbye!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey, Alex. Sorry. I'm a bit all over the place here. I need to reschedule dermatology appointment next Wednesday morning. I got called in for a work shift then, so
CUSTOMERis there any way to move it to a later time? If possible, I can only do after 3PM.
AGENTNo problem, I can help with that. First I need to verify you. Could you give me your full name and date of birth?
CUSTOMERYeah. Sure.
CUSTOMERIt's Wade Carter. My date of birth is 03/17/1948. Oh, sorry. No. 1984. 03/17/1984. Is that okay?
AGENTThanks, Wade. I'll use the corrected date.
AGENTThank you, Wade,
CUSTOMERAlright.
CUSTOMEROkay. So, about moving that appointment, do you have any times after 3PM next week?
AGENTI found your appointment with Dr. Okafor in dermatology, next Wednesday at 9:15 AM. Let me check for later openings.
AGENTHere
CUSTOMEROkay. Thanks. Sorry. I just wanna make sure nothing gets lost. 09:15AM next Wednesday was the original. Right? I need something after 3PM if possible. Is that going to be a problem?
AGENTYes, your original appointment is next Wednesday at 9:15 AM with Dr. Okafor, and it's no problem to find something after 3 PM. Dr. Okafor has two openings after 3 PM:
- Tuesday at 345 PM
- Thursday at 410 PM
There's nothing open after 3 PM on Wednesday itself. Would either of those work for you?
CUSTOMERSorry. Tuesdays don't work after all. I have to pick up my daughter. What about Friday? Is there anything on Friday after 3PM, or should I take Thursday at 04:10PM?
AGENTFriday's only opening is at 11:30 AM, so there's nothing after 3 PM that day. Thursday at 4:10 PM is the only option that fits. Would you like me to move your appointment to Thursday at 4:10 PM?
CUSTOMERYes, please. Thursday at 04:10PM. I hope that's alright. Could you confirm that for me? And is there a fee for changing the appointment?
AGENTI'll make the change and check the fee policy.
AGENTThe change is more than 24 hours before the appointment, so there's no fee. Now I'll move it.
CUSTOMEROkay. That's a relief. Thank you. While you're updating it, could you let me know where I should park when I come in? I wanna make sure I don't get lost.
AGENTYour appointment is confirmed, Wade. - Patient: Wade Carter, date of birth March 17, 1984
- ProviderDr. Okafor, Dermatology
- New timeThursday at 4:10 PM, moved from next Wednesday at 9:15 AM
- LocationMain Campus, Building B
- Confirmation codeRVB-3M8P2
Please arrive 15 minutes early with your photo ID and insurance card. There's no fee, since the change was made more than 24 hours ahead. For parking, the clinic has free patient parking in Lot C. The entrance is on River Road. Is there anything else I can help you with?
CUSTOMERAlright. I think that's all clear. Just one last thing. Does doctor Okafor accept Aetna insurance? I really need to be sure before I come in.
AGENTI can't confirm that, Wade. I don't have access to insurance or provider network information, and I don't want to guess on something this important. Please call your insurance company, or check Aetna's provider directory, to confirm that Dr. Okafor is in network. The clinic's front desk or billing office should also be able to verify it. Doing that before Thursday would help you avoid any surprise costs. Is there anything else I can help you with?
CUSTOMERNo. I think that covers it. Sorry. For all the questions. I just wanna make sure everything's in order. Thank you for your help, Alex. Goodbye.
AGENTYou're welcome, Wade,
AGENTand no need to apologize. Your appointment is Thursday at 4:10 PM with Dr. Okafor, confirmation code RVB-3M8P2. Take care, and goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. I need emergency plumbing help. The pipe under my kitchen sink just burst. And water is spreading across the floor toward a power strip. I haven't shut the water off yet. Can you send someone out right away?
AGENTLet's make this safe first, then I'll get someone out to you. 1. Stay away from the power strip and anything plugged in near the water. Don't touch it or step into the water near it. If you can reach your electrical panel without walking through water, turn off the breaker for the kitchen. If you can't do that safely, leave it alone. 2. Shut off the water. Look under the sink for the two small valves on the pipes and turn them clockwise until they stop. If that doesn't work or you can't get to them, turn off the main shutoff, usually where the water line enters the house, near the water heater, or by the meter. While you do that, I'll pull up your account. What's the phone number or street address on the account?
CUSTOMEROkay. I'm clear of the power strip. I'll turn off the water now. Alright. It stopped. My address is 1480 Larkspur Avenue. My phone number is (503) 555-0139. No. Zero one nine three.
AGENTGlad the water's stopped. Let me look up your account, and I'll use the number you corrected: 503-555-0193.
CUSTOMERYes. That's right. Go ahead. I moved last month from Unit 4 B to Unit 4 D. So make sure you have the right unit.
AGENTThanks, I'll use Unit 4D. One thing before I book: is there a gate code or any access instructions for the technician? And is 503-555-0193 the best number to reach you? Also, since you're a Copperline Care member, the emergency callout fee for you is $99 instead of the standard $149. The earliest emergency window is today, 2:00 PM to 4:00 PM. Do you agree to the $99 fee for that window?
CUSTOMERThe gate code is Pound 2719, and my number is (503) 555-0193. About the fee, just to confirm, you said $99. Right? Can anyone come before two?
AGENTYes, the fee is $99 for you as a Copperline Care member. The 2:00 to 4:00 PM window today is the earliest emergency slot I have. Nothing earlier is available. The water is off, so the main risk is contained while you wait. Do you agree to the $99 fee for today, 2:00 to 4:00 PM? If so, I'll book it now.
CUSTOMERYes. I agree to the $99 fee for the 02:00 to 04:00 window today. Who will be coming? And how will I know they're on their way? Also, can you give me the ticket number for this visit?
AGENTI'll open the ticket and book the window now.
CUSTOMEROkay. Go ahead. I'll wait for the ticket number.
AGENTYou're booked. Here are the details:
- Ticket numberCPL-58210
- Service address1480 Larkspur Avenue, Unit 4D
- Gate codepound 2719
- Callback number(503) 555-0193
- Arrival windowtoday, 2:00 PM to 4:00 PM
- Fee$99 emergency callout (Copperline Care member rate)
Your technician is Dana. Dana will text (503) 555-0193 about 30 minutes before arriving, so keep your phone nearby. Until then, keep the water off and stay clear of the wet area and the power strip. If you can safely unplug anything away from the water, do that, but don't reach through standing water. Put towels or a bucket down to limit the spread. If you notice sparking, a burning smell, or water near the outlets or panel, leave the unit and call 911. Is there anything else I can help you with?
CUSTOMERNo. That covers everything. Thanks for your help. Goodbye.
AGENTYou're
AGENTwelcome. Dana will see you this afternoon. Take care, goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah. I'm at home right now. Sorry. It's a little hectic. My baby's crying. But I'm safe. Just
CUSTOMERI wanted to get this started as soon as possible.
AGENTNo need to apologize, take all the time you need. I'm glad you're safe at home. Was anyone hurt in the accident, including you, any passengers, or the other driver? If anyone needs medical attention, please call 911 first and we can pick this up afterward. If no one is hurt, I'll start by verifying your policy. Can you give me your policy number and the last name on the policy?
CUSTOMERThank you. Yeah. Nobody's heard. Just me and the baby, and we're both okay. The other driver seemed fine too. So my policy number is NG4471903 Wait. Sorry. Last one is two, and the last name is Carter. Is that alright?
AGENTThat's alright, I'll use the corrected number. Let me verify it now.
AGENTThank you, Ms. Carter. I've verified policy NG4471902 for a 2021 Honda CR-V. I'm glad you and your baby are both okay. Can you tell me when and where the accident happened, and what happened?
CUSTOMEROh, sorry. It's Carter. I'm a mister, not miss. So the accident happened about twenty minutes ago. I was stopped at a red light at Sissy 5th Avenue and Alder Street, and another car hit the back of my car. The bumper's crushed, the rear wheel is rubbing, so I can't drive it. Nobody's hurt, though. Is that enough info, or do you need anything else?
AGENTMy apologies, Mr. Carter. Thank you for the details. Since the rear wheel is rubbing, I'll get a tow set up for you. Two quick questions first. 1. Is the car still at 5th Avenue and Alder Street, or did you move it? I want to send the tow to the right place. And did you say "Sissy 5th Avenue"? I want to be sure I have the street name right. 2. What's the best phone number for the tow driver to reach you? I also still need the other driver's name, their insurer, and their license plate number, and whether police came to the scene.
CUSTOMERThanks for checking. It's S, E Like Southeast, 5th Avenue in Alder Street. I haven't moved the car. It's still right there. The best phone number is (507) 698-9041. The other driver is Kevin Lund, insured with Pacific Shore, and his plate is 7KX like X-ray, R214. Police didn't come to the scene. Should I have called them?
AGENTLet me get the tow on its way and check your coverage at the same time.
AGENTBefore I dispatch the tow, I'll open your claim.
CUSTOMERAlright. Thank you. Can you let me know what I'll need to pay for this? I'm just anxious about how this works. Do I get a rental car while mine's being fixed?
AGENTI haven't dispatched the tow yet, so I'll do that now.
CUSTOMEROkay. Thank you. Could you tell me where the car will be taken? And will my premium go up because of this? Sorry. I just wanna make sure I understand everything.
AGENTNo need to apologize, these are good questions. Here is where things stand. Your tow: Eastside Towing is on the way to SE 5th Avenue and Alder Street, with an estimated arrival of about 45 minutes. They'll take your CR-V to the Northgate partner repair shop at 9th and Morrison. They have your number, (507) 698-9041, in case they need to reach you. Your towing coverage covers up to 25 miles. Your claim: The claim number is NGM-904417, and your policy number is NG4471902. The other driver is Kevin Lund with Pacific Shore, license plate 7KXR214. Please tell me if any of those are wrong. Your adjuster is Priya Shah, and she'll contact you within one business day. What you'll pay and the rental: Your policy has a $500 collision deductible. I can't say what the final repair cost or your out-of-pocket amount will be. Priya can go over that with you. For the rental, your policy covers $40 per day for up to 30 days, starting from the day the claim was opened, which is today. If the rental costs more than $40 a day, the difference would be yours to pay. Your premium: I don't have anything that tells me whether your premium will change, so I don't want to guess. Priya can tell you more about how the claim is handled. Another driver hit you while you were stopped, but I can't say how that affects your premium. Is there anything else I can help with while you wait for the tow?
CUSTOMERI think that's everything. Just about the deductible, he hit me, so I shouldn't have to pay that. Right? Sorry. I just wanna be sure I'm not missing something. And could you repeat the claim number one more time just to make sure I have it right?
AGENTYour claim number is NGM-904417. That's N-G-M, then 9-0-4-4-1-7. On the deductible, you've described a rear-end hit while you were stopped, which is a strong position. But I can't promise you won't owe it. Your policy has a $500 collision deductible, and I don't have information on how fault will be decided or whether the deductible could be recovered from the other driver's insurer. Priya Shah, your adjuster, can answer that after she reviews the claim. It's a good question to ask her when she calls within one business day. It would help to write down what you remember and take photos of the damage and the scene if you haven't already. Hold on to the contact details you have for Kevin Lund as well. I hope the tow gets there quickly, and I hope the rest of your day goes easier.