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
#315of 654 stacks
46 / 100
Leader AssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Cartesia Sonic-3.6, 68 / 100
Where it ranks
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.
#656 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.
#604 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
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.
#247 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.
#86 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.
#134 of 661 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#55 of 661 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 71% | 2.75 s | 83% |
| Home services | 80% | 2.88 s | 92% |
| Insurance | 74% | 2.75 s | 100% |
| Customer support | 81% | 3.24 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 74% | 2.77 s | — |
| Spanish-accented English, city street | 75% | 3.06 s | — |
| Indian English, busy café | 76% | 3.18 s | — |
| Southern US, flustered, crying baby | 79% | 2.88 s | — |
| Fast and interrupting, construction outside | 79% | 2.42 s | 92% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
AGENTOkay, let me quickly check what’s going on with your service and that road work.I’m checking your account and local outage info now, since the street work might be affecting service.One moment while I look into it.Let me check that for you.I’m pulling up your outage details now.I’m checking the outage status now.I’m verifying the local outage status now.Checking that for you now.I’m looking up your outage details now.I’m checking your outage details now.Let me check your outage status now.Checking your outage status now.I’m checking your outage details now.I’m checking your outage details now.I’m checking your outage details now.I’m checking your outage details now.Totally okay on the last digit correction. I can’t access live account or outage systems from this chat, so I can’t directly verify the road work status. Given the blinking orange light and the digging outside, it could be a line issue. If you can, contact Brightwave support directly so they can check outages for your address and give an estimated restore time.
CUSTOMERHi Alex, sorry, I'm kind of flustered. My baby's crying and I've been working from home, but my internet's been down for two hours now. I saw a road crew digging up the street outside, and I already rebooted the gateway twice, checked all my cables, but the internet light's blinking orange. Can you check if the roadwork is the reason? I really need the connection back. My account number's BW883017--sorry, last digit is one. Is that okay? Sorry, so you can't check right now? Is there anyone else I can reach, or do I need to call another number? I just really need to know how long this will last, and if there's any way to get back online sooner.
AGENTGot it, I’ll check your account and outage status first so I can point you the right way.
CUSTOMERSorry, so can you double check my account? It's BW88301 and the last digit is 1. Please tell me if that's enough to check if there's an outage. I'm just anxious with the internet down and the kid crying. Is that alright?
AGENTI looked up accountYes, that’s enough. I have account number BW883011. There’s no area outage showing. I ran a line check and sent a remote reset, and the gateway is now registered and online. Give your devices about two minutes to reconnect.
AGENTGot it, solid white is a good sign—let me check the credit option for you.
CUSTOMEROh, thank goodness! The light on the gateway just went solid white now. So, how long until my devices actually get back online? Is it really just two minutes? Sorry, I just need to be sure everything's working right. And since I lost two hours of work, is there any way you can credit my account for the downtime?
AGENTSolid white means it’s back. Two minutes is a typical reconnect time, but some devices can take a bit longer, so give it up to about five minutes if needed. I also applied a ten dollar service credit to account BW883011, and it will appear on your next bill.
CUSTOMERSorry, but I lost two hours of work. Is there any way you could make it more than that? I really depend on this for my job, and it's been stressful.
AGENTI hear you, and I know that’s really stressful. Let me check what additional credit may be possible.
AGENTI understand the situation. I was able to add another ten dollar credit, for a total of twenty dollars, and it will appear on your next bill.
CUSTOMERThank you so much, that helps a lot. I really appreciate it. Goodbye
AGENTYou’re welcome. I’m glad you’re back online. Take care, and goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
AGENTOkay, let me check the schedule and see what options you’ve got.I can’t directly change appointments from here, Wade, but I can help you get it done fast. Call the clinic or use their portal and say you need to reschedule next Wednesday morning because of work, then offer two or three time windows that do work for you, like Thursday afternoon or Friday morning. If you want, I can help you draft a quick one-sentence script you can read while you’ve got your hands full.
CUSTOMERHey Alex, sorry, I got a baby screaming in the background here so I might talk kinda fast. I need to reschedule my dermatology appointment. I was supposed to come in next Wednesday morning, but I just got put on a work shift. Can you help me move it? My name's Wade Carter. Thanks for the suggestion. I'm just... sorry, I'm pretty stressed. I was hoping to handle it over the phone right now. Can you put me through to someone who can actually change it for me, or is there a way to do it right here? I can only come after 3 p.m., if that helps. I'm just worried about missing work and getting this sorted.
AGENTI can help you right here. I can’t transfer calls, but we can reschedule once I verify you. I have Wade Carter. Please tell me your date of birth in year-month-day format, and I’ll look up your appointment and only offer times after 3 PM.
CUSTOMEROkay, sure. My date of birth is March 17, 1948. Sorry, no, 1984. March 17, 1984. Is that all right? I just want to make sure it's the right one.
AGENTGot it, I’ll verify your details and pull up your appointment, then we’ll look for after-3 options.
AGENTI have Wade Carter with date of birth March 17, 1984, verified. Your current dermatology appointment is next Wednesday at 9:15 AM. After 3 PM, I can offer Tuesday at 3:45 PM or Thursday at 4:10 PM with Dr. Okafor. Which one do you want?
CUSTOMERSorry Days won't work after all. I pick up my daughter then. What about Friday? Is anything open then after 3? If not, I guess Thursday at 4:10 PM would be all right. Just want to make sure I don't mess this up.
AGENTI’ll check Friday after 3 and, if nothing’s open, move you to Thursday at 4:10 PM.
AGENTThere’s no Friday slot after 3 PM; Friday is only 11:30. You’re now rescheduled to Thursday at 4:10 PM. Your confirmation code is R V B 3 M 8 P 2. Please arrive 15 minutes early.
CUSTOMERRight, thank you for confirming that. Just to be sure, there's no fee for changing the appointment, right? Sorry, I just want to make sure everything's okay.
AGENTLet me quickly check the clinic’s change policy so I don’t guess.
AGENTChanges made more than 24 hours before the appointment are free. Later changes have a 40 dollar fee.
CUSTOMEROkay. That's a relief. Thank you.
AGENTI’m glad thatYou’re welcome. I’m glad we got it sorted.
CUSTOMERWhere should I
AGENTWhere should you put what? If you mean the confirmation code, keep it somewhere handy, like your notes app or written on a card, so you can read it back if needed.
AGENTLet me check the parking details so I can give you the right spot.
CUSTOMEROh, no, sorry. I meant where to park when I get to the clinic. Is there a specific lot or street parking? I just want to make sure I don't get lost, you know?
AGENTFree patient parking is in Lot C, with the entrance on River Road.
CUSTOMERAll right, thank you. That helps a lot. Last thing, does Dr. Okafor accept Aetna insurance? Sorry, I just need to double-check so there aren't any surprises.
AGENTI can’t verify insurance acceptance here, so I don’t want to guess. Please call the clinic or check with Aetna using Dr. Okafor’s details to confirm coverage before your visit.
CUSTOMEROkay. Thanks for letting me know. I'll double-check with Aetna then, just to be safe. So to confirm, Thursday at 4:10 PM with Dr. Okafor, confirmation code RV
AGENTYes. Thursday at 4:10 PMYes. Thursday at 4:10 PM with Dr. Okafor, confirmationYour confirmation code is R V B 3 M 8 P 2.
CUSTOMERBB-3M Hi.
AGENTLet me double-check the rescheduled provider so you can feel confident.
CUSTOMERSorry, just want to be sure, Dr. Okafor, not York, right? I was booked with Dr. Okafor before. Can you confirm it's still Dr. Okafor for Thursday at 4:10 PM? I get nervous about these mix-ups.
AGENTIt’s still Dr. Okafor for that appointment.
CUSTOMERAlright, that's a relief. Thank you so much for checking. All set then. I really appreciate your help today. Goodbye.
AGENTYou’re all set. Take care, and good luck with the rest of your day. Goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
AGENTOkay, that sounds urgent—let’s focus on keeping you safe and stopping the water first.First, don’t touch the water near that power strip. If you can safely reach it without stepping in water, switch off the power to that outlet at your breaker panel, or unplug the strip from a dry area. Next, shut off the water supply to the sink, usually a valve under the sink or the main shutoff if needed. Then, keep the area clear and call an emergency plumber right away to fix the burst pipe.
CUSTOMERHi, yes, I have an emergency - a 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 help? Got it. I'm shutting off the water now. Okay, it's stopped. I'll keep clear of the power strip. Can you send someone out? How much will the visit cost?
AGENTLet me check the emergency window and fees, then we’ll get your details to book.
AGENTThe emergency callout fee is $149, or $99 if you have Copperline Care.I’ll pull up your account to confirm the right fee and address, then we can book the earliest emergency window.What’s the best callback number or the service address so I can look you up? I need that to confirm whether your emergency callout is 149 dollars or 99 dollars with Copperline Care, and to create the ticket.
CUSTOMERAll right
AGENTThanks—let me get your account pulled up and line up that earliest emergency slot.
CUSTOMERSure. My callback number is 503-555-0139. No, 0193. The service address is 1480 Larkspur Avenue. I moved from Unit 4B to Unit 4D last month, so it's 4D now. Can you confirm the fee and book the earliest emergency window? And the gate code is #2719.
AGENTYou’re all set. The Copperline Care emergency callout fee is 99 dollars, and you’re booked for today between 2:00 PM and 4:00 PM.
Let me read back detailsthe service address is 1480 Larkspur Avenue, Unit 4D, with gate code pound 2719. The callback number is 503-555-0193, and your ticket number is CPL-58210.
CUSTOMERThat's right. Is there any way someone can come before two? And who will be coming and how will I know they're on the way?
AGENTThe 2:00 to 4:00 PM window is the earliest emergency slot available right now, so there isn’t an earlier arrival I can book. The technician assigned is Dana, and you’ll get a text about 30 minutes before arrival at your callback number. Please keep clear of the area near the power strip until the technician can check it.
AGENTYou’re welcome. Stay safe, and we’ll see you in that window. Goodbye.
CUSTOMERUnderstood. I'll keep clear. Thanks for your help. And I've got the ticket number. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I am safe. I'm standing next to my car, in a cafe nearby. No injuries, but my car is not drivable.
AGENTOkay. If you’re safe and uninjured, stay out of traffic and keep the car where it is if moving it isn’t safe. Call your insurance or roadside assistance for a tow, and if needed, contact the local authorities to report the accident. Take photos of the scene and your vehicle, and exchange information with any other parties involved. Don’t admit fault; just stick to the facts.
AGENTOkay, let’s get your claim started and figure out the next steps together.To help with your claim, I need to verify your policy first. Please share your policy number and the policyholder’s last name.
Also, since your car isn’t drivable, tell me the exact location for pickup and a callback number, and I can arrange a tow after the policy is verified.
CUSTOMERYes, I have already exchanged information. The other driver is Kevin Lund, insured with Pacific Shores. His plate is 7K (X like X-ray) R214. Nobody is admitting fault. I just need to know what to do next. Can you help me with my claim? Sure, my policy number is NG4471903. No, sorry, last one is 2. My last name is Mehta. The car is at SE 5th Avenue and Alder Street. My callback number is 9074166676.
AGENTAlright, I’ll verify your policy and get a tow started, then we’ll finish the claim details.
CUSTOMEROkay, go ahead. I am waiting.
AGENTI’ve verified your policy number NG-4471902 and opened claim NGM-904417. The other driver’s plate I have is 7KXR214. A tow has been dispatched with an estimated arrival of about 45 minutes.
Your collision deductible is 500 dollars. Rental is 40 dollars per day for up to 30 days from when the claim was opened. Towing is covered up to 25 miles.
CUSTOMERAha, that's right! But he hit me, so I should not have to pay the deductible, right? And will my premium go up because of this? Also, where will my car be taken for repair?
AGENTOkay, let me walk through what I can see and what your adjuster will decide.I can only confirm the coverage details we have: the collision deductible is 500 dollars. Whether you ultimately pay it depends on the liability decision and any recovery; your adjuster will make that call. I also can’t say if your premium will go up.
Your car is being taken to a Northgate partner repair shop at 9th and Morrison. For reference, your policy number is NG-4471902, the other driver’s plate is 7KXR214, and your claim number is NGM-904417.
CUSTOMERYes, that's clear. Thank you for your help. Goodbye.
AGENTYou’re welcome