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
#427of 655 stacks
44 / 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.
#638 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.
#636 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.
#396 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.
#528 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.
#524 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.
#595 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.
#330 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.
#544 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.
#532 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#587 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 91% | 5.03 s | — |
| Home services | 80% | 4.37 s | — |
| Insurance | 91% | 4.68 s | — |
| Customer support | 74% | 4.89 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 92% | 4.23 s | — |
| Spanish-accented English, city street | 94% | 4.79 s | — |
| Indian English, busy café | 98% | 4.55 s | — |
| Southern US, flustered, crying baby | 68% | 5.15 s | — |
| Fast and interrupting, construction outside | 69% | 4.73 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey Alex, um, sorry, I'm kind of flustered. My baby's crying right now, so I might sound a little rushed. My internet
CUSTOMERIt's been down for 2 hours and I work from home, so I'm really anxious about it. There's a road crew digging up the street outside and
CUSTOMERI wondered if that's maybe the cause. I'd already rebooted the gateway twice and checked every cable, but the internet light's blinking orange. Can you help me figure out what's going on? My account Account number is, uh, BW883017. Oh, sorry, last digit is 1. Is that okay?
CUSTOMERHello?
AGENTI’m here, thanks for hanging on. And no worries about being rushed—totally understandable.
CUSTOMEROkay, thank you. I—
CUSTOMERAlright, thanks. Just, are you sure you got the right account? It's BW—
CUSTOMERUm, yes, sorry, that should be it. Is that okay? I just want to make sure nothing gets lost.
CUSTOMERSorry, I think you missed some at the end there. It's BW883011. Could you double-check that for me? I just want to make sure we're looking at the right info.
AGENTThanks for confirming—that helps.
CUSTOMERHello?
AGENTYes, I’ve got you. I’m looking at account BW883011 and everything is pointed at the right place.
CUSTOMEROkay, good. Thank you.
AGENTI went ahead and ran all the checks while we were talking, so you shouldn’t need to do anything extra.
CUSTOMERAlright, that's a relief. Thank you. So, uh—
AGENTYou’re all set on our side now.
CUSTOMEROkay, that's good to know. Thanks, I really appreciate you—
AGENTLet me fill in the blanks—I was too quick there.
CUSTOMERSorry, just want to double-check. Shouldn't it be BW883011?
CUSTOMERThank you. I get nervous about stuff like this, so I appreciate you double-checking.
CUSTOMEROh, good. Thank you. That's a relief. So, can you tell if that road crew outside is caught—
CUSTOMEROkay, uh, sure. So about the outage, do you know if that roadwork is causing my internet to be down?
CUSTOMERAlright, thanks. I'm just— can you see anything weird on your end? The internet light's still blinking orange here.
CUSTOMEROkay, appreciate it. So, uh, is there anything showing up as a problem?
CUSTOMERAlright, thank you. So, um, do you see anything about the road crew? Is that the reason my internet's—
CUSTOMEROkay, thank you. So, is there anything else you need me to do? I already restarted the gateway twice and checked all—
CUSTOMERAlright, thanks.
CUSTOMERSo what do you see on your end? Is the outage showing up there, or do you think it's from the road crew outside?
AGENTI can see everything clearly now, and I’ll walk you through it. 1.
CUSTOMERHello?
AGENTI’m here, and I’ve got everything pulled up on my side. Here’s what I’m seeing for account BW883011:
1.
CUSTOMEROkay, thanks.
AGENTYou’re right to double‑check; we are definitely on account BW883011.
CUSTOMERAll right, thank you.
CUSTOMERThanks.
AGENTHere’s what I’m seeing on my side for account BW883011:
1.
CUSTOMERYeah, sorry, exactly right. Is everything—
CUSTOMERHey, thank you for confirming.
CUSTOMEROkay, that's good. So, um, do you see any sign of an outage, roadwork?
CUSTOMERIs there something else?
CUSTOMERAll right, appreciate it.
CUSTOMERSo, uh, what—
CUSTOMERThank you for double-checking. So, is there anything showing up as a problem on your end? I'm just anxious to get back online.
AGENTI’ve already run all the checks on account BW883011, so let me give you a clear picture.
CUSTOMERAnything about the outage or the— I'm just trying to Trying to figure out.
CUSTOMERI just really need to get back online. If you can see anything about it.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, uh, yes, my name is Lucia Ramirez. I have a dermatology appointment next Wednesday morning, but I just found out I have to work then. I need to move that appointment, please. I can only come after 3 PM.
AGENTI can help with that. I’ll just need to verify your record first. Please tell me:
- Your full name as it appears on your ID (I have “Lucia Ramirez,” is that correct?), and
- Your date of birth (YYYY-MM-DD).
CUSTOMERAha, yes, Lucia Ramirez is correct. My date of birth is March 17th, 1948— sorry, no, 1984. March 17th, 1984.
AGENTThanks, Ms. Ramirez. I have you verified as Lucia Ramirez, date of birth March 17, 1984. I see your dermatology visit with Dr. Okafor scheduled for next Wednesday at 9:15 AM at Main Campus, Building B. You mentioned you can only come after 3 PM. With Dr. Okafor, the next available options after 3 PM are:
- Tuesday at 345 PM
- Thursday at 410 PM
Friday’s slot is at 1130 AM, which is before 3 PM, so that won’t work with your schedule. Which would you prefer: Tuesday at 3:45 PM or Thursday at 4:10 PM with Dr. Okafor?
CUSTOMERHmm, Tuesdays don't work after all. I pick up my daughter then. What about Thursday at 4:10 PM? That's good for me.
AGENTYou’re all set, Ms. Ramirez. I’ve moved your dermatology appointment with Dr. Okafor from next Wednesday at 9:15 AM to:
- Thursday at 410 PM, Main Campus, Building B
- New confirmation codeRVB-3M8P2
Please arrive about 15 minutes early with a photo ID and your insurance card. Anything else I can help you with today—like directions or parking info for Building B?
CUSTOMERYes, actually, is there a fee for changing the appointment? And where should I park for Building B? Also, does Dr. Okafor accept Aetna insurance?
AGENTFor your questions:
1) Change fee
Your change was made more than 24 hours before your appointment, so there is no fee. The $40 fee only applies to changes made within 24 hours of the visit. 2) Parking for Building B
You can park in Lot C, which has free patient parking. The entrance to Lot C is on River Road. From Lot C, follow the signs to Building B.
CUSTOMEROkay, got it. So no fee if it's changed ahead of time, and I should park in Lot C off River Road. About Aetna, could you tell me who I should contact to check if Dr. Okafor Accepted. And, uh, could you please read back the new appointment time and confirmation code just to be sure?
CUSTOMERUh-huh, okay. Could you give me the phone number for the billing insurance line? And, uh, if you could just confirm my new appointment time and the confirmation code again, please.
AGENTTo check Aetna coverage for visits with Dr. Okafor, you have two good options:
- Call Riverbend’s billing/insurance line, or
- Call the member services number on the back of your Aetna card and ask if Dr. Okafor at Riverbend Health Clinic is in-network for your specific plan. I don’t have the billing/insurance phone number in this system, so please use the main Riverbend Health Clinic number on your reminder text/email or our website and choose the billing/insurance option from the phone menu. They can confirm Aetna details for you.
CUSTOMER84. Dermatology appointment with Dr. Okafor, Main Campus, Building B, Thursday at 4:10 PM. Confirmation code: RVB3MHP2. Is that right?
AGENTAlmost—just a couple of small corrections. Your verified details are:
- Name and DOBLucia Ramirez, date of birth March 17, 1984
- Provider and locationDermatology with Dr. Okafor, Main Campus, Building B
- New appointment timeThursday at 4:10 PM
- Confirmation codeRVB-3M8P2
- That’s R–V–B–3–M–8–P–2 (there is an “8” after the M, not an “H,” and there is a dash after “RVB”). You mentioned wanting the billing/insurance phone number earlier. I don’t have direct access to phone numbers in this system, so please call the main Riverbend Health Clinic number (on your reminder or our website) and select the billing/insurance option from the menu; they can confirm Aetna coverage for visits with Dr. Okafor.
CUSTOMEROkay, understood. Thursday at 4:10 PM. Confirmation code: RVB-3M8P2. I'll call the main number and ask For billing insurance about Excellencia. Thanks for your help!
AGENTYou’ve got it exactly right:
- Thursday at 410 PM
- Dermatology with Dr. Okafor, Main Campus, Building B
- Confirmation codeRVB-3M8P2
And yes, calling the main number and asking for billing/insurance to check on your Aetna/Excellencia coverage is the right next step.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, I've got a plumbing emergency. The pipe under my kitchen sink just burst and water is spreading across the floor heading toward a power strip. I haven't shut the water off yet. Can you help?
AGENTYes, I can help.
CUSTOMERGreat. Could you tell me how to shut the water off first? I want to make sure the leaking stops before anything else.
AGENTFirst, stay safe:
1. Unplug the power strip immediately if you can do so without stepping in water. - If the floor around it is already wet, do not touch the strip or any cords. - Keep everyone (kids, pets) away from that area. 2.
CUSTOMERGot it.
CUSTOMEROkay, I'm listening. Go ahead.
CUSTOMERRight, could you explain what I need to open?
AGENTGood—let’s get that water stopped and keep you safe. First, about the power strip:
- If any water has reached or is very close to the power strip, do not touch it or anything plugged into it.
CUSTOMERUnderstood.
CUSTOMERYeah, I'll make sure to keep clear. So about shutting off the water, can you walk me through how to do that?
AGENTGood. Let’s get the water shut off step by step. First, we’ll try to shut off just the kitchen sink. If that doesn’t work, we’ll go to the main shutoff.
CUSTOMEROkay, I see the valves. What should I do next? Okay, I see them. What do I do next?
AGENTGood.
CUSTOMERRight, should I turn those valves to shut off the water?
AGENTYes.
CUSTOMERAll right.
CUSTOMEROkay, go ahead.
AGENTYes—those are what shut the water off to the sink. Here’s exactly what to do:
1. Locate the two small valves under the sink
- One is for hot (usually left), one for cold (usually right). - Each will have either a small round/oval knob or a little lever. 2. Turn both valves fully off
- If they’re round knobsturn each one clockwise (to the right) until it stops. - If they’re lever-style: turn each lever so it’s across the pipe (perpendicular), not in line with it. 3. Test the faucet
- Turn the kitchen faucet on (both hot and cold) and let it run. - It should slow to a trickle and then stop. - If water keeps running strongly after 10–15 seconds, tell me—it means we need to shut off the main water. While you’re doing that, stay clear of that wet area near the power strip. If the water is still spreading toward it, let me know how close it is now (in feet or just “almost there / touching”).
CUSTOMERAll right, I've turned both valves off and the water from the faucet has stopped. The water on the floor isn't touching the power strip yet, but it's maybe a foot away. What should I do next?
AGENTGood job getting the water stopped—that’s the most important part. Next, safety and cleanup:
1. Stay clear of the power strip area. - If you can safely do it without stepping in water, you may unplug the power strip from the wall and move it to a dry area. - If you’d have to step in water or reach over water to do that, leave it alone until a professional can safely deal with it. 2. Start mopping up the water. - Use towels, a mop, or a wet/dry vac if you have one. - Focus first on keeping the water from reaching that power strip—build a “towel dam” between the puddle and the strip. - Wring towels into a bucket or sink that’s not affected. I also want to get a plumber out to you as soon as possible.
CUSTOMERYeah, the address is 1480 Larkspur Avenue, Unit 4D. I moved from 4B to 4D last month.
AGENTThanks for the update on the valves and the address—glad the water is stopped. First, just a couple of quick safety/cleanup steps, then I’ll go over the visit details:
1. Keep that power strip dry
- If you can reach the wall outlet without stepping in water, go ahead and unplug the power strip and move it to a dry area. - If you’d have to stand in or reach over water, leave it where it is and just keep your “towel dam” between the water and the strip. 2. Keep soaking up water
- Keep using towels/a mop to pull water away from cabinets, walls, and that outlet/strip area. - Wring towels into a dry sink or tub. This helps prevent swelling of cabinets and flooring. Now I’ve opened an emergency plumbing ticket for you and checked availability. - You’re a Copperline Care member, so your emergency callout fee is $99. That covers the dispatch and diagnosis; any repair options would be quoted on-site before work is done. Earliest emergency window I can offer
- Today, 200 PM to 4:00 PM arrival window
Your service request
- Ticket numberCPL-58210
- Service address1480 Larkspur Avenue, Unit 4D
I don’t have a callback number or any gate/access notes on this ticket yet. 1. What’s the best phone number to reach you? 2.
CUSTOMERMy call—
CUSTOMERYeah, my callback number is 503-555-0139— no, 0193. Is there anything else you need for the ticket?
AGENTGot it, I’ve updated the callback to 503-555-0193.
CUSTOMERAll right.
CUSTOMERYeah, about the gate. If you need it, the gate code is #2719. Will that be included for the plumber?
AGENTYes, I’ve added that. Here’s what we’ve got now:
- TicketCPL-58210
- Address1480 Larkspur Avenue, Unit 4D
- Gate/access notes“Gate code #2719”
- Callback number503-555-0193
- Arrival windowtoday, 2:00 PM to 4:00 PM
- Emergency callout fee (with your Copperline Care membership)$99
The plumber will see the gate code on the work order, and they’ll text your 503-555-0193 number about 30 minutes before arrival. While you’re waiting
- Keep that area as dry as you can with towels. - Stay clear of the power strip area if any water gets close; don’t touch it if the floor around it is wet. If anything changes—like the leak starts again or water reaches the outlet area—tell me right away.
CUSTOMERGotcha. Who will be coming out? Do you know the plumber's name or company? And just to confirm, the emergency callout fee is $99, right?
AGENTYou’re correct on the fee, and I’ll explain what I can about who’s coming. - Emergency callout fee: $99
- That’s your Copperline Care member emergency rate. - It covers the dispatch and diagnosis; any repair work and parts will be quoted for your approval before they proceed. For who’s coming
- The visit is booked directly with Copperline Home Services; it’s our own plumbing technician, not a third-party company. - I don’t have permission to give out the technician’s name from the scheduling system here, but
- They’ll be a Copperline plumber. - They’ll text your number (503-555-0193) about 30 minutes before arrival so you know they’re on the way. Let me read everything back once more so you’re fully set
- Ticket numberCPL-58210
- Service address1480 Larkspur Avenue, Unit 4D
- Gate code#2719
- Callback503-555-0193
- Arrival windowtoday, 2:00 PM to 4:00 PM
- Emergency callout fee$99
While you wait, just keep that area as dry as possible and avoid the outlet/power strip if water gets close.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I'm safe. I'm just standing next to my car.
AGENTI’m glad you’re safe. Is anyone injured at all—either in your car or the other vehicle—or is anyone in danger right now? If anyone is hurt or in danger, please hang up and call 911 immediately before we continue.
CUSTOMERNo, nobody is hurt and there's no danger. I just need help with the claim.
AGENTUnderstood, I’ll help you get the claim started. First, I’ll need to locate your policy. 1) What’s your auto policy number? 2) And the policyholder’s last name as it appears on the policy? After that, I’ll ask you when and where the accident happened and what occurred.
CUSTOMERSure, my policy number is NG4471903. No, sorry, last one is 2. The last name is Ellis.
AGENTThanks, I’ve pulled up your policy ending in 1902 under Ellis for a 2021 Honda CR‑V. Now I’ll open the claim. I need a few details:
1) When did the accident happen? 2) Where did it happen? 3) Can you briefly describe what happened? 4) Do you have the other driver’s name, their insurance company, and their license plate number? 5) Did the police come to the scene, and is there a report number?
CUSTOMERThe accident happened about 20 minutes ago. I was stopped at a red light at SE 5th Avenue and Alder Street. Another car hit the back of mine. The back bumper is crushed and the rear The wheel rubs, so I can't drive it. The other driver is Kevin Lund, insured with Pacific Shore. His plate is 7KX, like x-ray, R214. Police did not come, so there's no report number.
AGENTI’ve got everything I need to get you taken care of. Here’s what I have on file—let me read key details back to you:
- Policy numberNG4471902
- Other driverKevin Lund, insured with Pacific Shore
- Other vehicle plate7KXR214
- LocationSE 5th Avenue and Alder Street
- DescriptionYou were stopped at a red light and were rear‑ended. Your rear bumper is crushed and the rear wheel is rubbing, so the vehicle is not drivable. - No police response and no report number. Your claim is now open. Your claim number is: NGM-904417. Your assigned adjuster is Priya Shah; you should hear from her within one business day. On coverage, based on your policy:
- Collision deductible$500
- Rental car$40 per day for up to 30 days, starting today (the day the claim is opened)
- TowingCovered up to 25 miles
Because the wheel is rubbing, the car isn’t safe to drive.
CUSTOMEROkay.
CUSTOMERWhere will my car be taken?
AGENTYour tow is already set up. Your car is being taken to a Northgate partner repair shop at 9th and Morrison. If you’d prefer a different shop later, you can let your adjuster, Priya Shah, know when she contacts you about claim NGM-904417, and we can redirect the vehicle if needed.
CUSTOMERAll right, that's clear. About the deductible, he hit me, so I should not have to pay that, right? And will my premium go up because of this?
AGENTHere’s how it works under your policy:
1) Deductible
Your policy shows a $500 collision deductible.
CUSTOMERGotcha.
CUSTOMERRight, so how much would I owe if his insurance covers it? And what about my premium? Is it going to go up?
CUSTOMEROkay.
CUSTOMERGo ahead.
AGENTI’ll break it into two parts: what you might owe, and what might happen with your premium. 1) What you’d owe if his insurance pays
- If Pacific Shore (the other driver’s insurer) accepts full liability and pays for your repairs directly, you typically would not end up paying your $500 collision deductible. - If we pay for your repairs first under your collision coverage, we would apply your $500 deductible. Then, if we recover that money from Pacific Shore, we generally reimburse your deductible (in whole or in part, depending on what we recover). - So if he’s clearly at fault and his company pays the full loss, your out‑of‑pocket cost is often $0 in the end. The exact amount depends on
- Whether they accept 100% fault
- How much we’re able to recover from them
- The final repair costs versus your coverage
Your adjuster, Priya Shah, will confirm which coverage is being used and how the deductible will apply once she speaks with you and reviews the facts. 2) Will your premium go up? I can’t quote or guarantee future premium changes here at claims intake. Rate changes depend on
- How the accident is classified (at‑fault vs. not‑at‑fault)
- State regulations and Northgate’s rating rules
- Your prior driving and claims history
Generally
- If you’re found not at fault (for example, rear‑ended while stopped, as you described), that is less likely to cause a premium increase than an at‑fault accident, but it can still be a factor depending on state rules and company guidelines. - Only the underwriting/rating team can determine if and how this claim will affect your premium at renewal. Your best next step
- When Priya contacts you about claim NGM-904417, ask her
1) “Will this be handled through my collision coverage or directly through Pacific Shore?”
CUSTOMERRight.
AGENTTo your two questions, as clearly as I can:
1) How much would you owe if his insurance covers it? - If Pacific Shore accepts 100% fault and pays the full cost of repairs directly, you typically would not end up paying your $500 collision deductible. - If we pay first under your collision coverage, we would apply the $500 deductible. Later, if we recover that money from Pacific Shore, we usually reimburse your deductible (all or part, depending on what we recover and how fault is decided). - So if he’s clearly at fault and his company ultimately pays everything, your out‑of‑pocket often ends up being $0, but it depends on
- Whether they accept full liability
- How much is recovered from them
- Final repair costs vs. your coverage
Your adjuster, Priya Shah, will confirm exactly how your deductible is being applied once she reviews both sides’ information. 2) Will your premium go up? I can’t see or predict premium changes from here in claims intake. Any change at renewal depends on things like
- How this accident is classified (at‑fault vs. not‑at‑fault)
- State regulations and Northgate’s rating rules
- Your overall driving and claims history
Being rear‑ended while stopped is generally treated as not‑at‑fault, which is usually better for your premium than an at‑fault accident, but underwriting is the only group that can say for sure whether it will affect your rate. When Priya contacts you about claim NGM-904417, I’d suggest asking her
- “Are you pursuing payment directly from Pacific Shore, or using my collision coverage?” - “If you recover from them, will my $500 deductible be reimbursed?” - “Can someone from underwriting tell me if this not‑at‑fault claim could affect my premium at renewal?”
Is there anything else about the process—repairs, rental car, or the tow—that you want me to walk through while you’re still at the scene?