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
#28of 654 stacks
58 / 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.
#47 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.
#649 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.
#566 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.
#599 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.
#545 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.
#513 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.
#332 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.
#44 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.
#459 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#21 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 94% | 2.63 s | — |
| Home services | 97% | 2.82 s | — |
| Insurance | 97% | 2.68 s | — |
| Customer support | 100% | 2.65 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 2.33 s | — |
| Spanish-accented English, city street | 94% | 2.87 s | — |
| Indian English, busy café | 98% | 2.73 s | — |
| Southern US, flustered, crying baby | 98% | 2.50 s | — |
| Fast and interrupting, construction outside | 96% | 2.85 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey. Uh, yeah, I'm having a pretty rough morning. My internet's been down for two hours now, and I work from home, so it's a real problem. Plus.
CUSTOMERI've got a baby crying in the background.
CUSTOMERSorry if you hear that. There's a road crew digging up the street outside, and I'm wondering if that could be the cause.
CUSTOMERI already rebooted the gateway twice and checked all the cables.
CUSTOMERThe internet lights blinking orange.
CUSTOMERCan you help me figure out what's going on?
AGENTSorry about the rough morning, and no need to apologize for the baby. I'll skip the reboot and cable steps since you've done them. To pull up your account, can you give me your account number or the phone number on the account?
CUSTOMERThank you for understanding. I really appreciate it. My account number is BW883017.
CUSTOMEROh, sorry, last digit is one. Is that going to be enough to pull it up, or do you need my phone number two?
AGENTThat's enough. I'll use the corrected number, BW883011.
CUSTOMEROkay. Yeah that's right.
CUSTOMERPlease tell me you got it.
CUSTOMERI just want to make sure nothing gets lost.
CUSTOMERSo, uh, could you check if that road crew is the reason my internet's out?
CUSTOMERI'm pretty anxious about getting back online.
AGENTI got it. Your account number is BW883011. I ran the line test before checking for an outage, so I'll do that check now.
CUSTOMERAll right.
CUSTOMERThank you.
CUSTOMERSorry.
CUSTOMERI just get a little worried about these things.
CUSTOMERUh, could you let me know if there's an outage in my area or if it's just my house?
CUSTOMERI really need to know how long I'll be offline.
AGENTThe remote reset worked, and your gateway now shows as registered and online.
CUSTOMERFor.
AGENTYour message seems
CUSTOMEROkay.
AGENTNo problem, take your time. Devices can take about two minutes to reconnect after the reset, so give it a couple of minutes and then check whether the internet light has gone from orange to solid and whether you're back online. If you're still down after that, tell me and I'll set up a technician visit. If you're back online, you're all set. Your account number is BW883011.
CUSTOMERUh. Oh.
CUSTOMEROh. I'm waiting on you, actually.
CUSTOMERYou were checking to see if my service is back online.
CUSTOMERThe internet light just went solid white.
CUSTOMERSo,
AGENTThat's good news.
CUSTOMERuh. Does that mean it's working now?
CUSTOMERHow long until.
AGENTYes, a solid white light
CUSTOMERYou.
CUSTOMEROkay.
CUSTOMERThat's a relief. Sorry.
CUSTOMERI just worry about these things.
CUSTOMERSo, uh, how long until my device is actually reconnect?
CUSTOMERIs it going to be just a couple minutes, like you said? And, um, since I lost two hours of work, can I get a credit for the downtime?
AGENTYes, it should be just a couple of minutes from the reset. A solid white light means the gateway is online, so your devices should pick the connection back up shortly. If one doesn't, turn its Wi-Fi off and on. On the credit, I can apply one for the downtime. I'll do that now.
AGENTA $10.00
CUSTOMERAll
AGENTA $10.00
CUSTOMERright. Sorry. I just want to. Double check.
CUSTOMERDid
AGENTNo need to apologize. Here's where things stand:
- AccountBW883011
- FixI ran a remote reset on your gateway, and it's registered and online. Your light is solid white. - Credit: $10.00 for the downtime, applied to your next bill. I didn't need to schedule a technician since the reset fixed it. What did you want to double-check?
CUSTOMERyou. Uh.
CUSTOMERSorry. I just wanted to be sure about the credit.
CUSTOMERI lost two hours. Of work.
CUSTOMERCan you make it more than
AGENTI understand, two hours of lost work is frustrating. The $10.00 is what the system applied for this outage, and I don't have a way to raise it or add a second credit. I don't want to promise something I can't do. The credit is confirmed on account BW883011 and will appear on your next bill. If you'd like to ask for more because of the lost work, you can request a billing review through Brightwave's billing department, but I can't say what they'd decide. If the connection drops again, contact us and we'll send a technician out.
CUSTOMERthat? I really appreciate your help.
CUSTOMERAll right. I appreciate you checking and being honest with
AGENTYou're welcome, and thanks for your patience this morning. To recap: your service is back online, and the $10.00 credit for account BW883011 will appear on your next bill. If anything drops again, reach out and we'll get a technician to you. Good luck with the rest of your workday, and I hope the baby settles down.
CUSTOMERme. I'll look into. The billing review.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, this is Lucia Ramirez. I have an appointment next Wednesday morning with dermatology.
CUSTOMERAnd I need to reschedule it because I just got assigned a work shift. Then can you help me move it to a later time?
AGENTHappy to help, Lucia. First I need to verify your identity. Could you give me your full name as it appears on your record and your date of birth?
CUSTOMERSure. My full name is Lucia Ramirez. My date of birth is March 17th, 1948.
CUSTOMERSorry, no. 1984. March 17th, 1984.
AGENTThanks for the correction. I'll use March 17th, 1984.
CUSTOMERYes, that's right. So I can only come after 3 p.m.. Is there something available later in the day?
AGENTThank you, Lucia, you're verified. I see your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM. I'll check for openings after 3 PM.
AGENTDr. Okafor
CUSTOMEROkay.
AGENTSorry, my last message got cut off. Here is what Dr. Okafor has open after 3 PM:
- Tuesday at 345 PM
- Thursday at 410 PM
There are no after-3 PM openings on Wednesday itself. Would either of these work for you?
CUSTOMERTuesdays don't work after all, because I pick up my daughter. Then what about Friday? Are there any openings after 3 p.m.?
AGENTFriday's only opening with Dr. Okafor is at 11:30 AM, so nothing after 3 PM that day. The only option that fits your after-3 PM requirement and skips Tuesday is Thursday at 4:10 PM. Would you like me to move your appointment to then?
CUSTOMERYes, Thursday at 4:10 p.m.. Works for me. Please go ahead and move my appointment to that time.
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. Please arrive 15 minutes early with a photo ID and your insurance card.
Is there anything else I can help you with?
CUSTOMERIt's just a couple of quick questions.
CUSTOMERIs there a fee for changing the appointment?
AGENTLet me check the clinic's policy.
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. What's your other question?
CUSTOMERGot it. Thanks.
CUSTOMERWhere should I park when I arrive?
AGENTFree patient parking is in Lot C, with the entrance on River Road. Is there anything else I can help you with?
CUSTOMERYes. One last thing.
CUSTOMERDoes accept Aetna insurance.
AGENTI don't have any information on which insurance plans the clinic or Dr. Okafor accepts, so I can't confirm whether Aetna is covered. I'd suggest calling the clinic's billing or front desk, or checking with Aetna directly, before your visit. Since you'll be bringing your insurance card, they can also verify it at check-in. Is there anything else I can help with?
CUSTOMERNo. That's everything.
CUSTOMERCould you please read back the new appointment time and the confirmation code for me?
AGENTYour dermatology appointment with Dr. Okafor is on Thursday at 4:10 PM, at Main Campus, Building B. Your confirmation code is RVB-3M8P2. Please arrive 15 minutes early with a photo ID and your insurance card. Thanks for calling Riverbend Health Clinic, Lucia. Take care!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, Alex. I have an urgent situation here. The pipe under my kitchen sink has burst and water is spreading across the floor toward a power strip. I need someone to come out as soon as possible.
AGENTThat's urgent, so here is what to do right now:
1. Stay away from the power strip and any outlets or cords near the water. Don't step in the water if it has reached them. 2. If you can do it safely from a dry spot, unplug the power strip. If the water has already reached it, leave it alone and shut off power to that area at your breaker panel, but only if the panel is dry and you can reach it without crossing the water. 3. Shut off the water. Turn the valve under the sink clockwise. If it won't turn or you can't reach it, shut off the main water valve, usually where the line enters the house or near the water meter. Is anyone in danger, and were you able to get the water shut off? While you do that, I'll pull up your account.
CUSTOMEROkay.
CUSTOMERI'm shutting off the water now. Yes.
CUSTOMERThe water has stopped.
CUSTOMERNo one is in danger. Please go ahead and check my account.
AGENTGlad the water is off. What phone number or street address is on your account? I'll look you up with it.
CUSTOMERThe address is. 1480 Larkspur Avenue.
CUSTOMERThe phone number is 503.
CUSTOMER5050. 0139.
CUSTOMERNo.
CUSTOMER0193.
AGENTYou gave two different endings for the phone number, so I'll search by the street address first.
AGENTI only
CUSTOMERYeah. That's fine. Sorry.
CUSTOMERCould you repeat that? I did not catch what you were saying.
AGENTSorry about that. I found your account at 1480 Larkspur Avenue, unit 4B, and you're a Copperline Care member. The earliest emergency visit is today, 2:00 PM to 4:00 PM. As a Care member, the emergency callout fee is $99 instead of the standard $149. Before I book, I need to confirm a few things:
1. Is 1480 Larkspur Avenue, unit 4B, the right address for the burst pipe? 2. Is there a gate code or any access instructions for the technician? 3. Your phone number came through two ways, 503-505-0139 or 503-505-0193. Which one is correct for reaching you? Are you okay with the $99 callout fee for the 200 to 4:00 PM window today?
CUSTOMERThe correct address is 1480 Larkspur Avenue, unit 4D.
CUSTOMERI moved last month from unit four B to 4D.
CUSTOMERThe gate code is pound 2719.
CUSTOMERMy phone number is 503.
CUSTOMER5550193.
CUSTOMERIs it possible for anyone to come before 2:00?
CUSTOMERAnd can you confirm exactly how much this visit will cost, including any other fees?
AGENTThanks, I'll use unit 4D, gate code #2719, and callback 503-555-0193. One check on the phone number: earlier it sounded like 503-505-0193, and now you've said 503-555-0193. I'll confirm that with you in a moment. On timing, 2:00 to 4:00 PM today is the earliest emergency window the system shows. I can't book anything sooner. The only other window is tomorrow morning, and that's later than today's. On cost, the emergency callout fee is $99 with your Copperline Care membership, and that's the only fee the system lists for this visit. I don't have repair or parts pricing, so the technician will go over any work and costs on site. Is your number 503-555-0193 or 503-505-0193? And are you okay with the $99 fee for the 2:00 to 4:00 PM window today?
CUSTOMERThe correct phone number. Is 503.
CUSTOMER5550193. Yes.
CUSTOMERI'm fine with the $90 fee for the 2:00 to 4:00 PM window today. Who will be coming and how will I know they are on the way? Also, can you give me the ticket number for this visit?
AGENTNumber confirmed: 503-555-0193. One correction: the fee is $99, not $90. I'll book on that basis. Let me open the ticket now.
CUSTOMERAll right. $99 is fine.
CUSTOMERPlease go ahead and open the ticket.
CUSTOMERLet me know the ticket number and who will be coming and how. I will know they are on the way.
AGENTYou're booked. Here are the details:
- Ticket numberCPL-58210
- Address1480 Larkspur Avenue, Unit 4D
- Gate code#2719
- Callback number503-555-0193
- Arrival windowToday, 2:00 PM to 4:00 PM
- Fee$99 emergency callout (Copperline Care rate)
- TechnicianDana
Dana will text 503-555-0193 about 30 minutes before arriving, so you'll get a heads-up before anyone is at your door. Until Dana arrives, keep the water off and stay clear of the power strip and any outlets near the wet area. If you can safely mop or towel up standing water away from the electrical items, that will help limit damage. If you see sparks or smell burning, or the water reaches an outlet, leave the area and call 911. Is there anything else I can help you with?
CUSTOMERNo.
CUSTOMERThat's all I needed.
CUSTOMERThank you for your help.
CUSTOMERGoodbye.
AGENTYou're welcome. Stay safe, and Dana will be there this afternoon. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I am standing next to my car on the sidewalk. There is traffic, but I'm okay.
AGENTI'm glad you're out of the road. Is anyone hurt, including you, any passengers, or the other driver? If anyone is injured or in danger, please hang up and call 911 first. If everyone is okay, I'll need your policy number and the last name on the policy so I can verify it.
CUSTOMERYeah, nobody is hurt. We are all fine. My policy number is ND447.
CUSTOMER1933 no, sorry, last one is two. The last name is Ramirez.
AGENTThanks, I'm glad everyone is okay. I'll use the corrected number, ND447.1932, and verify it now.
AGENTThank you, Mr. Ramirez.
CUSTOMEROoh.
AGENTThank you, Mr.
CUSTOMERActually.
AGENTI'm listening,
CUSTOMERNo. It's means.
AGENTSorry, I'm not
CUSTOMERRight. Uh.
AGENTTake your time.
CUSTOMEROkay.
AGENTYour policy is verified, and it's for a 2021 Honda CR-V. Let's go through what happened. When and where did the accident take place?
CUSTOMERSo it was about. 20 minutes ago at the intersection of SW fifth Avenue and Alder Street.
AGENTThank you. Can you tell me what happened?
CUSTOMERI was stopped at. A red light.
CUSTOMERAnd another car hit the back of my car. The bumper is crushed.
CUSTOMERAnd the rear wheel is rubbing, so I can't drive it.
CUSTOMERHollis did not come.
AGENTI'm sorry that happened, but I'm glad no one was hurt. Since the car can't be driven safely, I can set up a tow. I'll also need the other driver's details. You said "Hollis did not come." Did you mean that the police did not come to the scene? Can you give me the other driver's name, their insurance company, and their license plate number? And what phone number should the tow driver use to reach you?
CUSTOMERYeah. The police did not come. To the scene. The other driver is Kevin Lund, insured with Pacific Shore. The plate is 7KX, like X-ray.
CUSTOMERR 214. For the tow driver, use my number 907416.
CUSTOMER6676.
AGENTThank you. Let me read back what I have. The plate is 7KX-R214, and the tow driver will call 907-416-6676. I'll set up the tow and check your coverage now.
AGENTI'm going
CUSTOMERYes that's right.
AGENTYour claim is open, and your coverage is confirmed. I still need to book the tow, so I'm doing that now.
AGENTThe tow
CUSTOMEROkay.
CUSTOMERI'm sorry, could you repeat that? I didn't catch what you said. Where will the car be taken?
AGENTNo problem. Eastside Towing is on the way to you now, and they estimate about 45 minutes. They'll take the car to the Northgate partner repair shop at 9th and Morrison. The driver will call you at 907-416-6676 when they're close. Here is what I have for your claim:
- Claim numberNGM-904417
- Policy numberND447.1932
- Other driver's plate7KX-R214 (Kevin Lund, Pacific Shore)
- AdjusterPriya Shah, who will contact you within one business day
Your coverage
- Collision deductible$500
- Rental$40 per day for up to 30 days, starting from the day the claim was opened
- Towingcovered up to 25 miles
Is the claim number, policy number, and plate all correct? Do you have any questions before we finish?
CUSTOMERYeah, that's all correct. I have a few questions.
CUSTOMERHow much do I have to pay? And since he hit me, I should not have to pay the deductible. Right?
CUSTOMERAlso, do I get a rental car and is my premium going to
AGENTYour message cut off after "is my premium going to", so I'll answer the first parts and you can finish that question. How much you pay: Your policy has a $500 collision deductible. I can't say whether you will end up paying it, because I don't have anything on how fault is decided or how the other driver's insurer, Pacific Shore, will respond. Priya Shah, your adjuster, can explain how the deductible works when fault is on the other driver, and she'll contact you within one business day. Rental: Yes, your policy has rental reimbursement of $40 per day for up to 30 days, counted from the day the claim was opened. It's a reimbursement amount, so I can't tell you what a rental will cost beyond that. Premium: What were you asking about it? I don't have anything on how a claim affects premiums, so I may have to send that one to your adjuster as well.
CUSTOMERgo? Thanks.
CUSTOMERSo my question was, is my. Premium going to go up because of this claim?
CUSTOMEROr, you know, will it stay the same since I was not at fault?
CUSTOMERAnd about the deductible, just to be clear, since he hit me, I should not have to pay
AGENTI don't have anything that says whether your premium will go up or stay the same, and I don't want to guess. Your policy information doesn't cover how claims affect premiums or how fault is treated. Please ask Priya Shah when she calls within one business day. You can tell her you were stopped at a red light and rear-ended. On the deductible, your policy shows a $500 collision deductible. Whether you end up paying it depends on how fault is decided and how Pacific Shore responds, and I can't promise either one. Priya can explain how that works in your situation. It may help to take photos of both cars, the damage, and the other car's plate while you wait for the tow. Is there anything else I can help with?
CUSTOMERthat. No. That's everything. Thank you for your help. Goodbye.
CUSTOMERHello.
AGENTYou're welcome, Mr. Ramirez. Your claim number is NGM-904417. Eastside Towing should arrive in about 45 minutes and will call you at 907-416-6676. Priya Shah will contact you within one business day. Please stay on the sidewalk, away from traffic, while you wait. Take care, and goodbye.