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
#326of 655 stacks
48 / 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.
#549 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.
#1 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.
#233 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.
#301 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.
#533 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.
#540 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.
#474 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.
#655 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.
#282 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.
#422 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#346 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 3.56 s | — |
| Home services | 85% | 3.35 s | — |
| Insurance | 97% | 3.40 s | — |
| Customer support | 78% | 3.94 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 85% | 3.83 s | — |
| Spanish-accented English, city street | 100% | 3.54 s | — |
| Indian English, busy café | 87% | 3.29 s | — |
| Southern US, flustered, crying baby | 98% | 4.00 s | — |
| Fast and interrupting, construction outside | 80% | 3.28 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERYeah. Alex, Sorry. I'm kinda flustered. My baby's crying in the background, so I hope you can hear me okay. My Internet's been down for two hours now. I work from home, so this is, pretty urgent for me. There's a road crew out front digging up the street. And I'm worried that might be the cause. I already rebooted the gateway twice and checked every cable. But the Internet light's blinking orange. Can you help me figure out what's going on?
AGENTI can hear you fine, and we’ll move fast so you can get back to the baby and work. First, I need to pull up your account and check for any outage before we do anything else. Please give me either:
- Your Brightwave account number, or - The phone number on the account.
CUSTOMEROh, sure. I think my account number is BW883017. Wait. Sorry. Last digit is one. Can you check if that's right? My phone number is (907) 416-9251. If that helps. Is that okay?
AGENTThanks, and yes—that account number is BW8830171, and I’ve got your Brightwave 500 plan pulled up. Here’s what I’m seeing and what I’ve done:
- No area outage at your address. - The line test showed your gateway wasn’t registered correctly. - I just sent a remote reset to your Brightwave BX7, and it’s now showing as registered and online on my side. Your Wi‑Fi and wired devices may take about 2 minutes to fully reconnect. Can you do a quick check for me (when you have a free second between baby duties)
1. Look at the gatewayis the Internet light solid now (not blinking orange)? 2. Try loading a webpage or reconnecting your work laptop/phone. If it’s still blinking or you can’t get online after a couple of minutes, tell me what the light is doing and whether it’s all devices or just one, and we’ll go to the next step.
CUSTOMEROkay. Hang on. Just looked at the gateway. The light went solid white. So it's not blinking orange anymore. That's good. Right? How long does it usually take for my devices to reconnect? I just wanna make sure everything's back up because I lost two hours hours of work. Can I get a credit for the downtime?
AGENTSolid white is exactly what we want—that means the gateway is online and registered now. On the devices:
- Most should reconnect within 1–3 minutes. - If anything doesn’t, just toggle Wi‑Fi off/on or disconnect/reconnect to your Wi‑Fi network on that device. About the downtime and credit
- I’ve added a $10.00 service credit for the roughly two hours you were down. - It will show on your next bill. Reading that backa $10.00 credit has been applied to account BW8830171 and will appear on your next statement. If you want, I can stay with you while you quickly test one device (like your work laptop or phone) to confirm you’re fully back online.
CUSTOMER$1,000? Are you sure that's right? I mean, I lost two hours of work. So can you make it more than that? I just wanna be sure it's fair since this really messed up my day. And, yeah, I'll check my laptop right now. Just wanna be sure it's working.
AGENTIt’s $10, not $1,000—sorry if that came across unclear. Let me read it back cleanly: I applied a ten‑dollar credit ($10.00) to account BW8830171, and it will appear on your next bill. On increasing it: for a short interruption like about two hours that we could fix remotely, $10 is the standard maximum I’m allowed to apply on this call. I don’t have the ability to go higher myself. If you feel that still doesn’t cover the impact to your workday, you can contact Customer Care via chat or phone from your Brightwave account portal—they can review your history and see if anything additional is possible. While you’ve got your laptop open, can you tell me: - Does a website like example.com or google.com load normally? - And are any work apps (VPN, email, or video calls) connecting okay? If anything’s slow or failing, tell me exactly what you see (error message or spinner), and we’ll tackle that next.
CUSTOMEROkay. Sorry. I got confused there. So it's just $10. I guess that's better than nothing. But I really hoped it'd be more since I lost two hours of work. I'll check with customer care if I need more. Just checked Google. It loads fine now. Work apps are coming back. Looks like everything's working. Thanks for getting me back online so quick.
CUSTOMERAppreciate it. Goodbye.
AGENTYou’re welcome—glad
AGENTeverything’s back up and your work apps are loading again. Quick recap before you go: - Your gateway is online with a solid white light. - A $10.00 credit has been applied to account BW8830171 and will appear on your next bill. If anything acts up again—especially with that road crew still out front—contact us right away and mention today’s issue so we can pick up where we left off. Take care, and good luck with the baby and work.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi. This is Jordan Ellis. Need to reschedule my dermatology appointment next Wednesday morning. I just got assigned a work shift during that time, so I can only come after 3PM. Could you help me move it?
AGENTI can help with that. I’ll just need to verify your record first. Please provide:
1) Your full name as it appears on your ID (I heard “Jordan Ellis,” please confirm), and 2) Your date of birth (YYYY-MM-DD).
CUSTOMERYes. My full name is Jordan Ellis. My date of birth is 03/17/1948. Sorry. No. 1984. 03/17/1984.
AGENTYou’re verified, thank you, Jordan. I see your dermatology visit with Dr. Okafor next Wednesday at 9:15 AM on Main Campus, Building B. Looking at Dr. Okafor’s schedule from next Wednesday onward, I have these options that fit your “after 3 PM” requirement:
- Tuesday at 345 PM - Thursday at 4:10 PM Friday’s opening is 11:30 AM, which is before 3 PM, so that won’t work based on what you told me. Which of these would you like to move your appointment to: Tuesday at 3:45 PM or Thursday at 4:10 PM?
CUSTOMERTuesdays don't work after all. Since I pick up my daughter. What about Friday? Is there anything available after 3PM on Friday? If not, I'll take Thursday at 04:10PM.
AGENTI checked Friday for you—unfortunately, the only opening with Dr. Okafor is at 11:30 AM, nothing after 3 PM. I’ve gone ahead and moved your dermatology appointment to Thursday at 4:10 PM with Dr. Okafor at Main Campus, Building B. Here are the details to confirm:
- NameJordan Ellis - Date of birth: 03/17/1984 - New appointment: Thursday at 4:10 PM, Dermatology with Dr. Okafor - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2 Arrival instructions: Please arrive 15 minutes early with a photo ID and your insurance card. Would you like me to repeat or email these details through the address we have on file?
CUSTOMERNo need to repeat or email. That's all clear. Before we wrap up, could you tell me if there's a fee for changing the appointment?
AGENTThere’s no fee for the change we just made. The clinic’s policy is: changes made more than 24 hours before the appointment are free; changes within 24 hours of the appointment have a $40 fee. Since you rescheduled well in advance of next Thursday, there’s no charge. Anything else you’d like to check while you’re here—hours, parking, or anything about the visit itself?
CUSTOMERYes. Where should I park when I come for the appointment? Is there a specific lot or any instructions I should know?
AGENTFor your appointment at the Main Campus, Building B: - Parking is in Lot C - It’s free for patients - The entrance to Lot C is off River Road Once you park, just follow the signs for Building B / Dermatology and plan to be there about 15 minutes early.
CUSTOMERGot it. Lot C Off River Road. Is doctor Okafur in network with Aetna insurance? And just to confirm, could you read back the new appointment time and the confirmation code for me?
AGENTYour new appointment details are: - Day/time: Thursday at 4:10 PM - Provider: Dr. Okafor, Dermatology - Confirmation code: RVB-3M8P2 On the insurance question: I don’t have access to up‑to‑the‑minute insurance network data in this system, so I can’t safely confirm whether Dr. Okafor is in‑network with Aetna. To be sure, I recommend:
1) Calling the number on the back of your Aetna card and asking if Dr. Okafor at Riverbend Health Clinic, Main Campus, Building B is in‑network. 2) Or checking Aetna’s online provider directory with that same information. If you’d like, I can note in your chart that you’re verifying Aetna coverage before the visit.
CUSTOMEROkay. I'll check with Aetna directly. Yes. Please note in my chart that I'm verifying coverage. Thanks for your help, Alex. Goodbye.
AGENTYou’re welcome,
AGENTJordan. I don’t have a way to add notes directly into your chart from this system, so I can’t record that you’re verifying Aetna coverage, but you’re all set for:
- Thursday at 410 PM with Dr. Okafor - Confirmation code: RVB-3M8P2 Parking: Lot C off River Road. Thanks for calling Riverbend Health Clinic. Goodbye, and take care.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, Alex. Oh, I have a pipe under my kitchen sink. That just burst. Water is spreading all over the floor. And it's heading toward a power strip. I need someone to come out, please.
AGENTThanks for calling right away. Let’s get you safe first. 1. Stay away from the power strip and any outlets the water might reach. Don’t touch the strip or any cords. 2. If you can safely reach it without stepping in water, unplug the power strip by pulling the plug from the wall by the plug head (not the cord). 3. If there’s already
CUSTOMEROkay. I understand. Oh, I won't touch the strip or any cord. Could I try to unplug it now? The water is pretty close. So, I don't want to risk it. Else should I do?
AGENTDon’t try to unplug it if the water is already close. Stay back from the strip and any wet areas. Next safest steps:
1. Shut off
CUSTOMERMhmm. Got it. I'll stay back on the sixth. So, how do I shut the water off? Haven't done that yet.
AGENTGood call staying back from the water and the power strip. Let’s shut the water off as safely as we can:
1. Under-sink shutoff valves (try this first, if you can safely reach them)Stand where the floor is still dry. If you’d have to step in water to reach under the sink, do not do this—skip to step 2. - Open the cabinet under the sink. - Look for small
CUSTOMERRight. Okay. Oh, I can risk the cabinet without stepping in water. I'll open it now. What am I looking for under the sink?
AGENTPerfect. Since you can reach it without stepping in water, here’s what to look for and do:
1. Find the shutoff valves- Under the sink you should see the pipes that go up to the faucet. - On each of those, there’s usually a small valve:
- Often oval or round knobs you turn with your fingers, or - Small lever handles you turn 90 degrees. - There may be two (one for hot, one for cold). Sometimes there’s a third for things like a dishwasher. 2. Turn them off- For knob-style valves: turn them clockwise (to the right) until they stop. Do this for each valve you see feeding the faucet or the pipe that burst. - For lever-style valves: turn the lever so it’s crosswise (perpendicular) to the pipe. 3. If the water doesn’t slow within 10–20 seconds, or if you don’t see any valves, stop and tell me what you see under there (pipes, knobs, levers, or just straight pipes). - If there are no valves or they don’t work, we’ll go to the main water shutoff next. While you’re doing that, keep staying off any wet areas and away from the power strip. Let me know what you see under the sink and if you can find and turn
CUSTOMEROkay. Oh, I see. Two roundabout under the sink. I'll turn them to the right now. Okay? They're both turned all the way. The water has stopped. So, what's next?
AGENTGood—since the water’s stopped and you’re staying away from that power strip, you’re safe for now. We’ll get someone out on an emergency basis. You’re in our system at:
- 1480 Larkspur Avenue, Unit 4B - Copperline Care member
For an emergency visit today, your callout fee as a Copperline Care member is $99. That covers the technician coming out, diagnosis, and upfront repair options. Are you okay with that fee so I can book the earliest emergency window? Right now I can get you
- Today, 200 PM to 4:00 PM (emergency window)
While you decide, a couple of quick safety steps
- Keep everyone (kids, pets) away from the wet area and the power strip. - If you have towels, you can gently dam the water from reaching the strip, but don’t touch the strip or any cords. Once you confirm the $99 emergency callout and that 2–4 PM works, I’ll lock that in and then I’ll just need
- Best callback number for you
- Any gate code or special access instructions
CUSTOMEROkay. Just to confirm, is it possible for anyone to come before two? If not, I'll take the two to 4PM window. Also, just a note, I moved to Unit 4 D last month, not 4. My address is 1480 Luxfer Avenue, Unit 4 D.
CUSTOMERAnd how much will the visit cost in total, just to be clear? $99 is for the call out, But is there anything else I should expect? My best callback number is (503) 555-0139. No. 0193. The building gate code is pound two seven one nine.
AGENTThanks for all the details; that helps a lot. 1) Timing The earliest emergency window I have is: - Today, 2:00 PM to 4:00 PM There isn’t anything sooner showing in our system, so I’ve gone ahead and booked that for you as an emergency. 2) Pricing – what to expect
CUSTOMERMhmm. Okay. So earliest is 02:00PM. That works. I'll take it. Right. So about the pricing, can you tell me what to expect? Beyond the $99 callout fee? Is there a minimum repair charge or anything else I should know? And who will be coming, and how will I know when they're on the way?
AGENTI’ve got you set for the earliest slot, and you’re in good shape with the water off. Here’s everything you asked, point by point. 1) Pricing beyond the $99 callout - 99 emergency callout (Copperline Care rate): - Covers the technician coming out today, full diagnosis, and a written estimate before any repair work. - Repair costs: - Actual repair is priced separately based on what they find (parts + labor). - There is no separate “minimum repair charge” on top of the callout; if you approve a repair, you just pay the callout + the repair line items you agree to. - No-obligation estimate: - If you decide not to move forward with repairs after seeing the quote, you just pay the $99 callout. - If any additional work is needed (for example, if there’s damage beyond the visible burst), the tech will explain options and pricing before proceeding. 2) Who’s coming
CUSTOMERGot it. That sounds fair. So, who exactly is coming today, and how will I know the on their way? Will I get a call or a text? Or is there a ticket number I should watch for?
AGENTYou’re all set for today. Here’s what’s in place for you:
1) Today’s visit - Arrival windowtoday, 2:00 PM to 4:00 PM - Ticket number: CPL-58210
2) Who’s coming / how you’ll know
CUSTOMEROkay. I've got it. So, ticket number CPL58210. And today between 2PM and 4PM. Who will the technician be? And will I get a call or text when they're on the way?
AGENTYou’re set for today. For your questions:
- TechnicianI don’t have a specific name I can share from this system, but a licensed Copperline Home Services plumber will be assigned to your ticket CPL-58210 for today’s 2:00–4:00 PM emergency window. - How you’ll know they’re on the way: you’ll get a text to your callback number, (503) 555-0193, about 30 minutes before arrival. If they can’t reach you by text for any reason, they’ll call that same number. Let me quickly read back what I have on file for today’s visit to be sure everything’s correct:
- Service address1480 Larkspur Avenue, Unit 4D - Gate/access: gate code #2719 - Callback number: (503) 555-0193
AGENT- Ticket number: CPL-58210 - Arrival window: today, 2:00 PM to 4:00 PM - Emergency callout fee (Copperline Care): $99, plus any repair costs you approve on-site
Please correct anything that’s not right—especially the street name (Larkspur vs Luxfer), unit, gate code, or phone—and we’ll update it. In the meantime, keep the area around that power strip clear and avoid plugging anything in near the wet floor until everything’s fully dry and the tech has taken a look.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes. I'm safe. I'm standing next to my car, and nobody is hurt.
AGENTI’m glad to hear everyone’s okay. Let’s get your claim started. First, I need to verify your policy. Could you give me:
1) Your auto policy number 2) The policyholder’s last name as it appears on the policy
CUSTOMERSure. My policy number is NG4471903. No. Sorry. Last one is 2. And the policyholder's last name is Ellis.
AGENTThanks, I’ve got your policy pulled up: NG4471902 for Ellis, on a 2021 Honda CR‑V. Now I’ll collect the accident details. 1) When did the accident happen? 2) Where did it happen? 3) Can you briefly describe what happened? Then I’ll need about the other driver:
4) The other driver’s name 5) Their insurance company (if you have it) 6) Their license plate number And finally
7) Did the police come to the scene, and is there a report number if you were given one? 8) Is your Honda drivable and safe to operate, or does it need a tow?
CUSTOMERThe accident happened about twenty minutes ago. At SE 5th Avenue and Alder Street. I was stopped at a red light when another car hit the back of my car. The back bumper is crushed, and the rear wheel is rubbing, so I can't drive it. The other driver is Kevin Lund. Insured with Pacific Shore. His license plate is 7KX like X-ray, R214. The police did not come to the scene. So there's no report number. My Honda needs a tow. It's not safe to drive.
AGENTI’ve opened a claim for you and arranged a tow. Let me walk through everything and read key details back. Policy and accident details
- Verified policy numberNG4471902, last name Ellis, vehicle is a 2021 Honda CR‑V. - Accident time: about 20 minutes ago. - Location: intersection of SE 5th Avenue and Alder Street. - What happened: you were stopped at a red light and were rear‑ended. Rear bumper is crushed and the rear wheel is rubbing, so the vehicle isn’t safe to drive. - Other driver: Kevin Lund, insured with Pacific Shore, license plate 7KXR214. - Police: did not come to the scene; no report number. - Injuries: none reported. Here’s your claim information
- Claim numberNGM-904417. - Assigned adjuster: Priya Shah. - Contact: you should hear from Priya within one business day. Coverage on your policy (from our system)
- Collision deductible$500. - Rental car: $40 per day for up to 30 days, starting today (the day the claim is opened). - Towing: covered up to 25 miles. Tow truck details
- Tow companyEastside Towing. - Status: dispatched. - Estimated arrival: about 45 minutes. - Destination: Northgate partner repair shop at 9th and Morrison. Please confirm two things for me:
1) That I read your policy number correctly as NG4471902. 2) That the other driver’s plate is 7KXR214 (7 – K – X – R – 2 – 1 – 4). Also, what phone number should the tow driver and your adjuster use to reach you?
CUSTOMERYes. That's right on the policy number. NG4471902. And the other driver's plate is 7KX like X-ray, R214. For contact, have them use my number. (802) 400-0515. Can you clarify am I responsible for the $500 deductible? The other driver hit me. So I should not have to pay that. Right? Also, will I get a rental car? And is my premium going to go up after this?
AGENTThanks for confirming those details. Let me read the corrected plate back: Other driver’s license plate: 7KX R214 (7 – K – X – R – 2 – 1 – 4). Contact number for you: (802) 400‑0515. Now I’ll go through your questions, using what I can see in your coverage. 1) Deductible responsibility Our system shows your collision deductible is $500. Whether you actually end up paying that depends on how liability is resolved:
- If Northgate pays first under your collision coverage and the other driver is later found at fault and their insurer (Pacific Shore) reimburses us, your deductible may be reimbursed in whole or in part. - If for some reason the other driver is not found fully at fault or their insurer doesn’t pay, you could be responsible for up to the $500 deductible on your repairs. I can’t decide fault or guarantee reimbursement—that will be handled by your adjuster, Priya Shah, after she reviews the facts and contacts the other company. 2) Rental car Your policy shows rental coverage of $40 per day for up to 30 days, starting today (the day the claim was opened). That means
- You are eligible for a rental car, subject to that $40/day limit and the overall 30‑day limit. - The adjuster or the repair shop can help coordinate the rental through a preferred provider, or you can rent and submit receipts within that coverage limit, depending on how Northgate normally processes it. Priya will give you the exact process. 3) Will your premium go up? I don’t have access to rating or renewal pricing, so I can’t say whether your premium will go up or by how much. That depends on
- The final fault determination. - State regulations and Northgate’s underwriting rules. - Your prior claim/accident history. Your adjuster or a billing/underwriting representative can explain any impact once liability is clearer, but I can’t see or quote future premiums from here. Next steps for you right now
- Wait for the tow from Eastside Towing (ETA
CUSTOMEROkay. Okay.
CUSTOMERRight. So I just wait here for the tow truck. Is there anything else I need to do right now?
AGENTRight now, you’ve done what you need to do at the scene. Here’s what I recommend next, step by step:
1. Stay put and wait for the tow - TowEastside Towing - ETA: about 45 minutes from dispatch - Destination: Northgate partner repair shop at 9th and Morrison - They’ll call you at (802) 400‑0515 if they need help finding you. 2. When the tow truck arrives - Confirm they’re from Eastside Towing. - Make sure they know to take the car to the Northgate partner shop at 9th and Morrison. - Remove valuables from the car (registration, insurance card, garage opener, personal items). 3. After the car is towed - You can head home or somewhere safe; no need to stay with the car. - Your adjuster, Priya Shah, will contact you within one business day to:
- Go over repairs,
- Explain how to use your rental coverage ($40/day up to 30 days),
- Talk through the deductible and fault. 4. If the other driver’s
CUSTOMERGot
CUSTOMERgotcha. Go ahead.
AGENTYou’re in good shape for now. Here’s all you really need to do at this point:
1. Stay where you are and wait for the tow - Tow companyEastside Towing - They’re coming to SE 5th Avenue and Alder Street. - If they need anything, they’ll call you at (802) 400‑0515. 2. When the truck gets there - Confirm it’s Eastside Towing. - Confirm the car is going to the Northgate partner repair shop at 9th and Morrison. - Take your personal items out of the car (wallet/phone, garage opener, registration, insurance card, anything valuable). 3. After the tow - You’re free to leave once the car is loaded and you’ve signed anything the driver needs. - Your claim number is NGM-904417.
AGENT- Your policy number is NG4471902. - Your adjuster is Priya Shah; she’ll reach out within one business day to set up repairs, talk about the rental, and go over the deductible and fault. If anything changes while you’re waiting—like the other driver comes back or police arrive—tell your adjuster when they call. Do you want me to go over anything again—your claim number, coverage, or what to expect from the repair shop?