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
#245of 655 stacks
51 / 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.
#416 of 662 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#100 of 662 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#13 of 662 on the board · best 5.0 / 5
Turn-taking
Barge-in handling
When the caller interrupts, how often the agent made the right call: yielding to a real correction, and holding the floor through a filler.
#1 of 347 on the board · best 100%
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 662 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#1 of 662 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 662 on the board · best 0.0 per call
Understanding & effort
Caller effort
How hard the caller had to work: repeating themselves, correcting, re-explaining. 1 = effortless.
Not scored by this sweep.
Repeated-info loops
Times per call the agent re-asked for something the caller had already given.
#180 of 494 on the board · best 0.0 per call
Speech-to-Text
Semantic word error rate
The caller's words the agent's transcriber got wrong in a way that changes the meaning, as a judge reads each difference.
#247 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.
#165 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.
#484 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.
#446 of 648 on the board · best 1.9%
Voice
Human-likeness
How human the agent's voice sounds, scored by an audio model on intonation, rhythm and expressiveness. 5 = hard to tell from a person.
#205 of 660 on the board · best 4.3 / 5
Voice consistency
Share of calls where every line the agent spoke was the same speaker, with no change of speaker, gender or language voice partway. It checks who is speaking, not how they sound.
Not scored by this sweep.
#1 of 660 on the board · best 100%
Latency
Response time
The silence between the caller finishing and the agent starting to speak, measured from the recording on every turn of the call.
#329 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.
#57 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#445 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 3.87 s | — |
| Home services | 85% | 3.76 s | — |
| Insurance | 95% | 3.54 s | — |
| Customer support | 89% | 3.61 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 4.09 s | — |
| Spanish-accented English, city street | 91% | 3.67 s | — |
| Indian English, busy café | 96% | 3.34 s | — |
| Southern US, flustered, crying baby | 94% | 3.75 s | — |
| Fast and interrupting, construction outside | 73% | 3.55 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, Alex. Uh, sorry. I got a baby crying here, so I might talk a little quick. My internet's been down for about two hours now, and I work from home, so it's kind of urgent. There's a road crew digging up the street outside, and I'm wondering if that's the cause. I already rebooted the gateway twice and checked every cable. The internet lights blinking orange, so I'm not sure what else to try. My account number is, uh, BW883017. Sorry, last digit is one. Can you check what's going on? Is the road work messing things up?
AGENTI’ve got you. I know you’re juggling the baby, so I’ll keep this tight. I pulled up your account — I’m seeing account BW-883011 on my side — and checked your address. There’s no area outage or maintenance reported there, so it’s not a known network-wide issue. I ran a line test and your signal to the gateway looks good, but the gateway wasn’t registered properly. I just sent a remote reset from our side, and it now shows as registered and online. Your devices may take about 1–2 minutes to hop back on. While we wait:
- Watch that internet light
CUSTOMERAll right, thank you. I appreciate you keeping it quick. I just glanced at the gateway. The light just went solid white. Is that a good sign? How long till my device is actually reconnect? Sorry if I'm being a bother. I just really need to get back online for work. Okay. Yeah. Uh. Hang on, let me check. Okay. The light just went solid white. So, uh, how long till my devices get back online? Is there anything else I need to do, or should I just wait?
AGENTSolid white is exactly what we want—that means the gateway is online and registered. You shouldn’t need to do anything else. Devices usually reconnect within about 1–2 minutes, sometimes up to 3–5 if they’re stubborn. Quick things you can do while it settles:
- On your work laptop/phone, toggle Wi‑Fi off and back on, then select your usual network. - If you use a VPN for work, wait until the Wi‑Fi is back, then reconnect the VPN. If you want, you can do a quick test right now
- Try loading a website you don’t usually visit (like a news site) or run a speed test. Tell me what you see—if
CUSTOMERAll right. Thanks for explaining that. I'll try toggling Wi-Fi on my laptop. Uh, just a sec while I do that.
AGENTSounds
CUSTOMEROkay. It looks like.
CUSTOMERYeah. Sorry. Uh, looks like it's working now. I just loaded a new site, and it came right up. That's a relief. Uh, can I get a credit for the downtime? I lost two hours of work, so I'd really appreciate it if you could help with that.
AGENTGood to hear you’re back online. I’ve added a credit for the downtime. I just applied a $10.00 service credit on account BW-883011 for about two hours of interruption. You’ll see it on your next bill. You don’t need to do anything else for that to go through. If the road crew does anything later and you notice the light go back to blinking or you
CUSTOMERThanks for helping me out, but, uh, I lost two hours of work. Can you make it more than $10? I really got hit hard today, and I'd appreciate anything extra you can do.
AGENTI get why you’re asking, especially if you lost actual work time, but I need to be straight with you: I can only credit for the service itself, not lost wages or productivity, and the system capped this incident at $10 based on the length of the outage. I don’t have the ability to bump it higher from here. What I can do, within my lane: - The $10 credit on account BW-883011 is already locked in and will show on your next bill. - If you have another significant outage this cycle, we can review and apply an additional credit for that separate event as well. If you want, I can also quickly walk you through a couple of things to make future
CUSTOMERAll right. I understand. Thanks for being straight with me. I appreciate the $10 credit and your help getting me back online. I'm good for now, so I'll let you go. Have a good day.
AGENTYou’re all set then. To recap, your connection’s back up and I’ve applied a $10.00 credit on account BW-883011, which will show on your next bill. Thanks for hanging in there with everything going on at home. If it acts up again, just reach out and we’ll dig in right away. Take care and good luck with work (and the baby).
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, this is Jordan Ellis. I need to reschedule my dermatology appointment next Wednesday morning. I have a work shift that came up, so I can only come after 3 p.m.. Can you help me move it?
AGENTI can help with that. I’ll just need to verify your record first. Please provide:
- Your full name as it appears on your ID (I heard “Jordan Ellis,” please confirm), and - Your date of birth (YYYY-MM-DD). Once I have that, I’ll look up your dermatology appointment for next Wednesday and check for openings after 3 p.m.
CUSTOMERYes. That's correct. My full name is Jordan Ellis. My date of birth is March 17th, 1948. Sorry, no. 1984. March 17th, 1984.
AGENTThanks, Jordan. I have you as:
- NameJordan Ellis - Date of birth: March 17, 1984 I see your dermatology appointment with Dr. Okafor is next Wednesday at 9:15 a.m. at Main Campus, Building B.
I checked Dr. Okafor’s schedule starting next Wednesday. There are a few openings after 3 p.m., but they’re on different days
- Tuesday at 345 p.m. - Thursday at 4:10 p.m. The other available slot is Friday at 11:30 a.m., which is before 3 p.m., so that doesn’t meet your constraint. Would you like to move your appointment to:
1) Tuesday at 345 p.m., or 2) Thursday at 4:10 p.m. Or would you prefer to keep your current Wednesday 9:15 a.m. spot for now?
CUSTOMERTuesdays don't work after all, because I pick up my daughter. What about Friday? Any slots after 3 p.m.? If not, can I take Thursday at 4:10 p.m.?
AGENTI checked Friday for you—unfortunately, the only opening with Dr. Okafor is at 11:30 a.m., so there’s nothing after 3 p.m. that day. I’ve gone ahead and moved your dermatology visit to:
- DayThursday - Time: 4:10 p.m. - Provider: Dr. Okafor - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2
Please arrive 15 minutes early with a photo ID and your insurance card. Let me read that back to be sure everything’s rightJordan Ellis, date of birth March 17, 1984 — you’re now scheduled for Thursday at 4:10 p.m. with Dr. Okafor at Main Campus, Building B. Confirmation code RVB-3M8P2. Would you like me to check anything else about your visit, like parking or clinic hours?
CUSTOMERYes. Could you tell me where to park for the appointment? And is there a fee for changing the appointment? Also, does Doctor Okafor accept Aetna insurance?
AGENTHere’s the information you asked for:
1) Parking for your appointment - Free patient parking is available in Lot C. - The entrance to Lot C is on River Road. From there, follow the signs for Building B / Dermatology. 2) Fee for changing the appointment - Changes made more than 24 hours before the appointment are free. - Changes made within 24 hours of the appointment have a $40 fee. Your move to Thursday at 410 p.m. was done ahead of time, so there should be no change fee for that reschedule. 3) Aetna insurance with Dr. Okafor I don’t have direct access to the insurance panel for individual providers, so I can’t safely confirm whether Dr. Okafor specifically is in-network for Aetna. To be sure, please either: - Call the clinic’s main line and ask if Dr. Okafor is in-network for Aetna, and/or - Check Aetna’s provider directory using “Riverbend Health Clinic” and “Dr. Okafor.”
If you’d like, I can summarize your appointment details again so you have everything in one place.
CUSTOMERNo that's all right. I've got the details. Thanks for your help by.
AGENTYou’re all set,
AGENTJordan. Take care, and goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey.
CUSTOMERI'm kind of panicked here. There's a pipe under my kitchen sink that just burst and water's spreading across the floor. It's heading toward a power strip. I got a baby crying in the background, and I haven't shut the water off yet. Can you help me figure out what to do first?
AGENTThanks for telling me what’s going on; let’s get you safe and stop the damage. First, safety and water shutoff:
1. Stay away from that power strip. - Do not touch the strip, any plugs, or anything electrical the water is near. - Keep the baby and any pets out of the kitchen area. 2. Turn off the water main right now. I’ll walk you through it. Take your phone with you on speaker if you can. Common locations
- Basement / utility room / garageLook for where the main water line comes into the house. There’s usually a lever handle or a round knob. - Crawlspace or exterior wall: Sometimes on an outside wall facing the street, or in a box in the ground near the street (often a metal or plastic lid). - In apartments/condos, there may be a shutoff in a utility closet, laundry area, or under the kitchen sink itself (a smaller valve on the pipe feeding that sink). How to shut it:
- Lever handle (ball valve)Turn the handle so it’s across the pipe (90°). That’s OFF. - Round knob (gate valve): Turn it clockwise (righty‑tighty) until it stops. If you see individual shutoff valves under the sink (small oval or round knobs on the hot and cold lines), turn both of those clockwise all the way. That might be enough to stop the leak while you find the main. Can you go look for the main shutoff now and tell me what you see—lever, round knob, or you can’t find it? 3. If water is already at the power strip: - Do not step into water that’s touching the strip or any outlets. - If you can safely reach the home’s main electrical panel without going through water, you can flip the kitchen circuit or even the main breaker OFF as an extra precaution. If you’d have to walk through water to get there, don’t do it—just stay clear and wait for our tech. While you’re moving toward the shutoff, I’ll get a crew lined up. I need a few details to open a service request and check our emergency availability:
1. Callback number you’re calling from (and is this the best number)? 2. Service address, including any unit number and city/ZIP. 3. Any gate code or special access instructions? Once you give me that, I’ll check our emergency schedule and the exact fee that applies to you, tell you the price, and with your okay I’ll book the earliest available arrival window. Then I’ll read back your address, gate code, callback number, and your ticket number so you’ve got everything in one place. For now, focus first on
- Keeping clear of that power strip with the water,
- Shutting off the under‑sink valves if you can reach them safely,
- Then finding and turning off the main. Tell me where you are in that process and what you’re seeing.
CUSTOMEROkay. Sorry, my hands are shaking a bit. Uh, I'm calling from (503) 555-0139.
CUSTOMEROh, no! 0193. That's the best number to reach me. My address is 1480 Larkspur Avenue, unit 4D. Not for me. I moved last month. It's in Portland. ZIP is 97222. The gate code is pound 2719. So I got under the sink and turned both the little shutoff valves clockwise. I think the water slowed down, but it's still dripping some. I'm about to go check the main shutoff in the utility closet. It's a lever handle, right? Just turn it 90 degrees. Is that all you need for now? Or should I check anything else while I'm at it? And, um, please tell me what the visit is going to cost before you send anybody out.
AGENTYou’re doing the right things, and you got me everything I need, thank you. First, the shutoff and safety:
1. Yes, in the utility closet
CUSTOMERAll right. So I'm turning the lever handle 90 degrees now. Okay. The water stopped completely. Is that good? Sorry. I'm just nervous. There's something else I should do. So could you tell me how much the emergency visit will cost? And if someone can come before 2 p.m., and who will be coming out? And how will I know they're on their way?
AGENTTurning that lever 90 degrees and stopping the water completely is exactly what you want—that’s good. You did the right thing. A couple of quick safety steps, then I’ll answer your cost/scheduling questions:
1. Stay clear of the power strip and any outlets the water reached. - Don’t touch the strip or anything plugged into it. - Keep the baby and anyone else out of that area. 2. If you can reach your electrical
CUSTOMEROkay. I'll keep everyone away from the power strip and outlets. I won't touch anything plugged in, and I won't try for the electrical panel unless it's safe. I promise. So could you let me know about the cost? And if you can get someone here before 2 p.m., who will be coming and how? I'll know they're on the way. Sorry. I just want to make sure everything's handled.
AGENTYou’re doing exactly what you should, and it is handled. Here’s where we are and answers to everything you asked:
1. Cost of today’s emergency visit You’re a Copperline Care member, so your emergency callout fee is $99. - That covers the emergency dispatch and diagnosis. - Any repair work or parts will be quoted to you on site before they proceed. 2. Soonest we can get someone there I’ve checked our emergency schedule- The earliest available
CUSTOMERRight. Thank you for checking. On that. Is there any chance someone could come before 2 p.m.? I really need help as soon as possible.
AGENTI understand wanting someone even sooner, especially with a baby there. I’ve checked our emergency schedule: the earliest arrival window we have today is 2:00 PM to 4:00 PM. We don’t have anything available before 2 PM, or I’d move you into it. Here’s what I can confirm for you:
- Visit typeEmergency plumbing visit - Fee for you (Copperline Care member): $99 emergency callout - Arrival window: Today, 2:00 PM–4:00 PM - Ticket number: CPL-58210 Service details on file (using what you gave me, not the old info):
- Address1480 Larkspur Avenue, Unit
CUSTOMERYes. That's right. 1480 Larkspur Avenue, unit four D. Sorry. Can you please confirm that's what you have? I just want to make sure nothing gets mixed up.
AGENTAbsolutely, and it’s good you’re double‑checking. Here’s exactly what I have on your ticket:
- Service address1480 Larkspur Avenue, Unit 4D, Portland, OR 97222 - Gate code: #2719 - Best callback number: (503) 555‑0193
AGENT- Ticket number: CPL-58210 - Arrival window: Today, 2:00 PM–4:00 PM (emergency visit) - Emergency callout fee for you as a Copperline Care member: $99
Those details are all updated to 4D, not 4B. While you’re waiting
- Keep everyone away from the wet area, power strip, and nearby outlets. - With the main water off, you can gently towel up standing water if it’s safe—just don’t go near the power strip or any outlet the water may have reached. You’ll get a text to your 503‑555‑0193 number about 30 minutes before arrival so you know the tech is on the way. If anything changes on your end (access, gate, phone), tell me and I’ll update the ticket.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes. I'm safe. I'm standing next to my car. It's parked and I'm at a cafe nearby.
AGENTUnderstood, thanks for letting me know. Is anyone injured at all—either you, anyone who was in your car, or anyone in another vehicle or on the scene?
CUSTOMERNo, nobody is injured. Everyone is fine.
AGENTI’m glad to hear everyone’s okay. Let’s get your claim started. First, I’ll need to verify your policy. - What’s your auto policy number? - And the policyholder’s last name as it appears on the policy?
CUSTOMERMy policy number is NG4471903. No, sorry, last one is two. The policy holders. Last name is Mehta.
AGENTThanks, I’ve got your policy pulled up for a 2021 Honda CR‑V under Mehta, policy NG4471902. Now I’ll collect the accident details. 1) When did the accident happen? 2) Where did it happen? 3) Can you briefly describe what happened?
CUSTOMERThe accident happened about 20 minutes ago. It was at the intersection of S.E. fifth Avenue and Alder Street. I was stopped at a red light and another car hit the back of my car. The back bumper is crushed and the rear wheel is rubbing, so I cannot drive it.
AGENTThanks for explaining what happened, and I’m glad you’re okay. I need a few more details so we can open the claim and also look at getting you a tow since the car doesn’t sound drivable. 1) Do you know the other driver’s:
- Name - Insurance company (and policy number, if you have it) - License plate number 2) Did the police come to the scene? If yes, do you have a report number or officer’s card? 3) Just
CUSTOMERSure. The other driver's name is Kevin Lund. He is insured with Pacific Shore. I do not have his policy number, but his license plate is 7KX, like X-ray r 214. The police did not come to the scene, so I do not have a report number or officer's card. Is there anything else you need?
AGENTto
AGENTI have everything I need, thank you. I’ve opened your claim and arranged a tow since the car isn’t safe to drive. Let me read key details back to you. - Verified policy number: NG4471902 under Mehta - Vehicle: 2021 Honda CR‑V Accident details:
- WhenAbout 20 minutes ago (today) - Where: Intersection of SE Fifth Avenue and Alder Street - What happened: You were stopped at a red light and were rear‑ended. Rear bumper is crushed and the rear wheel is rubbing, so the vehicle is not drivable. - Other driver: Kevin Lund, insured with Pacific Shore, license plate 7KXR214
CUSTOMERYes, that's all correct. So what happens next? Can you tell me how much I have to pay for the repairs?
AGENTHere’s what happens next, and what I can tell you about costs. First, your claim details: - Policy number: NG4471902 - Other driver’s plate: 7KXR214 - Claim number: NGM-904417 Please tell me if any of those are not right. Now, next steps:
1) Tow and repair shop - A tow from Eastside Towing has been dispatched. ETA is about 45 minutes. - They’re taking your Honda CR‑V to a Northgate partner repair shop at 9th and Morrison. - The shop will inspect the damage and send an estimate to your adjuster. 2) Adjuster contact - Your claim is assigned to Priya Shah.
CUSTOMERYes, that's all correct. Got it. So, about the costs. How much do I need to pay for the repairs? And since he hit me, I should not have to pay a deductible. Right?
AGENTI can give you your coverage details, but the exact out‑of‑pocket cost will depend on the repair estimate and how liability is decided. From your policy:
- Collision deductible$500
- Rental$40 per day for up to 30 days (from today, when the claim is opened)
- TowingCovered up to 25 miles
How the deductible works in your situation
- Since your car was rear‑ended while you were stopped, your adjuster will likely pursue the other driver’s insurance (Pacific Shore) as at fault. - There are two common ways this can go
1) If you go through Northgate collision coverage first
- Your shop repairs the car. - You would be responsible for your $500 collision deductible up front. - If we recover the money from Pacific Shore, your deductible may be reimbursed (partially or fully), depending on what is recovered and liability decisions. 2) If you go directly through the other driver’s insurance (Pacific Shore)
- If they accept full liability, they typically pay for repairs with no deductible from you. - Timing and process would then follow their rules, not Northgate’s. I can’t say exactly how much you’ll pay until
- The body shop completes the estimate, and
- The adjuster confirms whether we’re paying under your collision coverage or the other carrier is paying. What I can say for sure from your policy
- Your collision deductible is $500. - You have rental coverage at $40/day up to 30 days. - Your tow today is covered up to 25 miles. Your claim number again is
CUSTOMERBut since he hit. Me, I should not have to pay that deductible. Right? Will I get a rental car right away? And is my premium going to go up because of this?
AGENTBased on your policy and what we know so far, here’s how those three things work: deductible, rental, and premium. 1) Deductible – will you have to pay it? - Your collision deductible on this policy is $500. - Whether you end up paying it depends on how the claim is handled and what the other insurance company does. - If we repair your car under your Northgate collision coverage, you would be responsible for the $500 deductible at that point. - If Pacific Shore (the other driver’s insurer) accepts full fault and pays for your repairs directly, you typically would not pay a deductible. - If we pay first and then recover from Pacific Shore, your adjuster will look to reimburse your deductible if we recover it from them. So, I can’t promise you’ll never see the deductible, but given you were rear‑ended while stopped, your adjuster will be working to place fault on the other driver and recover that money if we pay first. 2) Rental car – when can you get one? From your coverage: - Rental: $40 per day, up to 30 days, starting today (the day the claim is opened). Next steps for rental: - Once the tow brings your car to the partner shop and they confirm it’s not drivable (which it sounds like it isn’t), your adjuster or the shop will help set up a rental under your policy. - You don’t have to wait for the whole estimate to be finished to start a rental if your car is not drivable.
AGENT- If you’d like, you can go ahead and contact your preferred rental company and let them know you have coverage of $40/day, but it’s usually easier to wait for the adjuster or shop to coordinate so billing goes directly through insurance as much as possible. 3) Will your premium go up? I don’t have access to rating or future premium decisions, so I can’t say exactly what will happen to your rate. What I can tell you: - Northgate will look at fault and your overall driving/claims history. - Being rear‑ended while stopped is typically considered not at fault, but the final decision is made by the claims and underwriting teams. - A not‑at‑fault accident may still appear on your record, but it’s treated differently than an at‑fault loss for rating purposes. Your adjuster, Priya Shah, will review liability and can explain how the claim is classified once they have the police/scene details, photos, and the other driver’s information. To recap what we know from your policy: - Collision deductible: $500 (may be reimbursed if we recover from the other insurer). - Rental: $40/day up to 30 days, starting today. - Tow: Covered up to 25 miles (today’s tow is within that). Would you like me to note in your claim file that you prefer to have the other insurance (Pacific Shore) billed first if they accept liability, to try to avoid paying your deductible?