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
#61of 654 stacks
56 / 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.
#196 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.
#1 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.
#243 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.
#150 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.
#394 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.
#186 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.
#207 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.
#370 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.
#470 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#535 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 3.56 s | — |
| Home services | 87% | 3.95 s | — |
| Insurance | 98% | 3.76 s | — |
| Customer support | 98% | 3.84 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 96% | 3.68 s | — |
| Spanish-accented English, city street | 92% | 3.62 s | — |
| Indian English, busy café | 94% | 3.67 s | — |
| Southern US, flustered, crying baby | 96% | 3.94 s | — |
| Fast and interrupting, construction outside | 92% | 4.29 s | 100% |
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 now. I work from home and I'm calling from a busy cafe at the moment because I can't get online. There's a road crew digging up the street outside my house so I was wondering if that's the cause. I already rebooted the gateway twice and checked all the cables. The internet light is blinking orange. Can you check what's going on? My account number is BW883017. Sorry, last digit is one.
AGENTI understand—that's frustrating, especially when you're trying to work. Let me look into this for you. I'll check your account and see if there's an outage in your area.
AGENTGood news—no outage in your area. That road crew work might be related, but let me run a line test to see what's happening between our network and your gateway.
AGENTThe line test shows good signal from our end, but your gateway isn't registered. Since you've already rebooted twice, let me send a remote reset to your gateway and check if that brings it back online.
AGENTExcellent! The remote reset worked. Your gateway is now registered and online. Give your devices a couple of minutes to reconnect, and you should be back up and running. The blinking orange light should stabilize once everything syncs up. Is there anything else I can help with?
CUSTOMERYeah, the internet light just went solid white now. How long until all my devices reconnect fully? Also, since I lost two hours of work, can you give me a credit for the downtime?
AGENTGreat—solid white means you're good to go. Devices typically reconnect within a couple of minutes, though it can vary depending on how many you have. You should be fully up by now or very shortly. Absolutely, I can apply a credit for the two hours of downtime. Let me do that for you.
AGENTDone. I've applied a $10.00 credit to account BW883017 for the two-hour downtime. It'll show up on your next bill. You're all set—get back to work!
CUSTOMERI lost two hours of work. Can you make it more than that?
AGENTI understand the frustration, but the $10.00 credit is what the system allows me to apply for downtime incidents. That's what's been credited to your account BW883017. If you feel you need additional compensation beyond that, you're welcome
CUSTOMERAll right, that's clear. Thank you for your help. Goodbye.
AGENTYou're
AGENTwelcome! Glad I could get you back online. Take care!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi Alex. I need to reschedule my dermatology appointment next Wednesday morning. Something came up at work so I can only make it after 3 p.m. My name is Jordan Ellis. Can you help me move it?
AGENTI'd be happy to help you reschedule, Jordan. Before I look up your appointment, I need to verify your identity. Could you please provide your date of birth in the format YYYY-MM-DD?
CUSTOMERMarch 17, 1948. Sorry, no, 1984. March 17, 1984.
AGENTThank you for clarifying that. Let me look up your account with the corrected date of birth.
AGENTGreat, I've verified your account. Now let me find your upcoming appointments.
AGENTPerfect! I found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 a.m. You need to move it to after 3 p.m. Let me check Dr. Okafor's availability for next Wednesday afternoon.
AGENTI checked Dr. Okafor's availability, but unfortunately there are no open slots on next Wednesday after 3 p.m. The available times are:
- Tuesday at 900 a.m. or 3:45 p.m.
- Thursday at 410 p.m.
- Friday at 1130 a.m.
Would any of these work for you? The Thursday 410 p.m. slot is after 3 p.m. if you'd prefer to stay close to Wednesday.
CUSTOMERTuesdays don't work after all. I pick up my daughter then. What about Friday? Is there anything after 3 p.m. on Friday?
AGENTUnfortunately, the only available slot on Friday is at 11:30 a.m., which is before 3 p.m. Your best option that meets your after 3 p.m. requirement would be Thursday at 4:10 p.m. Would that work for you?
CUSTOMERThursday at 4 10 p.m. works for me. Please book that slot. Is there a fee for changing the appointment?
AGENTGreat! Let me reschedule your appointment to Thursday at 4:10 p.m., and I'll also check our cancellation and change policy for you.
AGENTNow let me reschedule your appointment:
AGENTPerfect! Your appointment has been rescheduled. Here are your details:
Rescheduled Appointment
- PatientJordan Ellis (DOB: March 17, 1984)
- DepartmentDermatology
- ProviderDr. Okafor
- New Date & TimeThursday at 4:10 p.m.
- LocationMain Campus, Building B
- Confirmation CodeRVB-3M8P2
Regarding the feeOur policy is that changes made more than 24 hours before the appointment are free. Since your original appointment was next Wednesday morning, you're well within that window, so there will be no fee for this change. Please arrive 15 minutes early with your photo ID and insurance card. Is there anything else I can help you with?
CUSTOMERThanks for confirming. Where should I park for this appointment?
AGENTYou can park in Lot C, which has free patient parking. The entrance is on River Road. Is there anything else I can help you with?
CUSTOMERDoes Dr. Okafor accept Aetna insurance?
AGENTI don't have access to insurance information in my system. For questions about which insurance plans Dr. Okafor accepts, I'd recommend contacting the clinic directly or checking your insurance card for the provider network. Is there anything else I can help you with regarding your appointment?
CUSTOMERNo, that covers everything. Thanks for your help. Goodbye.
AGENTYou're welcome, Jordan! Thanks for calling Riverbend Health Clinic. Have a great day!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMEROh. Hehe.
AGENTHey, no
CUSTOMERSorry if I sound rushed. I've got a real emergency here. The pipe under my kitchen sink just burst and there's water spreading all over the floor. It's heading right toward a power strip. I've got a baby crying in the background and I haven't shut the water off yet. Can you help me fast?
CUSTOMEROh, uh...
CUSTOMERSorry, I'm just really panicked right now. Are y'all not able to help with plumbing emergencies? Is there someone else I should call?
AGENTYou've reached the right place—we handle plumbing emergencies. Take a breath, I'm here to help. Let's get you safe first. Right now, do this immediately:
1. Shut off your water main. It's usually in the basement, garage, or outside near the street. Turn the valve clockwise until it stops. This will stop the water flow. 2. Move that baby away from the power strip area and keep everyone clear of the wet floor. 3. Unplug the power strip if you can do it safely without getting shocked. Once you've done those things, call me back or stay on the line and let me know you're safe. I'll get a technician out to you as fast as possible. Have you been able to shut off the water main?
CUSTOMERYeah, I'm doing it right now. Okay, I think it stopped. Thank goodness. Sorry, I'm just pretty shaken up. The baby's away from the area and the power strip's unplugged. Can you let me know how much the visit will cost before you send someone? And, uh, I moved last month. I'm in Unit 4D at 1480 Larkspur Avenue now, not 4B. Is that going to be a problem?
AGENTYou did exactly right—great job staying calm and getting everyone safe. That address change is no problem at all; we'll have the correct one on file. Let me check what an emergency plumbing visit costs and get you the earliest available slot.
AGENTOkay, here's what we have for you:
Emergency visit today, 200 PM to 4:00 PM: $149 callout fee
If you're a Copperline Care member, it's $99 instead. Are you signed up for that? The earliest we can get someone out is today in that 2 to 4 PM window. Does that work for you?
CUSTOMERSorry, I just... Is there any way someone could come before 2 p.m.? I'm really worried about the water damage, and the baby, and I'd feel a lot better if it could be sooner. If not, I'll take that 2 to 4 p.m. window. And, uh, I don't think I'm a Copperline care member, unless it's automatic with the building or something? Could you check for me?
AGENTI understand—that's a stressful situation. Unfortunately, 2:00 to 4:00 PM today is the earliest emergency window we have available right now. I wish I could get someone sooner, but that's what the system shows. The good news is we'll have a technician there this afternoon. Let me pull up your account to check on the Copperline Care membership.
AGENTGreat news! You are a Copperline Care member, so your emergency callout fee is $99 instead of $149. That's a nice savings. Now, to confirm before I book this: you're at 1480 Larkspur Avenue, Unit 4D (you mentioned you moved last month from 4B). The fee is $99, and we'll have someone there between 2:00 and 4:00 PM today. Does that work for you? And what's the best phone number to reach you?
CUSTOMERThank you so much for checking. Yes, that's right. I'm at 1480 Larkspur Avenue, Unit 4D. I moved from 4B last month. Sorry, I just want to make sure that's correct on your end. Is that okay? Window is fine. I'll take 2 o'clock to 4 o'clock PM. My best number is 503-555-0139.
AGENTPerfect. I've got it—Unit
CUSTOMERNo, sorry. 0-1-9-3. Could you repeat that back to me, just to be sure? And, uh, the building gate code is pound 2-7-1-9. Will the technician use that?
CUSTOMEROkay, thank you. Um, could you let me know who's coming and how I'll know they're on the way? Also, will I get a ticket number or something to track the visit? Sorry, I just want to make sure I don't miss anything.
AGENTLet me get that back to you clearly:
Callback number503-555-0193
Gate code#2719
Yes, the technician will use that gate code to access the building. And absolutely—I'm about to create your service request right now, which will give you a ticket number you can reference. I won't have a specific technician name until they're assigned, but once I book your visit, you'll have the ticket number and can track everything from there. Let me open this up for you now.
AGENTGreat! Your ticket number is CPL-58210. Now let me book you into that 2:00 to 4:00 PM window today.
AGENTExcellent! You're all set. Here's your summary:
Ticket NumberCPL-58210 Service Address: 1480 Larkspur Avenue, Unit 4D Gate Code: #2719 Callback Number: 503-555-0193 Visit Window: Today, 2:00 PM to 4:00 PM Technician: Dana Emergency Callout Fee: $99 (Copperline Care member) Dana will text you 30 minutes before arrival, so you'll know exactly when to expect them. Keep that water main shut off until Dana gets there and assesses the damage. You did everything right today. Is there anything else you need?
CUSTOMERNo, that covers everything. Thank you so much. I really appreciate your help. Alright, I'll wait for Dana's text and keep the water off.
AGENTYou're very welcome.
CUSTOMERGoodbye.
AGENTGoodbye, and hang
AGENTin there. Dana will take great care of you. Take care!
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERHi, Alex. I'm in a hurry. I need to file a claim for an accident Someone hit the back of my car about 20 minutes ago at Se 5th Avenue and Alder Street The rear bumper is crushed the wheels rubbing so I can't drive. Nobody's hurt. Police didn't come My policy number is NG4471903 Sorry, last one is two. The other driver is Kevin Lund, insured with Pacific Shore, plate 7KX, like x-ray, R214 Can you tell me what I have to pay and do I get a rental car? I need a tow truck, too Where's the car going? Also, is my premium going to go up? Yeah, I'm safe. Just standing next to my car Can we get started? I really need to get this sorted quickly
AGENTI've got you. Let me get this moving right away. First, let me verify your policy and then we'll handle everything.
AGENTActually, I need your callback phone number for the tow driver. Can you give me that? Also, I want to make sure I have your policy number
CUSTOMEROkay.
AGENTI need two
CUSTOMERYeah, it's plo-
CUSTOMER8-0- That's the number I'm calling from. Go ahead with the policy.
AGENTGot it. So your policy number is NG4471902, and your callback number is the one you're calling from. Let me verify
CUSTOMERuh-huh Yep, that's right. Let's move on. I need to know what I have to pay, and I need a tow truck.
AGENTPerfect. Your policy is verified. Now let me open your claim and get your coverage details so I can tell you what you'll pay.
AGENTGood news.
CUSTOMERRight, just give me the details. I'm short on time. Is there a deductible, and do I get a rental?
AGENTYes to both. Your collision deductible is $500. Your rental is covered at $40 per day for up to 30 days, starting from today when we open the claim. Towing is covered up
CUSTOMERBut he hit me, so I should not have to pay that, right?
AGENTI understand—the other driver was at fault. However, your deductible applies to your collision coverage regardless
CUSTOMERThank you for watching!
AGENTYou're
CUSTOMERYeah, got it. When does his insurance pay me back? Dude, where's my car getting towed?
AGENTYour car is being towed to Northgate's partner repair shop at 9th and Morrison. Eastside Towing is handling it—they'll be there in about 45 minutes. As for the other driver's insurance paying you back: that's something your adjuster, Priya Shah, will handle. She'll contact you within one business day. She'll work with Pacific Shore Insurance on their liability. Here's what you need:
-
CUSTOMEROkay.
CUSTOMEROkay, that's fine. What's the claim number? I need to make sure I have it. And will my premium go up because of this?
AGENTYour claim number is NGM-904417. As for your premium—I can't say. That's determined after the claim is fully resolved and depends on factors like your driving history and how the claim is settled. Your adjuster Priya Shah can answer that when she contacts you. To recap: Policy NG4471902, other driver's plate 7KXR214,
CUSTOMERGot it!
CUSTOMERAlright, thanks for your help, Alex. That's everything I need. Goodbye!
AGENTYou're
AGENTwelcome. Your claim number is NGM-904417. Take care, and Priya will be in touch within one business day.