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
#450of 655 stacks
45 / 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.
#423 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.
#598 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.
#107 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.
#310 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.
#493 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.
#620 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.
#290 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.
#515 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.
#554 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#496 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 84% | 4.78 s | — |
| Home services | 91% | 4.37 s | — |
| Insurance | 97% | 4.29 s | — |
| Customer support | 89% | 4.80 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 92% | 4.39 s | — |
| Spanish-accented English, city street | 83% | 4.64 s | — |
| Indian English, busy café | 96% | 4.56 s | — |
| Southern US, flustered, crying baby | 93% | 4.87 s | — |
| Fast and interrupting, construction outside | 88% | 4.33 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi, Alex. Uh, yeah, my internet has been down for about two hours now. I work from home, and, um, there's a road crew digging up the street right outside. I already rebooted the gateway twice and checked every cable. The internet light is blinking orange. My account number is BW883017. Sorry, last digit is one is the road. Work may be the cause of this.
AGENTThanks for the details, that helps a lot. I’ve got your account pulled up as BW-883011 on the Brightwave 500 plan, and I checked your address—there’s no area outage or maintenance showing, even with that road work going on. I ran a line test and your signal to the gateway looks good, but the gateway itself wasn’t registered, so I pushed a remote reset just now. The modem is now showing as registered and online on our side.
CUSTOMEROkay, but just so you know, I already restarted the gateway twice and checked all the cables before calling. The light on the modem. Just went solid white now. So, uh, how long until my devices reconnect?
AGENTSolid white is a good sign—that means the gateway is back online. Most devices should reconnect within 1–2 minutes on their own.
CUSTOMERGot it. So, uh, should I just wait for them to connect? Is there anything else I need to do? Also, since I lost two hours of work, can I get a credit for the downtime?
AGENTYou’re all set on your side for now. 1.
CUSTOMEROkay. Right. I'll wait and see if everything reconnects. So, about the credit, what can you offer for the downtime?
AGENTI’ve gone ahead and applied a credit for you. - Account: BW-883011
- Credit amount$10.00
- It will appear onyour next bill
You don’t need to do anything else for the connection right now—just give it a minute or two for everything to reconnect.
CUSTOMEROkay, thanks, but I lost two hours of work. Can you make the credit? More than $10.
AGENTI understand why you’re asking, especially if it cost you real work time. I’ve applied a $10.00 credit to account BW-883011, and that’s the standard one-time adjustment I’m able to issue for a short interruption like this. I don’t have the ability to increase that amount from here. If the connection drops again or this turns into a recurring issue (for example, if that road work actually damages our line and you see more outages), contact us and we can both troubleshoot and review additional credit based on the longer impact. For now, I’d keep an eye on things for the rest of the day. If you want, I can also note on your account that this outage affected your work so it’s documented if there are future problems.
CUSTOMERAll right, that. Makes sense. Yes. Please note on my account that the outage affected my work. Thanks for your help, Alex. Goodbye.
AGENTI’ve noted on account BW-883011 that today’s outage impacted your work and caused about two hours of downtime. Glad we got you back online. If it acts up again—especially with that road work going on—reach out right away. Take care.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey. Uh. Hi. Sorry, I'm a little flustered. I've got a baby crying here. Um, I need to reschedule my dermatology appointment next Wednesday morning, if that's all right. I just found out I have to work a shift then, so I can't make it. Can you help me move it? My name's Wade Carter.
AGENTI can help with that. We’ll take it step by step. To pull up your appointment, I need to verify your date of birth. Can you tell me your full date of birth (YYYY-MM-DD)?
CUSTOMEROh, yeah. Sure. Um, it's March 17th, 1948. Sorry. No. 1984. March 17th, 1984. Is that okay?
CUSTOMERHello?
AGENTThanks for waiting, and no worries about the mix‑up. I’ve found your dermatology appointment:
- ProviderDr. Okafor
- Daynext Wednesday
- Time09:15
- LocationMain Campus, Building B
- Appointment IDAPT-20931
You mentioned you need to move it from Wednesday morning because of work. What days and times generally work better for you? For example, are afternoons better, or a different day of the week? Once I know that, I’ll look for openings with Dr. Okafor that fit.
CUSTOMERYeah. Um, afternoons are best for me. Sorry. I can only come after 3 p.m.. Is that gonna be a problem? I just want to make sure nothing gets lost.
AGENTThat won’t be a problem, and your existing appointment details are all safe until we confirm a new time—nothing gets lost.
CUSTOMEROkay. Thanks for checking. Go ahead and let me know what you see. I just want to make sure I can get something after 3 p.m..
AGENTI checked Dr. Okafor’s schedule starting from your current appointment, and here are the options that are after 3 p.m.:
- Tuesday at 1545
- Thursday at 1610
Both are with Dr. Okafor. Which one would you like to move your appointment toTuesday at 15:45 or Thursday at 16:10?
CUSTOMERSorry. Tuesdays don't work after all. I pick up my daughter then, so I can't make that time. What about Friday? Or if not, Thursday at 1610 would be okay. Is that all right?
AGENTGiven what you’ve told me:
- Friday has an opening at 1130, but that’s before 3 p.m., so it doesn’t fit your schedule. - The Thursday slot at 16:10 does meet your “after 3 p.m.” requirement. So Thursday at 16:10 with Dr. Okafor is a good option. If you’d like, I can go ahead and move your current appointment next Wednesday at 09:15 to Thursday at 16:10. Just say “yes, reschedule to Thursday at 16:10,” and I’ll process the change and read back the new details and confirmation code for you.
CUSTOMERYes. Please reschedule me to Thursday at 1610. Is that okay? I just want to make sure nothing gets lost or messed up.
AGENTYou’re all set, and nothing was lost or messed up—I’ve just moved your existing visit. Here are your new appointment details, Wade:
- DepartmentDermatology
- ProviderDr. Okafor
- DayThursday
- Time16:10 (4:10 p.m.)
- LocationMain Campus, Building B
- New confirmation codeRVB-3M8P2
The old appointment next Wednesday at 0915 has been replaced with this new one. Arrival instructions: please arrive 15 minutes early with a photo ID and your insurance card. Can I help with anything else for you or the baby while you’re on the line?
CUSTOMERYeah, actually, a couple quick things. Is there a fee for changing the appointment? Sorry if that's a bother. I just want to make sure. And, uh, where do I park for building B? Does Doctor Okafor take Aetna insurance?
AGENTI can help with all of that. 1) Fee for changing the appointment
Your change is free. Our policy is
- Changes made more than 24 hours before the appointment are free. - Changes within 24 hours carry a $40 fee. You rescheduled your dermatology visit more than 24 hours in advance, so there’s no charge. 2) Parking for Building B
For Building B, patient parking is
- Free patient parking in Lot C
- Entrance is on River Road
From Lot C, follow the signs for “Building B / Dermatology.” 3) Aetna insurance with Dr. Okafor
I don’t have provider-by-insurance-panel access in this system, so I can’t safely confirm Aetna coverage for Dr. Okafor. To be sure nothing gets “messed up” with billing, I recommend one of these
- Call the main clinic line and ask if Dr. Okafor is in-network for Aetna, or
- Check Aetna’s online provider directory using “Riverbend Health Clinic” and “Dr. Okafor.” If you’d like, I can also read your appointment back once moreWade Carter, date of birth 1984-03-17, dermatology with Dr. Okafor on Thursday at 16:10, confirmation code RVB-3M8P2.
CUSTOMERThank you. That's helpful. Sorry. Can you just repeat the confirmation code real quick. I want to make sure I've got it right. And uh is there a number I should call if I need to check on the insurance part?
AGENTYour confirmation code is RVB-3M8P2. That’s: R–V–B – 3–M–8–P–2. For the insurance question about Aetna and Dr. Okafor, please call the clinic’s main line; they can check the insurance details for you.
CUSTOMEROkay. That's perfect. Thank you for confirming. I think that's everything I needed. Uh, thanks again for your help. I really appreciate it. Goodbye.
AGENTYou’re very welcome, Wade. Just to leave you with the key details one last time:
- AppointmentDermatology with Dr. Okafor
- DayThursday
- Time16:10 (4:10 p.m.)
- Confirmation codeRVB-3M8P2
If anything comes up, just give us a call. Take care, and good luck with the little one. Goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. I have an emergency. A pipe under my kitchen sink just burst and water is spreading across the floor, heading toward a power strip. I haven't shut the water off yet. Can you send someone?
AGENTFirst move away from the water and the power strip right now for safety. Let’s do two quick things:
1. Keep electricity safe
- If you can unplug the power strip without stepping in water or reaching over water, do that now.
CUSTOMEROkay, I'm moving back now. I'll unplug it from a distance. Oh, there's water close, but I think I can reach safely. What's next?
AGENTDon’t reach through or over any water to get to that power strip. If there’s any doubt, leave it and stay clear of that area. Next, we need to stop the water:
1. Shut off the water to the house if you can
- Look for the main shutoff valve
- Often where the water line enters the house (basement, utility room, or near the front foundation wall), or
- Outside near the street in a ground box, or on an exterior wall. - Turn the handle clockwise until it stops (if it’s a lever, turn it so it’s **perpendicular** to the pipe). 2.
CUSTOMEROkay.
CUSTOMERSorry. Could you repeat that last bit? I didn't catch all of it. Where should I look for the shut off?
AGENTNo problem, I’ll walk you through it step by step. First, stay clear of any water near that power strip. Don’t reach through or over water to unplug it. If it’s at all risky, leave it. Now, to shut off the water to the house, here’s where to look for the main water shutoff valve:
1.
CUSTOMERCould you say that again? I missed the last part. Where should I look first?
AGENTLook in these spots, in this order:
1.
CUSTOMERGot it.
CUSTOMERI'm looking for the shut off valve. So inside basement. Utility room. Garage. What does it look like?
AGENTGood, stay clear of that water near the power strip while you look. The main shutoff can look like either of these:
1. Round handle (gate valve)
- Looks like a round wheel on a pipe. - You turn it clockwise (right) until it stops to shut the water off. 2.
CUSTOMERYes, I understand. Round wheels. Turn it clockwise all the way or leave a handle. Turn it so it's perpendicular to the pipe. I'll do that now. Okay, I see it. I'm turning the round handle clockwise right now. All right. The water has stopped. What should I do next?
AGENTGood job getting the water shut off—that’s the most important part.
CUSTOMEROkay. Go ahead. What should I do now? For safety.
AGENTNow that the water is off, here are the key safety steps:
1. Stay away from the power strip and any outlets near the water. - Don’t touch the strip, cords, or any plugs near the wet area.
CUSTOMERI'll stay clear. The power. Strip and any. Outlets near the water. The breaker panel is not in the wet area. So I can turn off the kitchen breaker if needed. Should I do that now?
AGENTGood. Since water got close to that power strip, let’s add one more safety step:
1. If your main electrical panel (breaker box) is in a dry area you can reach without crossing any water
- You can switch off the breaker that controls the kitchen or that outlet circuit, or
- If you’re unsure which one it is, you can turn off the main breaker at the top of the panel.
CUSTOMEROkay.
CUSTOMERSorry, I. Didn't catch. The last part. Could you repeat that?
AGENTNo problem, I’ll repeat it more simply. Since water got close to that power strip:
1.
CUSTOMERI see if my breaker panel is in a. Dry area. I can turn off the kitchen breaker or the main breaker. Should I do that now?
AGENTYes—if you can reach the breaker panel without going near any water, go ahead and do that now. 1. Make sure the path to the panel is completely dry. 2. At the panel:
- If you know which breaker is for the kitchen, switch that one OFF, or
- If you’re not sure, you can switch the MAIN breaker OFF at the top of the panel. If you’d have to cross or stand in any wet area to reach it, do NOT go to the panel—just stay clear of the kitchen outlets and that power strip and tell me.
CUSTOMEROkay. I'm checking. The path is dry, so. I'll turn the main breaker off now. Alright. It's off. What comes next? All right. The path to the panel is dry, so I'm turning off the kitchen breaker now. Okay. It's off. So can you send someone out? And can you tell me how much the visit will cost before I agree?
AGENTYes, we can send someone.
CUSTOMERI actually moved last month. My unit now is 4D. Not four B. The address is 1480 Larkspur Avenue, unit 4D, and um, okay, $99 for the visit. Can anyone come before two?
AGENTThanks for the update on the address, and I’m glad you got the water and power handled. I’ve got a few things for you:
1) Cost
You’re a Copperline Care member, so the emergency callout fee is $99 for today’s visit. Any repair work or parts would be additional, and the technician will go over options and pricing with you before doing anything.
CUSTOMERRight
CUSTOMEROkay, what else should I know?
CUSTOMERAll right, go ahead. What time will someone be able to come?
AGENTI’ve got you set up, and I’ll walk you through everything clearly. 1) Timing
The earliest emergency window we have today is
- Today, 200 PM to 4:00 PM
I’ve booked that window for you. 2) Cost
- As a Copperline Care member, your emergency callout fee is $99. - The plumber will inspect the burst pipe, then explain repair options and pricing before doing any work. 3) Your service request
Here’s what I have on the ticket
- IssueBurst pipe under kitchen sink, water spread across the floor toward a power strip. You’ve shut off the main water and turned off the kitchen breaker. - Urgency: Emergency
- Address1480 Larkspur Avenue, Unit 4D
- Ticket numberCPL-58210
I need two quick things from you so we’re sure everything’s correct
1. Is 1480 Larkspur Avenue, Unit 4D the correct service address, and is there any gate code or special access info we should note? 2. What’s the best callback phone number for the technician, and can they text you 30 minutes before arrival? While you’re waiting
- Keep the water main off. - Keep away from the wet area and all outlets/cords in the kitchen until everything is dry and a tech has checked it.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah. I'm okay. I'm just standing next to my car on the sidewalk. There's a lot of traffic, but I'm not hurt. My car got hit about 20 minutes ago at 35th Avenue and Alder Street. Nobody's hurt, but the back bumper is crushed and the rear wheel rubs, so I can't drive it. I need to report the claim.
AGENTThanks for letting me know. Since no one is hurt or in danger, we’ll go ahead and start your claim and get a tow set up since the car isn’t drivable.
CUSTOMEROkay. Go ahead. Let me know what you need from me.
AGENTI’ll take care of this step by step. First, I need to find your policy. - What’s your auto policy number? - And the policyholder’s last name?
CUSTOMEROh, the policy number is NG4471903. Oh, sorry, the last one is two, and the last name is Ramirez.
AGENTI’ve got everything started for you. First, to confirm:
- Your policy numberNG4471902
- Policyholder last nameRamirez
If that’s not right, tell me and I’ll fix it.
CUSTOMERJust to correct, it was Fifth Avenue and Alder Street, not 35th. Everything else is right. I was stopped at a red light and another car hit the back of my car. The bumper is crushed and the rear wheel rubs so I can't drive it.
CUSTOMEROkay, so what do you need from me next?
AGENTThanks for the update; I’ve noted the correct location as Fifth Avenue and Alder Street instead of 35th. I’ve already opened your claim and started a tow, but I still need a few details from you:
1. Other driver’s information
- What’s the other driver’s full name, if you have it? - Do you know their insurance company? - Do you have their license plate number? 2. Police
- Did the police come to the scene? - If yes, do you have a police report number or the name of the department? 3. Best contact
- What’s the best phone number for the adjuster to reach you? - And is there a good email address for you? Also, just so you know what’s already in place
- Your claim number is NGM-904417. - We’ve dispatched Eastside Towing to Fifth Avenue and Alder Street with an ETA of about 45 minutes to take your 2021 Honda CR‑V to our partner shop at 9th and Morrison. - Your policy shows collision coverage with a $500 deductible, rental reimbursement ($40/day up to 30 days from today), and towing up to 25 miles. Once you give me the other driver’s info and your contact details, I’ll summarize everything back to you.
CUSTOMEROkay. So the other driver is Kevin Lund. His insurance is with Pacific Shore. The license plate is 7KXR214X, like X-ray. Hollis did not come to the scene, so there's no report. The best phone number is the one I'm calling from (507) 698-9041. For email, it's Lucia dot ramirez@gmail.com, that's LUCIA dot ramirez@gmail.com. So about the deductible, how much do I have to pay? And he hit me. So I should not have to pay that, right? Also, just to confirm, I can get a rental car and is my premium going to go up? Where exactly will my car be taken?
AGENTI’ve added all that info to your claim. Let me walk through your questions one by one. First, reading key details back to you:
- Policy numberNG4471902
- Other driverKevin Lund, insured with Pacific Shore
- Their license plate7KXR214X
- Your claim numberNGM-904417
If any of that is off, tell me and I’ll correct it. Now, your questions
### 1. Deductible – how much, and do you have to pay it? From your policy
- Collision deductible$500
If we repair your car under your collision coverage
- The shop’s bill gets paid minus $500, which is your share. - We may then pursue the other driver’s insurer (Pacific Shore). - If they accept fault and reimburse us, your $500 may be paid back to you. - That part depends on their liability decision and any investigation. Because you were rear-ended at a red light, it sounds like the other driver may be at fault, but
- I can’t make a fault decision or guarantee reimbursement myself. - Your adjuster, Priya Shah, will review the details and contact Pacific Shore. ### 2. “He hit me, so I shouldn’t have to pay, right?” I understand why you feel that way. The way it usually works
- To get your car moving quickly, we use your collision coverage (with the $500 deductible). - Separately, we go after the other insurer. - If they accept full responsibility, they typically reimburse what we paid, including your deductible, subject to their review. So
- You may have to pay the $500 up front, but
- You might get it back later if Pacific Shore accepts liability. Your adjuster will explain where things stand once they’ve spoken with the other company. ### 3. Rental car – can you get one? Your policy has
- Rental coverage$40 per day, up to 30 days, starting today (the day the claim is opened). That means:
- Yes, you can get a rental car, subject to that $40/day limit and 30‑day maximum. - If the rental costs more than $40/day, you’d pay the difference. - Your adjuster or the partner shop can help you get set up with a rental through one of our preferred providers, or you can arrange your own and submit receipts within those limits. ### 4. Will your premium go up? I’m not able to say whether your premium will or won’t increase
- Rate changes depend on state rules, your full driving/claim history, and how this loss is ultimately classified. - I can’t quote or predict premium changes from here. Your adjuster can
- Explain how this claim will be coded (at‑fault, not‑at‑fault, comprehensive, etc.) once the investigation is further along. - Let you know how that coding typically affects rating, but they still can’t guarantee future pricing decisions. ### 5. Where is your car being taken? The tow we dispatched is set to go to
- Northgate partner repair shop at 9th and Morrison. If you’d prefer a different shop
- Tell me now, and we can note a different destination for the tow and for your claim file. ---
Next steps for you
- The tow from Fifth Avenue and Alder Street is already on the way (Eastside Towing, ETA about **45 minutes** from dispatch). - Your adjusterPriya Shah will contact you within one business day at:
- Phone(507) 698‑9041
- Emaillucia.ramirez@gmail.com
They’ll
- Go over fault and the deductible situation in more detail. - Help coordinate the repair and rental. - Answer any follow‑up questions about coverage or timing. Is 9th and Morrison okay as the repair location, or do you want the car taken somewhere else?
CUSTOMERNinth and Morrison is fine. Yeah. So just to confirm, claim number is NGM904417. The car will go to your partner's shop there and I'll wait for your adjuster to call. That's all I needed. Thank you. Goodbye.
CUSTOMERHello.
AGENTHi again, this is Alex with Northgate Mutual claims. It looks like we just spoke and you’re all set with:
- Claim numberNGM-904417
- Policy numberNG4471902
- Your vehicle going to our partner shop at 9th and Morrison
- AdjusterPriya Shah, who’ll contact you at (507) 698‑9041 and lucia.ramirez@gmail.com
What can I help you with now?