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
#300of 655 stacks
49 / 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.
#441 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.
#363 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.
#343 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.
#447 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.
#394 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.
#364 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.
#441 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#496 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 94% | 3.98 s | — |
| Home services | 84% | 3.86 s | — |
| Insurance | 98% | 3.64 s | — |
| Customer support | 84% | 3.74 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 92% | 4.00 s | — |
| Spanish-accented English, city street | 91% | 4.04 s | — |
| Indian English, busy café | 94% | 3.41 s | — |
| Southern US, flustered, crying baby | 91% | 3.89 s | — |
| Fast and interrupting, construction outside | 82% | 3.66 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. I work from home, so it's a problem. There's a road crew digging up the street outside. I already rebooted the gateway twice and checked every cable. The internet light is blinking orange. Can you check if the road crew is causing this or if there's an outage in my area? My account number is BW883017. Sorry, last digit is one.
AGENTI’ve got you pulled up under account BW883011, and there’s no area outage showing for your address, so the road work isn’t logged as a known outage on our side. I ran a line test to your BX7 gateway. The signal to your home looks good, but the gateway had dropped its registration. I’ve just pushed a remote reset, and it’s now showing as registered and online. Your Wi‑Fi and wired devices may take about 1–2 minutes to fully reconnect. Can you check:
1. The internet light on the gateway — it should turn solid (not blinking orange) once it’s fully online. 2. Try loading a site on your work device (ideally a couple of different sites or a speed test). If it’s still not working after two minutes, tell me
- What color/state the internet light is now, and - Whether any device in the house can get online (Wi‑Fi or Ethernet). From there I’ll either dig deeper or get a tech scheduled if needed.
CUSTOMERThe internet light just went solid white. How long until my devices reconnect? I'll check a couple of sites right now. Also, since I lost two hours of work, can you add a credit for the downtime to my account?
AGENTYour gateway’s back online now, so most devices should reconnect within 1–3 minutes on their own. If anything doesn’t:
- Toggle Wi‑Fi off/on on that device, or - Forget and rejoin your Wi‑Fi network once. I’ve also added a service credit for the downtime on account BW883011
- Amount$10.00 - It will appear on your next bill. Go ahead and try a couple of sites and, if you can, a speed test. If anything is still slow or not loading after a few minutes, tell me which devices are affected and whether they’re on Wi‑Fi or Ethernet, and I’ll dig in further.
CUSTOMEROkay, I will check my devices about the credit. $10 isn't much for two hours of work lost. Can you make it more than that?
AGENTI understand—that’s a real impact if you’re working from home. On my side, I’m limited to the standard courtesy credit level the system allows for this type of short interruption, which in your case is the $10 I already applied to account BW883011 and will show on your next bill. I don’t have the ability to increase that amount directly. If you want to request a larger adjustment based on lost work time, the only path is through Customer Care so a supervisor can review it against our credit policy. You can reach them at the number on your bill or via chat in the Brightwave app under Support → Billing. They’ll see the outage notes and the $10 credit I’ve already added and can tell you what else is possible. In the meantime, are all your devices back online and stable now?
CUSTOMERYes. Everything's back online and working fine now. Thanks for the help, Alex. Goodbye.
AGENTYou’re welcome—glad everything’s back up and running. Quick recap before you go:
AGENT- Account: BW883011 - Credit applied: $10.00, will show on your next bill. If anything acts up again, just reach out. Take care.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey. Hi. Sorry. I got a baby crying in the background here, so I might be a little scatterbrained. Um, I need to reschedule my dermatology appointment next Wednesday morning. I just found out I got a work shift then, and I can't make it. Can you help me move it?
AGENTI can help with that. We’ll first verify your record, then I’ll look up your appointment and available times.
CUSTOMERI. All right. Thank you. Is there anything I need to do right now or just wait? Sorry. Just making sure I'm doing this right.
AGENTYou’re doing everything right, no worries at all. To get started, I just need to verify your record. When you have a second, please tell me:
1. Your full name (first, middle if you use one, and last), and 2. Your date of birth (YYYY-MM-DD). Once I have that, I’ll look up your dermatology appointment for next Wednesday morning and we can pick a new time that works with your schedule.
CUSTOMEROkay. Um, my name's Wade Carter. No middle name. My date of birth is March 17th, 1948. Oh, wait. Sorry. That's wrong. It's 1984. March 17th, 1984. Sorry about that. I got distracted. Is that all you need?
AGENTThanks, Wade. I’ve got you pulled up with date of birth March 17th, 1984. I see your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at Main Campus, Building B. To reschedule it, what works better for you? - A different time that same day (Wednesday),
CUSTOMERThanks for confirming. Sorry, I can't do Wednesday morning at all now. Actually, I can't come till after 3 p.m. any day because of work. Is there anything open after 3 p.m.?
AGENTYes, there are some options after 3 p.m. with Dr. Okafor:
- Tuesday at 345 PM - Thursday at 4:10
CUSTOMERSorry. Tuesdays don't work after all. I pick up my daughter. Then. What about Friday? Or if that's not available, is Thursday at 4:10 p.m. still open?
AGENTYou’re all set just talking it through; I won’t change anything unless you say so. Right now, the late-day options I see with Dr. Okafor are:
- Thursday at 410 PM - Friday at 11:30 AM (this one is before 3 PM)
So for your “after 3 p.m.” requirement, the only match is Thursday at 410 PM. If you’d like, I can move your current appointment (next Wednesday at 9:15 AM) to Thursday at 4:10 PM with Dr. Okafor. Should I go ahead and reschedule it to Thursday at 4:10 PM?
CUSTOMERYeah. Ah, that. Sounds good. Please go ahead and move it to Thursday at 4:10 p.m.. Is that okay? Just want to make sure nothing gets messed up. And, um, is there any fee for changing the appointment?
AGENTI’ve gone ahead and moved it, and everything looks good. Here are your updated details, just to confirm:
- PatientWade Carter - Date of birth: March 17th, 1984 - Provider: Dr. Okafor, Dermatology - New appointment: Thursday at 4:10 PM - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2 Please arrive 15 minutes early with a photo ID and your insurance card. About fees: The clinic’s policy is that changes made more than 24 hours before the appointment are free. Changes within 24 hours have a $40 fee. Since we’re moving this ahead of time,
CUSTOMERI. Okay. Thank you for explaining that. So since we're moving it early, there's no fee, right? Sorry, just double checking. And, uh, where do I park for the main campus? Building B? Is there a specific lot or spot I should use?
AGENTYou’re correct: because we rescheduled your appointment more than 24 hours in advance, there is no fee for this change. For parking at Main Campus, Building B: - Patient parking is in Lot C. - The entrance to Lot C is on River Road. - Parking there is free for patients. Once you park in Lot C, follow the signs for Building B / Dermatology; there will be directional signs from the lot. If you’d like, I can also repeat your appointment time and confirmation code.
CUSTOMERNo, that's all right. You already gave it to me. Thanks for clearing that up. Um, last thing. Does Doctor Okafor accept Aetna insurance. Sorry. I just want to make sure everything's covered.
AGENTI don’t have access to insurance-network details for individual providers, so I can’t safely confirm whether Dr. Okafor is in-network with Aetna. Here’s how to check reliably: 1. Call the clinic’s main line and ask, “Is Dr. Okafor in-network for Aetna for dermatology visits?” 2. Or log in to your Aetna member portal / app and search for “Riverbend Health Clinic” and “Dr. Okafor” under dermatology. 3. You can also call the number on the back of your Aetna card and ask them to verify Dr. Okafor by name and the clinic’s address. If you want, I can help you draft exactly what to ask Aetna or the clinic so you can confirm coverage quickly.
CUSTOMERNo that's okay. You've given me enough info to check on my own. Sorry for all the questions. I just get nervous about missing something. So Thursday at 4:10 p.m.. Confirmation code RVB3M8P2, building B, lot C for parking. Is that all set on your end? Just want to hear you say it's definitely booked.
AGENTYes, it is definitely booked and all set on my end. You are scheduled as: - Name: Wade Carter - Date of birth: March 17th, 1984 - Provider: Dr. Okafor, Dermatology - Appointment: Thursday at 4:10 PM - Location: Main Campus, Building B - Parking: Free patient parking in Lot C (entrance on River Road) - Confirmation code: RVB-3M8P2 You’re all set, Wade. If anything changes later, just reach out and we can adjust it again.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey. Uh, sorry. I'm kind of frazzled right now.
CUSTOMERI've got a pipe busted under my kitchen sink, and water's just pouring out all over the floor. Heading straight for a power strip. Can you send somebody out?
AGENTThanks for hanging in there. Let’s get you safe first. 1. Stay away from that power strip and any outlets the water might reach. Don’t touch it. 2. If you can safely reach it without stepping in water, unplug the power strip from the wall by the plug, not by the cord. 3. If there’s already water around it or you’re not sure it’s safe, do NOT touch it. Instead, go to your breaker panel and flip the breaker for the kitchen/offending outlets, or if you can’t tell which, flip the main breaker off. Next, for the water:
4. Look under the sinkdo you see two small shutoff valves (one for hot, one for cold) on the pipes going up to the faucet? - If yes, turn both clockwise until they stop. 5. If that doesn’t slow/stop the water, or you don’t see valves, you’ll need to shut off the main water: usually - In a basement or utility room near where the water line comes in, or - Outside at a main shutoff by the street or on an exterior wall. Turn the main valve
CUSTOMERI. Uh, yeah. Okay. I see the two valves under the sink. Hang on. I'm turning them both right now.
CUSTOMEROkay, I think the water stopped. Sorry. Is that enough for now? What should I do next?
AGENTGood job getting those valves closed—that’s exactly what you needed to do. Next safety steps, quickly:
1. Stay clear of that power strip and any outlets that got splashed. 2. If there is any water near it, don’t touch it. If you can safely get to your breaker panel without going through water, switch off the breaker for the kitchen, or if you’re unsure which one, switch off the main until our tech can check it. Now I’ll get someone out to you. A couple quick questions
- Is any water still actively dripping or spraying, or is it just puddles on the floor now?
CUSTOMERI. Um. I think it's just puddles now. The water stopped after I turned those valves, but I'm a little nervous. Could you double check? That's all right.
AGENTYou did the right thing, and it is normal to feel nervous. Let’s double-check together:
1. Look under the sink again at the broken pipe area. - Do you see any water still actively dripping or spraying from the pipe or fittings? - Or is everything there just wet but not moving? 2. Look at the floor- Is the puddle staying the same size now, or is it slowly growing? If the valves are fully turned clockwise and the puddles are not growing, the leak is stopped for now. You can start laying down towels or a mop to soak up the standing water, staying away from that power strip area. I also want to get a plumber out to fix this properly. Can you tell me:
- The address where this
CUSTOMERI. Yeah. Let me check real quick.
CUSTOMEROkay. Under the sink. It's just wet. No more dripping or spraying. Floor is wet, but the puddle isn't getting bigger. So I think it stopped. Sorry. I just want to be sure that's all right. My address is 1480 Larkspur Avenue, and I'm in unit four D now. I moved from four B last month. Will that be a problem?
AGENTYou did exactly what you should, and it sounds stable now: if nothing is dripping and the puddles aren’t growing, the valves did their job. You’re okay for the moment. Two quick safety things before we book you:
- Stay clear of that power strip and any outlets that got wet. - If any water reached them, and you can get to your breaker panel without walking through water, switch
CUSTOMERAll right. I'll stay away from the power strip and I can get to the breaker panel without stepping in water. Should I flip the main breaker off or just the kitchen one if I don't know which is which. Sorry. I just want to be sure I'm not missing anything.
AGENTYou’re not missing anything—that’s exactly what you should be thinking about. Do this in order:
1. Go to the breaker panel and look for anything labeled “Kitchen,” “Counter outlets,” or similar. - If you see one that’s clearly the kitchen or the outlets by the sink, switch just that breaker OFF. 2. If nothing is clearly labeled, or you’re unsure- It’s safer to switch the main breaker OFF until we arrive. Your lights will go out, but you’ll eliminate the risk around that wet power strip/outlet area. Once you’ve done that, you’re in good shape until our tech gets there. Next,
CUSTOMERI. Okay. I'm going to go. Ahead and flip the main breaker off just to be safe. All right. Lights are out now. Sorry. Is that all right? What happens next? Can y'all send someone soon?
AGENTYes, flipping the main off is exactly right in this situation—better a dark house than a shock risk. You’ve done what you need to for now. Next is getting you on the schedule. I see you in our system at 1480 Larkspur Avenue as a Copperline Care member, and I’ve updated you to Unit 4D for this visit. We have an emergency arrival window today from 2:00 PM to 4:00 PM. Because you’re a Copperline Care member, the emergency call-out fee is $99. That covers the technician coming out, diagnosis, and an upfront estimate for the repair.
CUSTOMERI. Sorry. $99. Does that include everything, or could there be more charges? And is there any way someone can come before 2 p.m.? I've got a baby here, and I'm just kind of anxious about all this.
AGENTYou’re doing the right things, especially with a baby in the house, and it’s okay to be anxious. On the cost:
- The $99 is the emergency call‑out/diagnostic fee for Copperline Care members. - That covers the plumber coming out today, inspecting the damage, and giving you an upfront estimate. - Any actual repair work or parts would be additional, but the tech will go over prices with you before doing anything so you can approve or decline. On timing
- I’ve just rechecked our emergency schedule, and the earliest emergency arrival window we have today is 200 PM to 4:00 PM. There’s nothing available earlier showing in the system, or I’d offer it. Given you’ve:
- Shut off the hot and cold valves under the sink, and - Turned off the main breaker,
you and the baby are safe while you wait. You can keep putting down towels or a bucket under the sink if it feels better, but you don’t need to do anything with the plumbing or power until we arrive. If you’re okay with the $99 emergency fee and the 200–4:00 PM window, I’ll lock that in. Before I book it, I just need: - Best callback number for you, and - Any gate code or special instructions for getting to Unit 4D.
CUSTOMEROkay. Thank you for explaining all that.
CUSTOMERI'm all right.. With the $99. Fee and the 2 to 4 p.m. window, since that's the earliest, my call back number is (503) 555-0139.
CUSTOMERNo, sorry, 0193. And for the gate, it's pound 2719. Is that everything you need? Will I get a ticket number or something? So I know who's coming and how will I know they're on the way?
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I am safe. I'm calling from a busy cafe standing next to my car. I was stopped at a red light at SW fifth Avenue and Alder Street about 20 minutes ago, when another car hit the back of my car. No one is hurt. The back bumper is crushed and the rear wheel is rubbing, so I cannot drive it. Police did not come.
AGENTThanks for letting me know, and I’m glad no one is hurt. Since everyone is okay and not in danger, we can go ahead and get your claim started and arrange a tow for you. First, I need to locate your policy. 1. What’s your auto policy number? 2. What’s the policyholder’s last name? After that, I’ll also need:
- The other driver’s full name (as much as you have),
- Their insurance company (if you were able to get it),
- Their license plate number. And just to confirm details I heard
- Time of accidentabout 20 minutes ago, today. - Location: SW Fifth Avenue and Alder Street. - No injuries, and police did not attend, correct? Once I have your policy number and last name, I’ll verify your policy, open the claim, and then I’ll set up a tow since the rear wheel is rubbing and the car can’t be driven safely.
CUSTOMERYes, that's correct. About the accident details. My auto policy number is NG4471903. No, sorry, last one is two. The policy holders last name is Mehta. The other driver is Kevin Lund, insured with Pacific Shore. And the license plate is 7KX, like X-ray r 214. Kindly do the needful for the tow truck, please.
AGENTI’ve got everything I need, and I’m getting this taken care of now. First, just to read key details back to you:
- Verified policy numberNG4471902 - Policyholder last name: Mehta - Other driver: Kevin Lund, insured with Pacific Shore - Other vehicle license plate: 7KXR214 - Location of accident: SW Fifth Avenue and Alder Street - No injuries, and police did not attend. If any of that is not right, tell me and I’ll fix it. Now, what I’ve done for you:
1. Claim opened - Your claim number isNGM-904417 - Assigned adjuster: Priya Shah You’ll hear from your adjuster within one business day at the contact details we have on file. 2. Tow truck arranged - Tow company: Eastside Towing - ETA: about 45 minutes from now - Pickup location: SW Fifth Avenue and Alder Street (where you and the car are now) - Destination: Northgate partner repair shop at 9th and Morrison
Please stay near your vehicle but in a safe spot
CUSTOMERAha, that's right. I'll stay near the vehicle in a safe spot. Could you tell me how much do I have to pay out of pocket for this? And since he hit me, I should not have to pay a deductible, right? Also, do I get a rental car while mine is being repaired? And will my premium go up because of this accident?
AGENTI’ll walk through each of those, based only on what I can see on your policy and what typically happens. Here’s what your coverage shows: - Collision deductible: $500 - Rental coverage: $40 per day, up to 30 days, starting today (the day the claim is opened) - Towing: Covered up to 25 miles (your tow today is within that limit)
Now to your questions
1. How much do you pay out of pocket? - Your collision deductible is $500. - If we handle repairs under your collision coverage, the shop estimate
CUSTOMERBut he hit. Me so I should not have to pay that deductible, right? Since it's the other driver's fault, can you clarify if that applies here or if you can recover it from his insurance?
AGENTBased on your policy, you do have a $500 collision deductible, but whether you actually end up paying it depends on how the claim is handled and fault determination. Here’s what I can tell you, staying within what I’m allowed to say:
1. Does the $500 deductible apply right now? - If we process the damage under your collision coverage, the $500 deductible does apply up front. - That usually meanswhen the repair is billed under your policy, you’re responsible for that deductible amount, and Northgate pays the rest to the shop (subject to the estimate and coverage). 2. Since he hit you from behind, can Northgate recover it
CUSTOMERGotcha. So if Northgate. Recovers from his insurance, will the deductible be refunded to me? And do you know how long that usually takes? Also for the rental car coverage, do I need to book it myself or will someone arrange it for me?
AGENTOn the deductible and recovery, I need to stay within what I’m allowed to see and not guess at timelines, but here’s how it works in general and what I can and can’t confirm:
1. If Northgate recovers from his insurance - If Northgate is able to recover your damages from the other driver’s insurer (Pacific Shore), and your deductible is part of that recovery,
CUSTOMERRight. So if. Northgate is able to recover from Pacific Shore, then my deductible could be refunded. Understood. Can you clarify about the rental car? Will someone call me or do I need to arrange it myself? And will my premium increase because of this claim?
AGENTFor the rental car: - Your policy includes rental coverage of $40 per day for up to 30 days from today. - In most cases, once the claim is set up (which it is), the adjuster or our rental team will help set up a direct-bill rental with a partner company so you’re not paying everything up front. - You can also arrange a rental yourself if you prefer; just keep receipts. How it’s billed (directly to us vs. you first, then reimbursed up to $40/day) will be confirmed by your adjuster. - Since your claim is open under number NGM-904417, your adjuster, Priya Shah, will go over the exact rental process with you when they contact you (within one business day). On whether your premium will increase: I’m not able to see or predict any future premium changes or rating decisions from here. Premium impact depends on things like fault determination, state rules, and Northgate’s underwriting review. Your adjuster can explain how the claim is being evaluated, but they also can’t guarantee what your next renewal premium will be. To summarize: - Rental: You are covered up to $40/day for 30 days from today; your adjuster will help you with the setup details. - Premium: I can’t see or promise whether your premium will go up; that’s handled separately by underwriting at renewal. Would you like me to note on your claim that you’ll need a rental as soon as the car goes into the
AGENTshop?
CUSTOMERYes. Kindly note on. The claim that I will need a rental car as soon as my car goes into the shop. Also, I have the claim number now, so I'm all set. Thank you for your help, Alex. Goodbye.