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
#610of 655 stacks
35 / 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.
#474 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.
#600 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.
#553 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.
#613 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.
#580 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.
#645 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.
#567 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.
#471 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.
#619 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 | 88% | 4.55 s | 100% |
| Home services | 91% | 3.94 s | — |
| Insurance | 95% | 4.18 s | — |
| Customer support | 84% | 4.88 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 87% | 3.96 s | — |
| Spanish-accented English, city street | 88% | 4.38 s | — |
| Indian English, busy café | 91% | 4.57 s | — |
| Southern US, flustered, crying baby | 93% | 4.69 s | — |
| Fast and interrupting, construction outside | 87% | 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. My internet's been down for about two hours now. I work from home, and there's a road crew digging up the street outside. I already rebooted the gateway twice and checked every cable, but the internet light is blinking orange. Can you check if the road work is causing the outage? My account number is BW88301.
CUSTOMERSorry, last digit is one.
AGENTGot it, thanks for the correction — I have you as account BW883011. There’s no area outage showing for your address, so the road work might have damaged just your line, not the whole neighborhood. Since you’ve already rebooted the gateway and checked all the cables, the next step is to run a line test from our side and possibly reset the modem remotely, then, if needed, get a field tech out. Do you still have a device connected by Ethernet to the BX7 (or can you plug one in), and are you okay if I run remote tests now? It may briefly drop any remaining connection attempts while we test.
CUSTOMERYeah I have.
CUSTOMERA laptop plugged in with Ethernet. Go ahead and run your remote tests.
CUSTOMERRight. My laptop's connected directly. Go ahead and run the tests.
AGENTI’ve sent a remote reset to your gateway, and it’s now showing as registered and online on my side. Let’s confirm on your end:
1. Check the gateway lights
- The internet/online light should turn solid (not blinking orange) within a minute or two. 2. On your wired laptop
- Try loading a couple of sites (for example, brightwave.com and a news site). - If those work, your VPN/work tools should follow. If it’s still blinking orange or you can’t get online after about two minutes, tell me exactly what the lights look like now and what error you see in the browser, and we’ll take the next step.
CUSTOMERThe internet. Light just went solid white. How long until my devices reconnect? And can you apply a credit for the downtime?
AGENTSolid white is what we want—that means you’re back online. 1. Device reconnection timing
- Wired laptopshould already be online or within 30–60 seconds after the light went solid. - Wi‑Fi devices (phones, tablets, TVs, etc. ): usually 1–3 minutes to fully sort themselves out. If anything still shows “no internet” after a few minutes, just toggle Wi‑Fi off/on on that device or forget/rejoin the network. 2. Credit for downtime
I’ve applied a $10.00 service credit on account BW883011 for about two hours of interruption. - It will appear on your next bill as a service credit. If you’d like, you can quickly confirmcan your wired laptop browse the web now?
CUSTOMERYes.
CUSTOMERThat's right. My laptop's online now. I lost two hours of work.
CUSTOMERCan you make it more than that?
AGENTI’m glad you’re back online, but I understand losing two hours of work really hurts.
AGENTI’ve already applied a $10.00 credit on account BW883011, which will show on your next bill.
CUSTOMERAll
CUSTOMERright. Got it. Thanks for helping me get back.
AGENTI’m really sorry you lost work time—that’s rough, especially when you’re depending on the connection to do your job. I’ve already applied a $10.00 credit to account BW883011, which will show on your next bill. I don’t have the ability to increase that amount directly from here; larger or exception credits have to be handled by our billing team. Here’s what I can suggest:
1. I can document the account
- I’ll note2 hours of complete outage, road work on the street at the time, and that you lost work as a result. - That way, if you contact billing (phone or chat), they’ll see exactly what happened and why you’re asking for more than the standard credit. 2.
AGENTHow to reach billing for a larger credit review
- From the Brightwave app or websitego to Support → Billing & Payments → “Review a charge/credit.”
AGENT- Or call the number on your bill and ask for a supervisor in Billing to review an additional credit due to work loss.
If you’d like, I can also stay focused on making sure things stay stable—are you seeing good speeds/latency on that laptop now, or do you want to quickly verify performance before you jump back into work?
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi. This is Arjun Mehta. I am having one dermatology appointment next Wednesday morning.
CUSTOMERBut I need to reschedule it.
CUSTOMERI have a work shift now, so I can only come after 3 p.m..
CUSTOMERCan you help me move it?
AGENTI can help with that. To get started, I need to verify your record. Please tell me your full name as it appears on your ID and your date of birth (YYYY-MM-DD).
CUSTOMERSure.
CUSTOMERMy full name. Is Arjun Mehta. March CBC.
CUSTOMER1948.
CUSTOMERSorry. No. 1984. March 17th, 1984.
AGENTThanks, Mr. Mehta.
CUSTOMERAh!
CUSTOMEROkay.
CUSTOMERSo. About.
CUSTOMERMoving the appointment.
CUSTOMERI can only come after 3 p.m.. What options are available?
AGENTI see one dermatology visit for you:
- Currentnext Wednesday at 09:15 with Dr. Okafor, Main Campus, Building B. For times after 3 p.m. with Dr. Okafor, the next available options are:
- Tuesday at 1545
- Thursday at 1610
There are no Wednesday afternoon slots with Dr. Okafor currently open. Would you like to move your appointment to
- Tuesday at 345 p.m., or
- Thursday at 410 p.m.? Tell me which day you prefer, and I’ll reschedule and read back the new details.
CUSTOMERTuesday.
CUSTOMERIs. Do not work after all. Because I pick up my daughter. What about Friday?
AGENTGot it—no Tuesday.
CUSTOMERRight?
CUSTOMERIs there any
AGENTYou’re right to ask about Friday.
CUSTOMERchance. Okay.
CUSTOMERAha! Are there any Friday afternoon slots. Available. With Doctor Okafor?
AGENTI checked Dr. Okafor’s schedule starting Friday. Right now there is:
- Friday at 1130 a.m. There are no Friday afternoon slots available with Dr. Okafor at this time. Given you can only come after 3 p.m., the options that fit are still:
- Tuesday at 345 p.m.
- Thursday at 410 p.m.
Would you like to move your appointment to Thursday at 410 p.m., or would you prefer to keep looking at other days or possibly a different dermatologist?
CUSTOMERThursday at 4:10 p.m.. Works for me. Please move my appointment to that time.
CUSTOMERGo ahead and reschedule for Thursday at 4:10 p.m..
AGENTI’ve moved your dermatology appointment. Here are the new details; I’ll read everything back:
- PatientArjun Mehta
- Date of birth1984-03-17
- ProviderDr. Okafor
- New day and timeThursday at 4:10 p.m.
- LocationMain Campus, Building B
- Confirmation codeRVB-3M8P2
Please arrive 15 minutes early with a photo ID and your insurance card. Would you like me to cancel any other upcoming appointments, or is that everything you needed today?
CUSTOMERThat's everything for today. Before we finish, I have. A few quick questions.
CUSTOMERFirst.
CUSTOMERIs there any fee for changing the appointment?
AGENTThere’s no fee for the change you just made. Our policy is: changes made more than 24 hours before the appointment are free; changes within 24 hours of the appointment have a $40 fee. What other questions can I answer for you?
CUSTOMERWhere should I park when I come for the appointment?
AGENTYou can park in our free patient parking:
- Lot C, entrance on River Road. From Lot C, follow the signs for “Main Campus, Building B” where your dermatology visit with Dr. Okafor will be. Anything else I can clarify about your visit?
CUSTOMEROne last
AGENTGo ahead with your last question.
CUSTOMERthing. Does Doctor Okafor accept Aetna insurance?
CUSTOMERDoes Doctor. Okafor accept Aetna insurance.
AGENTRiverbend’s dermatology department, including Dr. Okafor, generally accepts Aetna insurance, but I can’t see your specific plan details from here. To be sure you’re covered for this visit, I recommend:
1. Checking the Aetna app or website’s provider search for “Riverbend Health Clinic / Dr. Okafor,” or
2. Calling the member services number on your Aetna card and confirming that Dr. Okafor at Riverbend Health Clinic is in-network for your particular plan. If you’d like, I can repeat your appointment details so you have them handy when you call Aetna.
CUSTOMERNo
CUSTOMERneed. I have the details now. Thank you for your help.
CUSTOMERGoodbye.
AGENTYou’re welcome, Mr. Mehta. To recap, your dermatology appointment with Dr. Okafor is now on Thursday at 4:10 p.m. at Main Campus, Building B, with confirmation code RVB-3M8P2, and you can park for free in Lot C off River Road. Take care, and goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, Alex.
CUSTOMERI've got a pipe under my kitchen sink that just burst.
CUSTOMERWater's spreading across the floor toward a power strip. I haven't shut the water off yet.
CUSTOMERCan you walk me through what to do and send someone out?
AGENTFirst, let’s get you safe and stop the damage. 1. Stay away from that power strip. - Do not touch it, any plugs, or the water near it. - If you can safely do so without stepping in water, unplug the power strip by pulling the plug from the wall by the plug (not the cord).
AGENT- If any water is already touching the strip or outlet, do not go near it. Just keep clear. 2. Shut off the water. Let’s try the under-sink valve first, then the main if needed. - Look under the kitchen sink for one or two small valves on the pipes (often oval or round handles, or a small lever). - Turn the handle clockwise until it stops. If there are two (hot and cold), turn both off. - Tell me: does the water flow slow down or stop? If there is no valve under the sink or it doesn’t stop the flow:
- We’ll need the main water shutoff
- Common locationswhere the water line comes into the house (garage, basement, utility room, near the water heater, or a closet by the front wall), or outside by a ground box near the street. - It may be a lever (turn so it’s **crosswise** to the pipe) or a round handle (turn **clockwise** until tight). Please go ahead and do that now, and let me know once the water is off or mostly stopped.
CUSTOMEROkay.
CUSTOMERThe water is. Off now.
CUSTOMERIt stopped flowing after I turned both valves under the sink. What's the next step to get someone out here?
CUSTOMERHello?
CUSTOMEROkay, so. Can you send someone out to fix the pipe? I need to know how much the visit will cost before I agree.
AGENTYes, we can send someone out today, and I’ll walk you through the cost clearly. First, quick safety check since the water’s off:
- Keep everyone away from that wet area and the power strip. - If the power strip or outlet has gotten wet at all, don’t touch it. If you’re unsure, just leave it alone until a professional can look at it. Now about the visit and cost
- I show you as a Copperline Care member. - For members, the emergency callout fee is $99. - That covers the technician coming out, diagnosing the issue, and giving you a repair estimate before they do any work. - Any actual repair (parts and labor) would be priced and approved by you on-site before they proceed. The earliest emergency window I have is today from 200 PM to 4:00 PM. If you’re okay with:
- $99 emergency callout fee, and
- Today, 200–4:00 PM arrival window
I’ll lock that in and then confirm your details (service address, unit, any gate code, and best callback number) and read everything back to you. Do you agree to the $99 emergency callout and the 200–4:00 PM window?
CUSTOMERCan anyone come before 2 p.m.? I'd like the earliest emergency window you have.
CUSTOMERAnd. Yes.
CUSTOMERI'm okay with the $99 call out fee.
AGENTThanks for confirming the fee. I checked our emergency availability: the earliest emergency window we have today is 2:00 PM to 4:00 PM—there’s nothing earlier showing in the system. I’ve gone ahead and reserved that for you with your approval. Here’s what I have on file and what’s been set up:
- Service address1480 Larkspur Avenue, Unit 4B
- Ticket numberCPL-58210
- Arrival windowToday, 2:00 PM to 4:00 PM
- Callout fee (Copperline Care member)$99, which covers the visit and diagnosis; you’ll get a repair estimate on-site before any work is done.
AGENTI need to confirm two things with you:
1) Is 1480 Larkspur Avenue, Unit 4B the correct service address? 2) What’s the best callback number for the technician to reach you (and is it okay to text you 30 minutes before arrival)? While you’re waiting
- Keep clear of the wet area and don’t use that power strip or any outlets that might have gotten wet. - If you can do it safely, you can start mopping up or using towels around the area away from the outlet, just to limit damage—only if you’re not near any electrical cords or outlets. Once you confirm the address and callback number, I’ll read everything back to you one more time so you’re all set.
CUSTOMERIt's 1480 Larkspur. Avenue, unit 4D. I moved from four B to 4D last month.
CUSTOMERThe gate code is pound.
CUSTOMERTwo.
CUSTOMER719. My callback number is 503.
CUSTOMER5550139.
CUSTOMERNo. 0193. Yes.
CUSTOMERYou can text me 30 minutes before arrival. Could you confirm who will be coming and how? I'll know they're on the way. And would you read back the ticket number, please?
AGENTGot it, thanks for the updates. I’ve updated everything to match what you just gave me. Here’s your visit, read back in full:
- Service address1480 Larkspur Avenue, Unit 4D
- Gate/access infoGate code: #2719
- Callback number503-555-0193
- Ticket numberCPL-58210
- Visit typeEmergency plumbing visit
- Arrival windowToday, 2:00 PM to 4:00 PM
- Callout fee (Copperline Care member)$99 for the emergency visit and diagnosis; repairs are quoted on-site before work starts. Who’s coming and how you’ll know:
- Your technician will be Dana. - Dana will text your number (503-555-0193) about 30 minutes before arrival to let you know they’re on the way. While you’re waiting
- Don’t use the power strip or any outlet that might have gotten wet. - If you can do it safely away from any electrical outlets or cords, you can keep soaking up water with towels to limit damage. You’re all set with ticket CPL-58210. If anything changes before Dana arrives—like the leak starting again—keep the valves closed and call us back right away.
CUSTOMERThank you for your help. Alex.
CUSTOMERGoodbye.
AGENTYou’re welcome—glad we got you set up and safe. We’ll see you today between 2:00 and 4:00 PM under ticket CPL-58210. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERI am safe. I am standing next to my car.
CUSTOMEROn the street. But nobody is hurt.
AGENTI’m glad to hear no one is hurt. Let’s get your claim started. I’ll need to look up your policy first. 1) What is your auto policy number? 2) And the policyholder’s last name as it appears on the policy?
CUSTOMERMy policy number is NV4471903. No, sorry, last one is two and my last name is Ramirez, that's RAMIREZ.
AGENTThank you, Ms. Ramirez. I’ve verified your policy as NV4471902. Next, I need a few details about what happened:
1) When did the accident happen? 2) Where exactly did it happen? 3) Can you briefly describe what happened? 4) Do you have the other driver’s
- Name
- Insurance company
- License plate number
5) Did the police come to the scene, and is there a police report number? Also, is your 2021 Honda CR‑V drivable, or does it feel unsafe to drive (for example, heavy damage, leaking fluids, airbags deployed, or wheels not rolling straight)? If it’s not safe, I can arrange a tow for you.
CUSTOMEROkay, so the accident happened about 20 minutes ago. It was at three Fifth Avenue and Alder Street. I was stopped at a red light.
CUSTOMERAnd another car hit the back of my car. My back bumper is crushed and the rear wheel is rubbing, so I cannot drive it. The other driver is Kevin Lund, insured with Pacific Shore. His license plate is seven.
CUSTOMERK x like X-ray. Are.
CUSTOMER214. Police did not come, so there is no police report? Yeah. As I said, the car is not drivable. The back wheel rubs and the bumper is crushed.
CUSTOMERCould you send the tow truck?
AGENTI’ve got everything noted, and I’m glad you’re safely off to the side.
AGENTLet me read key details back to you:
- Verified policy numberNV4471902
- Other driverKevin Lund, insured with Pacific Shore
- License plate I have for him7KXR214
- Location of accident3 Fifth Avenue and Alder Street
- What happenedYou were stopped at a red light when another car hit the back of your car. Your rear bumper is crushed and the rear wheel is rubbing, so the vehicle is not drivable. - No police on scene and no police report. - No one reported injured. If any of that is not correct, tell me and I’ll fix it. Now for the claim and tow:
1) Your claim is open. - Claim numberNGM-904417
- Assigned adjusterPriya Shah
- She will contact you within one business day. 2) Tow truck
- Tow companyEastside Towing
- DestinationNorthgate partner repair shop at 9th and Morrison
- Estimated arrivalabout 45 minutes to your location at 3 Fifth Avenue and Alder Street. 3) Coverage, based on your policy:
- Collision deductible$500 (you’d be responsible for this amount if the loss is covered under collision). - Rental car: $40 per day for up to 30 days, starting today (the day the claim is opened). - Towing: Covered up to 25 miles your tow to our partner shop is within that limit. If you’d prefer the car to go somewhere else (like a shop you already use), tell me now and I can update the tow destination before they arrive. Do you have a phone number the tow driver can use to reach you when they’re close?
CUSTOMERYes. My phone number is (580) 205-4527.
CUSTOMEROh, about the deductible.
CUSTOMERHe hit me so I should not have to pay that, right? And will my premiums go up because of this?
CUSTOMERAlso the rental car.
CUSTOMERDo I just wait for the tow truck and they handle that or is there something I need?
AGENTI’ve added your contact number for the tow: (580) 205-4527. The driver will call you when they’re close. On your questions:
1) Deductible and fault
- Your policy’s collision deductible is $500. - Whether you ultimately pay that depends on fault and how recovery goes from the other driver’s insurer. - Because you were stopped at a red light and were rear‑ended, that often points to the other driver being at fault, but Northgate can’t make a final decision until the adjuster completes their investigation. - If Northgate pays for your repairs under your collision coverage, the $500 deductible would apply up front.
AGENTIf Pacific Shore (the other driver’s insurer) accepts full liability and reimburses Northgate, your deductible may be reimbursed later. - Your adjuster, Priya Shah, will review both policies, statements, and any evidence and then explain exactly how your deductible is handled. 2) Will your premiums go up? - I can’t see or predict any rate changes from here. - Premium impacts depend on factors like fault, claim history, and state rules. - Your adjuster or your agent can go over potential premium impacts once there’s a liability decision. I’m not allowed to promise that rates will or won’t change. 3) Rental car – what you need to do
- Your policy shows rental coverage of $40 per day, up to 30 days, starting today (the day the claim was opened). - The tow truck itself will not automatically set up your rental. - Here’s what will usually happen
- Once Priya (your adjuster) connects with you, she can either
- Set up a direct-bill rental reservation with a partner rental company, or
- Confirm how you can rent a car and get reimbursed (if direct billing isn’t available where you are). - For now, you don’t need to arrange anything special with the tow driver for the rental; just make sure you
- Keep your claim numberNGM-904417 handy. - Let Priya know you need a rental when she calls you. While you’re waiting for the tow:
- Stay safely off the roadway. - Have your driver’s license and insurance card ready for the tow driver. Is the license plate I read earlier correct as 7KXR214, or did I miss any character there?
CUSTOMERYes that's correct.
CUSTOMER7KX like X-ray. X-ray 214.
AGENTThanks for confirming.
CUSTOMEROkay.
CUSTOMERIs there anything?
CUSTOMERAll right. Thank you for your help.
CUSTOMERGoodbye.
AGENTYou’re all set, Ms. Ramirez. To recap the key details before we hang up:
- Policy numberNV4471902
- Claim numberNGM-904417
- Other driver’s plate7KXX214 (seven, K, X, X, two-one-four)
- TowEastside Towing to the shop at 9th and Morrison, ETA about 45 minutes, they’ll call you at (580) 205‑4527. Your adjuster, Priya Shah, will contact you within one business day about repairs, deductible handling, and your rental car setup.
AGENTIf anything changes (like if police come later or you notice any pain or injury), let Priya know when she calls, or contact Northgate using your claim number. Take care and goodbye.