Roark Live Bench · Suite v1.3 · Sweep of 30 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
Roark scoreTask completionMedian responseCost per minute- Best overallUniversal-3.5 Pro + GPT-6.1 Sol + Turbo v2.570 / 10096%4.0 s$0.12
- Best valueUniversal-3.5 Pro + GPT-6.1 Sol + Coda69 / 10098%4.0 s$0.040
- FastestGrok Voice 3.066 / 10087%1.9 s$0.086
- Best speech-to-speechGPT Live 1 (Sol)65 / 10085%2.3 s$0.061
- Best in customer supportGrok Voice 3.085 / 10095%1.7 s$0.083
- Best in healthcareUniversal-3.5 Pro + Gemini 3.8 Flash + Flash v2.575 / 10097%4.3 s$0.10
- Best in home servicesGPT Live 1 (Luna)79 / 10095%2.1 s$0.052
- Best in insuranceUniversal-3.5 Pro + GPT-4o + Sonic-3.676 / 10098%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 2.0 s to 6.2 s on the same agent and the same caller, a spread of 4.2 s that comes entirely from the models behind it.
- No stack wins everything. The fastest, Speechmatics Linden-1 (own VAD) + Anthropic Claude Haiku 4.5 + ElevenLabs Turbo v2.5 at 2.0 s, ranks 559 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.
- The fastest speech-to-speech model answers 0.1 s sooner than the fastest cascade, and its completion rate sits 12 points below the best cascade.
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, time to first word, barge-in handling and cost per task; speech-to-speech leads on response time. Neither wins outright, so the right choice depends on what your calls need.
- Speech-to-speech costs 1.6 times as much per completed task: $0.24 for speech-to-speech against $0.15 for cascades.
- The biggest difference is response time: 3.8 s for cascades against 2.1 s for speech-to-speech.
| Measure | Cascade | Speech-to-speech |
|---|---|---|
| Task completion | 94% (leads) | 85% |
| Tool use | 78% (leads) | 78% |
| Time to first word | 0.8 s (leads) | 1.1 s |
| Response time | 3.8 s | 2.1 s (leads) |
| Barge-in handling | 100% (leads) | 96% |
| Cost per task | $0.15 (leads) | $0.24 |
The three strongest of each, averaged. Cascades: AssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Rime Coda; Speechmatics Linden-1 (own VAD) + OpenAI GPT-4.1 + Rime Coda; AssemblyAI Universal-3.6 Pro + Google Gemini 3.8 Flash + Rime Coda. Speech-to-speech: grok-voice-think-fast-2.0; gpt-live-1 (backend gpt-6-luna); grok-voice-3.0. 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 (grok-voice-3.0 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 12 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.
Roark score, best first
| # | |||||
|---|---|---|---|---|---|
| 1 | Universal-3.6 ProAssemblyAI | 90 / 100. Semantic word error rate 0.9%, 61.2 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points(among the best) | 0.9%(among the best) | 0.89 s(among the best) | $0.030 |
| 2 | Universal-3.5 ProAssemblyAI | 84 / 100. Semantic word error rate 1.1%, 55.7 of 71 points; Time to final transcript 0.90 s, 28.6 of 29 points(among the best) | 1.1%(among the best) | 0.90 s | $0.030 |
| 3 | Nova-3Deepgram | 82 / 100. Semantic word error rate 1.1%, 53.5 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points(among the best) | 1.1%(among the best) | 0.89 s(among the best) | $0.031 |
| 4 | Enhanced (realtime)Speechmatics | 82 / 100. Semantic word error rate 1.1%, 53.3 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points(among the best) | 1.1%(among the best) | 0.98 s | $0.054 |
| 5 | Linden-1Speechmatics | 79 / 100. Semantic word error rate 1.3%, 50.0 of 71 points; Time to final transcript 0.99 s, 28.6 of 29 points | 1.3% | 0.99 s | $0.020(among the best) |
| 6 | Nova-2Deepgram | 71 / 100. Semantic word error rate 1.5%, 42.2 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points | 1.5% | 0.89 s(among the best) | $0.023(among the best) |
| 7 | Standard (realtime)Speechmatics | 66 / 100. Semantic word error rate 1.7%, 37.5 of 71 points; Time to final transcript 0.96 s, 28.6 of 29 points | 1.7% | 0.96 s | $0.031 |
| 8 | Whisper-1OpenAI | 56 / 100. Semantic word error rate 1.4%, 45.5 of 71 points; Time to final transcript 1.93 s, 10.9 of 29 points | 1.4% | 1.93 s | $0.025 |
| 9 | Linden-1 (own VAD)Speechmatics | 52 / 100. Semantic word error rate 2.2%, 23.1 of 71 points; Time to final transcript 0.49 s, 28.6 of 29 points | 2.2% | 0.49 s(among the best) | $0.020(among the best) |
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 (77%) 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-4o: last on task completion (88%).
- 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 77% of calls, against 38% for OpenAI GPT-5.1.
- In 161 of 648 cascades the language model is the slowest step of the turn, whichever model runs it.
Roark score, best first
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6.1 SolOpenAI | 66 / 100. Task completion 95%, 27.0 of 36 points; Tool use 77%, 15.0 of 27 points; Instruction following 4.2 / 5, 11.3 of 18 points; Time to first token 0.97 s, 12.4 of 18 points(among the best) | 95%(among the best) | 4.2 / 5(among the best) | 77%(among the best) | 0.97 s | 73% | $0.019(among the best) |
| 2 | Claude Sonnet 5.5Anthropic | 61 / 100. Task completion 94%, 25.1 of 36 points; Tool use 72%, 11.8 of 27 points; Instruction following 4.2 / 5, 10.8 of 18 points; Time to first token 0.90 s, 13.3 of 18 points(among the best) | 94%(among the best) | 4.2 / 5(among the best) | 72%(among the best) | 0.90 s | – | $0.138 |
| 3 | Gemini 3.8 FlashGoogle | 51 / 100. Task completion 95%, 26.5 of 36 points; Tool use 62%, 6.7 of 27 points; Instruction following 4.2 / 5, 11.1 of 18 points; Time to first token 1.47 s, 6.4 of 18 points(among the best) | 95%(among the best) | 4.2 / 5(among the best) | 62%(among the best) | 1.47 s | – | $0.016(among the best) |
| 4 | GPT-4.1OpenAI | 50 / 100. Task completion 92%, 21.2 of 36 points; Tool use 48%, 0.0 of 27 points; Instruction following 4.2 / 5, 10.8 of 18 points; Time to first token 0.52 s, 18.0 of 18 points | 92% | 4.2 / 5(among the best) | 48% | 0.52 s | 82%(among the best) | $0.022 |
| 5 | Claude Haiku 4.5Anthropic | 49 / 100. Task completion 91%, 19.4 of 36 points; Tool use 47%, 0.0 of 27 points; Instruction following 4.2 / 5, 11.0 of 18 points; Time to first token 0.36 s, 18.2 of 18 points | 91% | 4.2 / 5(among the best) | 47% | 0.36 s(among the best) | – | $0.062 |
| 6 | GPT-4o miniOpenAI | 47 / 100. Task completion 90%, 17.4 of 36 points; Tool use 51%, 0.7 of 27 points; Instruction following 4.2 / 5, 10.8 of 18 points; Time to first token 0.45 s, 18.2 of 18 points | 90% | 4.2 / 5(among the best) | 51% | 0.45 s(among the best) | 81%(among the best) | $0.002(among the best) |
| 7 | GPT-5.1OpenAI | 44 / 100. Task completion 89%, 17.0 of 36 points; Tool use 38%, 0.0 of 27 points; Instruction following 4.1 / 5, 10.1 of 18 points; Time to first token 0.59 s, 17.1 of 18 points | 89% | 4.1 / 5 | 38% | 0.59 s | 74%(among the best) | $0.031 |
| 8 | GPT-4oOpenAI | 44 / 100. Task completion 88%, 15.0 of 36 points; Tool use 50%, 0.0 of 27 points; Instruction following 4.2 / 5, 10.9 of 18 points; Time to first token 0.45 s, 18.2 of 18 points | 88% | 4.2 / 5(among the best) | 50% | 0.45 s(among the best) | – | $0.027 |
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, ElevenLabs v4 Turbo and Cartesia Sonic-3.5 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).
Roark score, best first
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | Sonic-3.6Cartesia | 77 / 100. Readback accuracy 87%, 25.6 of 38 points; Word error rate 6.2%, 14.5 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 99%, 12.1 of 13 points(among the best) | 6.2% | 87%(among the best) | 3.8 / 5(among the best) | 99% | 0.12 s(among the best) | $0.168 |
| 2 | v4 TurboElevenLabs | 77 / 100. Readback accuracy 87%, 25.1 of 38 points; Word error rate 5.7%, 15.8 of 25 points; Time to first audio byte 0.11 s, 25.0 of 25 points; Voice consistency 98%, 11.2 of 13 points(among the best) | 5.7%(among the best) | 87%(among the best) | 3.6 / 5 | 98% | 0.11 s(among the best) | $0.470 |
| 3 | Sonic-3.5Cartesia | 77 / 100. Readback accuracy 86%, 24.6 of 38 points; Word error rate 6.2%, 14.6 of 25 points; Time to first audio byte 0.13 s, 25.0 of 25 points; Voice consistency 100%, 12.4 of 13 points(among the best) | 6.2% | 86%(among the best) | 3.8 / 5(among the best) | 100%(among the best) | 0.13 s | $0.165 |
| 4 | Sonic-3Cartesia | 73 / 100. Readback accuracy 85%, 23.3 of 38 points; Word error rate 6.9%, 12.8 of 25 points; Time to first audio byte 0.17 s, 25.0 of 25 points; Voice consistency 99%, 12.1 of 13 points | 6.9% | 85% | 3.4 / 5 | 99% | 0.17 s | $0.165 |
| 5 | Turbo v2.5ElevenLabs | 71 / 100. Readback accuracy 80%, 19.0 of 38 points; Word error rate 5.7%, 15.6 of 25 points; Time to first audio byte 0.15 s, 25.0 of 25 points; Voice consistency 98%, 11.5 of 13 points | 5.7%(among the best) | 80% | 3.4 / 5 | 98% | 0.15 s | $0.451 |
| 6 | Flash v2.5ElevenLabs | 70 / 100. Readback accuracy 80%, 18.5 of 38 points; Word error rate 6%, 14.9 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 98%, 11.5 of 13 points | 6%(among the best) | 80% | 3.4 / 5 | 98% | 0.12 s(among the best) | $0.437 |
| 7 | CodaRime | 68 / 100. Readback accuracy 83%, 21.7 of 38 points; Word error rate 8.1%, 9.8 of 25 points; Time to first audio byte 0.18 s, 25.0 of 25 points; Voice consistency 99%, 11.8 of 13 points | 8.1% | 83% | 3.7 / 5(among the best) | 99% | 0.18 s | $0.116(among the best) |
| 8 | TTS-1OpenAI | 55 / 100. Readback accuracy 82%, 21.0 of 38 points; Word error rate 6.1%, 14.8 of 25 points; Time to first audio byte 1.13 s, 7.1 of 25 points; Voice consistency 100%, 12.5 of 13 points | 6.1% | 82% | 3.6 / 5 | 100%(among the best) | 1.13 s | $0.036(among the best) |
| 9 | TTS-1 HDOpenAI | 39 / 100. Readback accuracy 80%, 18.3 of 38 points; Word error rate 8.7%, 8.4 of 25 points; Time to first audio byte 2.09 s, 0.0 of 25 points; Voice consistency 100%, 12.4 of 13 points | 8.7% | 80% | 3.6 / 5 | 100%(among the best) | 2.09 s | $0.065(among the best) |
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: xAI Grok Voice 3.0 completes 87% of tasks, ElevenLabs Realtime v1 Mini 42%.
- xAI Grok Voice 3.0 answers in 1.9 s against 4.2 s for Google Gemini 2.5 Flash native audio.
- Price varies as much as quality: $0.06 per completed task for Amazon Nova 2 Sonic, $0.69 for OpenAI GPT Realtime 2.
Roark score, best first
Whiskers show the 95% interval. The shaded models tie for first: these calls cannot separate them.
| # | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1= (tied) | GPT Live 1 (Sol)OpenAI | 65 / 100±3.8. Task completion 85%, 6.0 of 23 points; Response time 2.3 s, 16.6 of 18 points; Instruction following 4.2 / 5, 8.2 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 87%, 10.2 of 14 points; Time to first word 1.4 s, 3.9 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best) | 85%(among the best) | 4.2 / 5 | 87%(among the best) | 2.3 s(among the best) | 1.4 s | 77% | 3.1 / 5 | 100%(among the best) | $0.24 |
| 2= (tied) | Grok Voice 3.0xAI | 66 / 100±4.7. Task completion 87%, 8.0 of 23 points; Response time 1.9 s, 18.2 of 18 points; Instruction following 4.5 / 5, 10.5 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 66%, 4.4 of 14 points; Time to first word 0.9 s, 4.5 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best) | 87%(among the best) | 4.5 / 5(among the best) | 66% | 1.9 s(among the best) | 0.9 s | 94% | 3.0 / 5 | 100%(among the best) | $0.26 |
| 3= (tied) | GPT Live 1 (Luna)OpenAI | 65 / 100±3.5. Task completion 85%, 5.7 of 23 points; Response time 2.3 s, 16.6 of 18 points; Instruction following 4.2 / 5, 8.4 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 86%, 9.9 of 14 points; Time to first word 1.5 s, 3.8 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best) | 85%(among the best) | 4.2 / 5 | 86%(among the best) | 2.3 s(among the best) | 1.5 s | 93% | 3.1 / 5 | 100%(among the best) | $0.21 |
| 4= (tied) | Grok Voice Think Fast 2.0xAI | 65 / 100±3.7. Task completion 82%, 2.8 of 23 points; Response time 2.2 s, 17.4 of 18 points; Instruction following 4.6 / 5, 10.7 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 82%, 8.6 of 14 points; Time to first word 0.9 s, 4.5 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best) | 82% | 4.6 / 5(among the best) | 82%(among the best) | 2.2 s(among the best) | 0.9 s | 100%(among the best) | 3.6 / 5 | 100%(among the best) | $0.26 |
| 5= (tied) | Gemini 3.8 LiveGoogle | 53 / 100±4.8. Task completion 78%, 0.0 of 23 points; Response time 2.8 s, 14.6 of 18 points; Instruction following 4.3 / 5, 8.7 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 69%, 5.2 of 14 points; Time to first word 1.6 s, 3.6 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 78% | 4.3 / 5(among the best) | 69% | 2.8 s | 1.6 s | 100%(among the best) | 4.1 / 5(among the best) | 100%(among the best) | $0.14(among the best) |
| 6= (tied) | GPT Realtime 2.1OpenAI | 53 / 100±5.7. Task completion 78%, 0.0 of 23 points; Response time 2.6 s, 15.6 of 18 points; Instruction following 3.8 / 5, 5.6 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 75%, 6.8 of 14 points; Time to first word 0.8 s, 4.5 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 99%, 4.3 of 5 points | 78% | 3.8 / 5 | 75% | 2.6 s | 0.8 s(among the best) | 83% | 3.9 / 5(among the best) | 99% | $0.43 |
| 7= (tied) | Ultravox v0.7Ultravox | 48 / 100±5.0. Task completion 79%, 0.0 of 23 points; Response time 2.4 s, 16.2 of 18 points; Instruction following 3.7 / 5, 4.9 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 61%, 3.0 of 14 points; Time to first word 1.6 s, 3.6 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 79% | 3.7 / 5 | 61% | 2.4 s | 1.6 s | 94% | 3.6 / 5 | 100%(among the best) | $0.22 |
| 8= (tied) | Gemini 3.1 Flash Live (preview)Google | 48 / 100±5.1. Task completion 80%, 0.0 of 23 points; Response time 2.7 s, 15.1 of 18 points; Instruction following 4.2 / 5, 8.0 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 38%, 0.0 of 14 points; Time to first word 1.5 s, 3.8 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 80% | 4.2 / 5 | 38% | 2.7 s | 1.5 s | 100%(among the best) | 4.0 / 5(among the best) | 100%(among the best) | $0.15 |
| 9= (tied) | GPT Realtime 2OpenAI | 48 / 100±6.7. Task completion 76%, 0.0 of 23 points; Response time 2.9 s, 14.0 of 18 points; Instruction following 3.8 / 5, 5.4 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 64%, 3.7 of 14 points; Time to first word 0.8 s, 4.5 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 76% | 3.8 / 5 | 64% | 2.9 s | 0.8 s(among the best) | 91% | 3.7 / 5 | 100%(among the best) | $0.69 |
| 10= (tied) | Nova 2 SonicAmazon | 46 / 100±5.1. Task completion 69%, 0.0 of 23 points; Response time 3.0 s, 13.8 of 18 points; Instruction following 4.2 / 5, 7.9 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 48%, 0.0 of 14 points; Time to first word 1.5 s, 3.7 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 69% | 4.2 / 5 | 48% | 3.0 s | 1.5 s | 100%(among the best) | 3.5 / 5 | 100%(among the best) | $0.06(among the best) |
| 11= (tied) | Realtime v1 MaxElevenLabs | 47 / 100±7.5. Task completion 56%, 0.0 of 23 points; Response time 2.6 s, 15.6 of 18 points; Instruction following 4.0 / 5, 6.7 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 40%, 0.0 of 14 points; Time to first word 0.7 s, 4.5 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 56% | 4.0 / 5 | 40% | 2.6 s | 0.7 s(among the best) | 76% | 3.9 / 5(among the best) | 100%(among the best) | $0.65 |
| 12= (tied) | Realtime v1 MiniElevenLabs | 45 / 100±7.1. Task completion 42%, 0.0 of 23 points; Response time 2.7 s, 15.1 of 18 points; Instruction following 3.8 / 5, 5.1 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 34%, 0.0 of 14 points; Time to first word 0.7 s, 4.5 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 42% | 3.8 / 5 | 34% | 2.7 s | 0.7 s(among the best) | 94% | 3.4 / 5 | 100%(among the best) | $0.64 |
| 13= (tied) | GPT Realtime 2.1 miniOpenAI | 44 / 100±6.7. Task completion 70%, 0.0 of 23 points; Response time 2.8 s, 14.5 of 18 points; Instruction following 3.6 / 5, 4.4 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 51%, 0.3 of 14 points; Time to first word 1.0 s, 4.5 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 70% | 3.6 / 5 | 51% | 2.8 s | 1.0 s | 84% | 3.9 / 5(among the best) | 100%(among the best) | $0.14(among the best) |
| 14 | Gemini 2.5 Flash native audioGoogle | 36 / 100±5.4. Task completion 77%, 0.0 of 23 points; Response time 4.2 s, 8.2 of 18 points; Instruction following 3.9 / 5, 6.2 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.6 of 14 points; Tool use 40%, 0.0 of 14 points; Time to first word 3.4 s, 0.9 of 5 points; Readback accuracy 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points | 77% | 3.9 / 5 | 40% | 4.2 s | 3.4 s | 100%(among the best) | 3.7 / 5 | 100%(among the best) | $0.08(among the best) |
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.
Roark score, top 15
Whiskers show the 95% interval. The shaded stacks tie for first: these calls cannot separate 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. 85 stacks are level with the leader: their calls cannot tell them apart. Among them, 36 OpenAI GPT-6.1 Sol, 22 Anthropic Claude Sonnet 5.5, 19 Google Gemini 3.8 Flash, 4 speech-to-speech, 3 Anthropic Claude Haiku 4.5 and 1 OpenAI GPT-4o mini; 42 AssemblyAI, 20 Deepgram and 19 Speechmatics; 37 Cartesia, 36 ElevenLabs, 7 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 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. Each row reads across: the main board's figure first, then every industry's on the same figure.
No stack matches these filters.
No stack matches
Each industry column is that industry's own board, every row it ranks. A dash is a row the industry does not rank on this figure; the arrow beside an industry opens its full board.
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.
656
stacks
20
calls per stack
13,956
calls scored
Every model, in every combination
9 transcribers, 8 language models and 9 voices are run in every combination with each other, beside 14 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 and kept one steady voice, and whether its tools were handled. How human a voice sounds is shown on the boards and not scored. 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, best value and best speech-to-speech picks, and the best stack in each industry, are each the one 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 by score, so the pick can sit below a higher score it cannot be told from, and its reason says how many stacks are level with it.
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 | 23% | 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 | 18% | 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 | 14% | 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 | 14% | 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 | 14% | 100% | 50% |
| An agent that mishandles its tools on half its calls cannot be trusted with the systems it runs on. | |||
Time to first wordtime_to_first_word | 5% | 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 | 5% | 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 | 5% | 2% | 12% |
| At 2% the voice says what it was given; at 12% one word in eight comes out wrong. | |||
Voice consistencyvoice_consistency_check | 5% | 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, Human-likenessvoice_human_likeness
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 | 38% | 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 | 25% | 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 | 25% | 0.20 s | 1.50 s |
| Under 0.2 s is not noticeable; 1.5 s is half the point where calls go worse. | |||
Voice consistencyvoice_consistency_check | 13% | 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: Human-likenessvoice_human_likeness
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, 30 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
#106of 655 stacks
53 / 100
Leader AssemblyAI Universal-3.5 Pro + OpenAI GPT-6.1 Sol + ElevenLabs Turbo v2.5, 70 / 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.
#400 of 662 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#100 of 662 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#13 of 662 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.
#1 of 347 on the board · best 100%
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 662 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#290 of 662 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 662 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 494 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.
#574 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.
#559 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.
#421 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.
#476 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.
#205 of 660 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 660 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.
#239 of 661 on the board · best 1.85 s
Time to first word
How long the caller waits before the agent first speaks after pickup.
#350 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#225 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 98% | 3.82 s | — |
| Home services | 83% | 3.42 s | — |
| Insurance | 87% | 3.21 s | — |
| Customer support | 95% | 3.44 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 3.45 s | — |
| Spanish-accented English, city street | 96% | 3.63 s | — |
| Indian English, busy café | 87% | 3.29 s | — |
| Southern US, flustered, crying baby | 98% | 3.97 s | — |
| Fast and interrupting, construction outside | 78% | 3.25 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, uh, so my internet's been down for about 2 hours now, and I work from home, so it's, you know, kind of urgent. There's a road crew digging up the street outside, and I was wondering if that might be the cause? I already rebooted the gateway twice and checked all the cables, but the internet light's blinking orange. Can you help me figure out what's going on?
AGENTWe can definitely dig into this. The road work could be related, but I’ll confirm what’s actually going on with your line. First, I need to pull up your account and check for any area outage. Please give me either: - Your Brightwave account number, or. - The phone number on the account. Once I have that, I’ll: 1. Check for any outage at your address. 2. If there’s no outage, run a line test to your gateway and see what the dig crew might have hit.
CUSTOMEROkay, uh, sorry, I've got the account number right here. It's BW883017— wait, sorry, last digit is 1. Is that enough for you? And just to be sure, can you tell me if the road crew could have knocked something loose or cut a line?
AGENTYes, the road crew absolutely could have caused an issue—if they hit or disturbed the line in the street, it can knock whole houses or parts of the block offline. In your case, though, that doesn’t look like what’s happening. I’ve got your account pulled up under BW8830171, and here’s what I’m seeing: - No area outage at your address. - Your line signal from the network looks good. - Your gateway had fallen into a “not registered” state, which matches the blinking orange light. - I just sent a remote reset to your Brightwave BX7, and it’s now showing as registered and online on my end. Your devices may take about 2 minutes to fully reconnect. Can you check for me, right now: 1. Is the internet/online light on the gateway solid now (not blinking orange)? 2. Can you get a page to load on your work laptop or phone (maybe try a non-work site like news or search to be sure)? If it’s still blinking or you can’t get online after a couple of minutes, tell me what the lights look like on the gateway and I’ll take the next step.
CUSTOMEROkay, uh, the light just went solid white now, so I— I think it's back up. How long until my devices reconnect? Should I wait for them, or is there something else I need to do? I'm still a little anxious, so I just want to make sure everything's good before I try working again. And, uh, since I lost 2 hours of work, can I get a credit for the downtime?
AGENTYou’re in good shape now—the solid white light means the connection is back and stable. Here’s what to expect and what to do: 1. Device reconnect timing. - Most devices will reconnect within 1–3 minutes after the gateway comes fully online. - Some work laptops/phones may take a bit longer if they were trying and failing repeatedly. 2. What you should do. - On your main work device, if it doesn’t reconnect on its own within a minute: - Turn Wi‑Fi off and back on, or unplug/replug the Ethernet cable if it’s wired. - If needed, “Forget” the Wi‑Fi network and reconnect by entering the Wi‑Fi password again. - You don’t need to reboot the gateway again—just let it run now that it’s solid white. 3. Quick sanity check
CUSTOMERSure, I'll try that. Just to double-check, if it doesn't come back right away, I'll switch Wi-Fi off and on or replug the cable. I don't need to restart the gateway again, right? Sorry, I just want to make sure I don't miss mess anything up. And about that credit for the downtime, can you tell me what you can offer?
AGENTYou’ve got it right: - If a device doesn’t come back right away, toggle Wi‑Fi off/on or replug the Ethernet cable. - You do not need to restart the gateway again—the solid white light means it’s already fully online and stable. Rebooting it now would just slow you down. On the credit: - I’ve applied a $10.00 service credit for the 2 hours of downtime to your account BW8830171. - You’ll see that credit on your next bill. If anything seems off once you start working again—pages slow to load, VPN dropping, or the light changing from solid white—tell me exactly what you see and I’ll dig back in.
CUSTOMERAny way you could make the credit a little more? I lost 2 hours of work, so $10 doesn't really cover it. Sorry if I'm being a bother, but I'd really appreciate it if you could bump it up a bit.
AGENTYou’re not a bother at all for asking; I get why you’re frustrated if you lost billable time. I do need to be straight with you: I can only apply the standard service credit that the system allows for this type/length of outage, and that’s the $10 I already added to account BW8830171. I don’t have the ability to increase that amount from here. If you want to push for more than that, the options are: - Contact our billing team via phone or chat and explain the impact on your work; they have more discretion than I do. - If this becomes a recurring issue, we can document the pattern on your account, which often helps when billing reviews larger adjustments. For now, you’re credited $10.00 on BW8830171, and it will show on your next bill. Before you jump back into work, do you want to quickly confirm: - Your main work device is online and loading sites normally? - Any VPN or remote desktop you use can connect without dropping?
CUSTOMERThanks for being straight with me. I'll check my laptop now and see if it's back online. I appreciate your help, and I'll reach out to billing if it happens again. Okay, I think that's everything. Have a good day.
AGENTYou’re all set on my end—your connection looks stable and the $10.00 credit is on account BW8830171 and will show on your next bill. If the laptop gives you any trouble (sites not loading, VPN flaky, light changing from solid white), just reach back out and mention the road work and that the gateway had to be re-registered so we can pick up quickly. Hope the rest of your workday goes smoothly.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, uh, this is Lucia Ramirez. I have a dermatology appointment next Wednesday morning, but I need to move it because I have a work system. Could you help me reschedule? I can only come after 3 PM.
AGENTI can help with that. To get started, I need to verify your account. Please tell me: - Your full name as it appears on your records (just to confirm), and. - Your date of birth (YYYY-MM-DD). Then I’ll look up your dermatology appointment for next Wednesday and find options after 3 PM.
CUSTOMERSure, my full name is Lucia Ramirez. My date of birth is March 17th, 1948. Sorry, no, 1984. March 17th, 1984.
AGENTThanks, Ms. Ramirez. I have you verified with date of birth March 17, 1984. I see your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at Main Campus, Building B. You mentioned you can only come after 3 PM. Here are the available options with Dr. Okafor starting next week that meet that: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. There’s also a Friday 11:30 AM slot, which is too early based on what you told me, but I can offer it if your availability changes. Which of these would you like to move your appointment to: Tuesday at 3:45,
CUSTOMERHmm, Tuesdays actually do not work after all. I pick up my daughter then. What about Friday? Is there anything later? If not, Thursday at 4:10 PM would be okay.
AGENTRight now, the only Friday slot I’m seeing with Dr. Okafor is 11:30 AM, so nothing later that day is available.
CUSTOMEROkay, I'll take Thursday at 4:10 PM then. Can you confirm if there is a fee for changing the appointment?
AGENTI’ve moved your dermatology visit with Dr. Okafor to 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. Regarding fees: the clinic’s policy is that changes
CUSTOMERAnd where should I park for the appointment?
AGENTFor your appointment, you can use the free patient parking in Lot C. The entrance to Lot C is on River Road.
CUSTOMERThat's right. And does Dr. Okafor accept Aetna insurance?
AGENTI don’t have access
CUSTOMEROkay, could you check if Dr. Okafor accepts Aetna insurance for dermatology appointments?
AGENTI don’t have access to our insurance panel or billing system from here, so I can’t reliably see which specific plans Dr. Okafor is in‑network with, including Aetna. To get an accurate answer, you have two good options: 1. Call the clinic’s front desk/billing directly. Ask: “Does Dr. Okafor accept my specific Aetna plan for dermatology visits?” They can check by: -
CUSTOMERAll right, thanks for explaining. So just to confirm, my new appointment is Thursday at 4:10 PM, Main Campus, Building B, and the confirmation code is R. Is that correct?
AGENTAlmost—let me restate it clearly so we have it correct together. Your rescheduled appointment is: - Day: Thursday. - Time: 4:10 PM. - Location: Main Campus, Building B. - Confirmation code: RVB-3M8P2 (not just “R”). Please make sure you have the full code RVB-3M8P2 written down.
CUSTOMERYes, that's right. I have it written down. RVB-3M8P2. Thank you for your help. Goodbye.
AGENTYou’re all set, Ms.
AGENTRamirez—Thursday at 4:10 PM, Main Campus Building B, with confirmation code RVB-3M8P2. Take care, and goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, yeah, I've got a burst pipe under my kitchen sink. Water is spreading across the floor and heading toward a power strip. I haven't shut the water off yet. Can you help?
AGENTYes, I can help right away. First, let’s keep you safe
CUSTOMEROkay.
CUSTOMERAll right, go ahead.
AGENTThanks for hanging on. Let’s handle safety first, then I’ll get someone booked. 1) Immediate safety steps (please do these now): - Stay away from that power strip and any outlets near the water. Don’t touch the strip or any cords. - If you can do this without stepping in water, go ahead and unplug the power strip from the wall by the plug, not the cord. - If the plug or outlet is already in the water or you’d have to stand in water to reach it, do not touch it. Just keep everyone away from that area. - Next, we need to shut off the water: - Look under the kitchen sink for two small shutoff valves (one for hot, one for cold) on the pipes going up to the faucet. Turn both clockwise until they stop. - If those aren’t there or won’t turn, do you know where your main water shutoff is? Common spots are: - In the basement near the front wall. - In a utility room near the water heater. - In a ground‑level closet or near where the water line enters the house. - If you know where it is, turn the main valve clockwise (or pull the lever so it’s **crosswise to the pipe**) to shut the water off to the whole house. Please tell me: - Are you able to reach the power strip plug without standing in water? - And do you see the shutoff valves under the sink or know where the main shutoff is? Once I know you’re safe and the water is at least slowing or off, I’ll open an emergency ticket and book the earliest available plumber.
CUSTOMERYeah, I can reach the power strip plug without standing in water, so I'll unplug it now. I see the shutoff valves under the sink. Turning them now. Okay, the water has stopped.
AGENTGood job getting the water stopped and unplugging that strip—that’s exactly what we needed. You’re already in our system, so I’ve gone ahead and set this up as an emergency visit. Here’s what I’ve done and what to expect: - Service request opened: Burst pipe under kitchen sink, water spread across floor toward a power strip. Water is now off at the under‑sink valves. - Service address on file: 1480 Larkspur Avenue, Unit 4B. - Ticket number: CPL-58210. - Arrival window: today, 2:00 PM to 4:00 PM (emergency slot). - Your membership: Copperline Care member. - Emergency call-out fee for you: $99 (Copperline Care emergency rate). - Any additional work or parts will be quoted on site before we proceed. Before I lock this in, can you please confirm a couple of details: 1. Is 1480 Larkspur Avenue, Unit 4B the correct service address, and is there any gate code or special access info we should note? 2. What’s the best callback number for you for updates and the 30‑minute arrival text? While you’re waiting: - Keep the sink area clear so the tech can get right under there. - You can towel up or mop any standing water on the floor, but avoid using any electrical devices near where the water was. Once you confirm the address/access and callback number, I’ll read everything back to you including the ticket number so you have it handy.
CUSTOMERActually, I moved from Unit 4B to Unit 4D last month, so it should be 1480 Larkspur Avenue, Unit 4D. The gate code is #2. For callback, use 503-555-0139— no, 0193.
AGENTThanks for the corrections—let me read everything back so we’re set, and I’ll confirm the fee before we go any further. Here’s what I have now: - Service address: 1480 Larkspur Avenue, Unit 4D. - Gate/access info: Gate code #2. - Callback number: 503-555-0193. - Issue: Burst pipe under kitchen sink; water spread across floor toward a power strip. You’ve unplugged the strip and shut the under-sink valves; water is stopped. - Ticket number: CPL-58210. - Priority: Emergency. - Arrival window: today, 2:00 PM to 4:00 PM. You’re a Copperline Care member, so your emergency call-out fee for today is $99. Any repair costs and parts will be discussed and approved with you on site before we proceed. Can you please confirm you agree to the $99 emergency call-out fee for today’s 2:00–4:00 PM arrival at 1480 Larkspur Avenue, Unit 4D, gate code #2, with callbacks to 503-555-0193? Once you say yes, you’ll be all set and our technician will text you about 30 minutes before arrival.
CUSTOMERYes, that's exactly right. I agree to the $99 emergency call-out fee for today, and the address, gate code, and callback number are correct. Can anyone come before 2:00 PM? PM, or is the 2 to 4 window the soonest? Also, who will be coming out, and how will I know they're on the way? And can you confirm the ticket number, CPL-58210?
AGENTThe 2:00–4:00 PM emergency window is the earliest we have today—that’s the soonest we can get someone to you. Here’s what’s set and how it will work: - Ticket number: Confirmed — CPL-58210. - Arrival window: Today, 2:00 PM to 4:00 PM (earliest available emergency slot). - Who’s coming: One of our licensed plumbers from Copperline Home Services. Our system doesn’t provide me a specific name I can share in advance, but it will be one of our on‑call emergency techs. - How you’ll know they’re on the way: - You’ll get a text to 503-555-0193 about 30 minutes before arrival. - The tech will arrive at 1480 Larkspur Avenue, Unit 4D, using gate code #2. While you’re waiting, you’re safe to: - Leave the under‑sink valves closed. - Mop or towel up any remaining water on the floor. - Keep the area under the sink as clear as possible for the tech. If anything changes (like the leak starts again or you notice any electrical burning smell or sparks), stay clear of the area and tell me right away so we can update the notes for the technician.
CUSTOMERUnderstood. I'll keep the area clear, mop up any water, and let you know if anything changes or if I notice anything unusual. Thanks for your help, and goodbye.
AGENTYou’re all set for today’s 2:00–4:00
AGENTPM emergency visit under ticket CPL-58210 at 1480 Larkspur Avenue, Unit 4D, gate code #2, with callbacks/texts to 503-555-0193. If anything at all changes with the leak or you notice anything electrical acting odd, call us right away. Take care, and goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERUh, yeah, I think so. I'm just at home, but my baby's crying and I'm a little flustered. I'm standing next to my car. It's not drivable because the back bumper's cracked. crushed and the rear wheels rubbing. Nobody got hurt, thankfully. Sorry, is that okay?
AGENTI’m glad nobody’s hurt—that’s the most important thing. If you need to pick up or soothe your baby at any point, that’s absolutely okay; we can pause whenever you need. Since no one is injured and you’re safe, we’ll go ahead and start your claim and also look at getting a tow, since the car doesn’t sound drivable. First, I’ll need to pull up your policy. 1. What’s your auto policy number? 2. And the policyholder’s last name?
CUSTOMERMy policy number is
CUSTOMERNG4471903.
CUSTOMEROh wait, sorry, the last one is 2. NG4471902. And the last name is Carter. Is that all right?
AGENTThanks for that update, Ms. Carter, and yes—that’s all right. I’ve now verified your policy as: - Policy number: NG4471902. - Vehicle: 2021 Honda CR‑V. Let’s get the accident details so I can open your claim and then we’ll arrange a tow, since the car doesn’t sound safe to drive. 1. When did the accident happen? 2. Where did it happen? 3. What happened? Just a brief description in your own words. 4. Did another vehicle or driver hit you? If yes: - The other driver’s name (if you have it). - Their insurance company (if known). - Their license plate number. 5. Did the police come out, and is there a police report number? Also, since the rear wheel is rubbing, we should plan a tow: 6. Where is the vehicle right now (your home address or exact location)? 7. What’s the best phone number for the tow driver to reach you?
CUSTOMERI'll try to go through all that.
CUSTOMERI'm a little flustered, but here goes. The accident happened about 20 minutes ago. It was at SE 5th Avenue and Alder Street. 3. I was stopped at a red red light and another car hit the back of mine. The bumper's crushed and the rear wheel rubs, so I can't drive it. 4. Yes, the other driver hit me. His name is Kevin Lund. His insurance company is Pacific Shore. His license plate is 7KX, like x-ray, R214. 5. The police did not come, so So there's no police report. 6. The vehicle is at my home right here. 7. The best phone number is 618-582-8130. Is that everything you need? Sorry if I missed something.
AGENTYou did great, and you gave me everything I need—thank you for hanging in there, especially with a crying baby and after a scare like that. Let me read a few key things back to you: - Policy number I have for you: NG4471902. - Other driver’s license plate: 7KXR214. If either of those is not right, tell me and I’ll fix it. I’ve opened your claim with this information: - You were stopped at a red light at SE 5th Avenue and Alder Street. - You were rear‑ended by Kevin Lund, insured with Pacific Shore. - No injuries and no police report. - Your 2021 Honda CR‑V has a crushed rear bumper and the rear wheel is rubbing, so it’s not drivable. - The car is now at your home. Your claim is open: - Claim number: NGM-904417. - Assigned adjuster: Priya Shah. - You’ll hear from your adjuster within one business day. For the tow: - I’ve arranged a tow through Eastside Towing. - They’re coming to your home. - They’ll call you at 618-582-8130. - Estimated time of arrival: about 45 minutes. - They’ll take the car to a Northgate partner repair shop at 9th and Morrison. While you’re waiting, you don’t need to do anything else with the car—just keep it where it is and have your keys and ID handy for the tow driver. Do you want me to check your policy’s coverage details next—like towing, rental car, and collision deductible?
CUSTOMERYeah, please. I'm worried about how much I'll have to pay. And if he hit me, I shouldn't have to pay the deductible, right? Also, will I get a rental car, and is my premium going to go up because of this? Sorry, I just want to make sure I understand everything.
AGENTHere’s what your policy shows, and I’ll keep it as simple and clear as I can. First, your coverage details. - Collision deductible: $500. - Rental coverage: $40 per day, up to 30 days, starting today (the day the claim was opened). - Towing: Covered up to 25 miles. So today’s tow to the partner shop is within your towing coverage. About the deductible and who pays. Because you were rear‑ended while stopped at a red light, it sounds like the other driver may be at fault. But Northgate can’t officially decide that on this call—that’s up to your adjuster after they review the facts and talk with Pacific Shore. How the deductible usually works in a situation like this: - If we repair your car under your collision coverage, you are responsible for the $500 deductible up front. - If the other driver is found at fault and their insurer pays us back, your adjuster will work on getting your deductible reimbursed to you. - If, for some reason, the other insurer doesn’t accept fault or there’s a dispute, you may end up paying the deductible and not getting it back. Your adjuster, Priya Shah, will walk you through exactly how this plays out once she has all the information. Rental car. - You have rental coverage at $40 per day, up to 30 days, starting today. - Your adjuster will help set this up—either by direct billing with a rental company or by explaining how reimbursement works if you book it yourself. - If the other driver’s insurer accepts full responsibility quickly, they may also offer a rental. Your adjuster will tell you which option is best so you’re not paying out of pocket unnecessarily. Will your premium go up? I’m not able to see or predict premium changes or renewal pricing on this system. What I can say is: - A not‑at‑fault rear‑end accident is often treated differently from an at‑fault accident, but rating decisions vary by state and by company rules. - Your adjuster or a billing/agent representative can go over how this claim might affect your policy once more is known about fault and payments. What happens next. - Claim number: NGM-904417. - Adjuster: Priya Shah. - You should hear from Priya within one business day. She’ll: - Confirm fault and next steps with Pacific Shore. - Go over your deductible in your specific situation. - Help you with the rental car setup. - Coordinate the repair process with the shop. You’ve already done the hard part by getting the claim started and the tow arranged. While you’ve got me: - Is the policy number I have still NG4471902? - And the other driver’s plate still 7KXR214? If anything there is off, I’ll correct it now. After that, I can walk you through what to expect when the tow truck arrives, if that would help you feel more prepared.
CUSTOMERYeah, I think that's right. Please tell me those are the ones you have. I just want to make sure nothing gets lost. And, uh, I'd appreciate if you could tell me what happens when the tow truck gets here. I'm still a little anxious about all this.