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
#257of 655 stacks
50 / 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.
#506 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.
Not scored by this sweep.
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.
#446 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
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.
#482 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.
#457 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.
#529 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.
#298 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.
#535 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.
#289 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.
#473 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 | 91% | 3.80 s | — |
| Home services | 82% | 3.54 s | — |
| Insurance | 88% | 3.50 s | — |
| Customer support | 95% | 3.38 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 92% | 3.51 s | — |
| Spanish-accented English, city street | 77% | 3.60 s | — |
| Indian English, busy café | 92% | 3.74 s | — |
| Southern US, flustered, crying baby | 96% | 3.72 s | — |
| Fast and interrupting, construction outside | 87% | 3.33 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, uh— Sorry, I'm a little flustered. I work from home and my internet's been down for about 2 hours now. My baby's crying, so I'm a bit distracted. There's a road crew digging right outside. outside, and I'm wondering if that's got something to do with it. I already rebooted the gateway twice and checked every cable. The internet light's blinking orange. Can you check what's going on? My The account number is BW883017.
CUSTOMERSorry, last digit is 1. Is that enough for you to pull it up?
AGENTYou’re all set—I can work with that account number BW883011. Here’s what I’m seeing and what I did for you: - No area outage at your address. - Your line signal looks good, but the gateway wasn’t registered. - I pushed a remote reset to your Brightwave BX7, and it’s now showing as registered and online on my side. Your devices may take up to 2 minutes to fully reconnect. While you’ve got your hands full: 1. Just glance at the gateway: the internet light should go from blinking orange to a solid light (usually white/green). 2. On your work computer/phone, try a quick test site like `example.com` or run a speed test once it’s back. Can you check: - What color/state the internet light is showing now? - If at least one device (laptop/phone) can get online?
CUSTOMERI just look the internet light. Wait till everything's back up and my devices reconnect. I really need to get back to work.
AGENTOn my end your gateway at account BW883011 is online now, so you should be coming back up as your devices reconnect. Since you’re in a hurry, just do these two quick checks when you can glance over: 1. Confirm the internet light is solid (not blinking orange). 2. Try loading any website on your work device. If either: - the light stays blinking orange after a few minutes, or. - none of your devices can get online, tell me exactly which of those is happening and I’ll move straight to the next step (likely a technician, since the line and modem both look good now).
CUSTOMERAnd my laptop's loading websites again, so I think it's all set now. I wanted to ask, since my internet was down for 2 hours and I lost work time, could I get a credit for the downtime?
AGENTYes, I can do that. I’ve applied a $10.00 service credit on account BW883011 for about 2 hours of downtime. You’ll see it on your next bill. Since everything’s back up and your laptop is loading sites again, you should be good to work. If the connection drops again—especially with that road crew out front—come back and tell me exactly what the lights are doing and I’ll jump straight into testing/scheduling a tech.
CUSTOMERI appreciate the credit, but I lost 2 hours of work, so is there any way you could make it more than $10? Sorry to be a bother. I just want to make sure it covers what I missed.
AGENTI get why you’re asking—losing two hours of paid work is a big deal. On my side, I’m limited to applying the standard downtime credit, which I’ve already done: $10.00 on account BW883011, showing on your next bill. I don’t have the ability to increase that amount or approve exceptions. If you want to push for a larger adjustment, the best option is to contact Billing/Customer Care by phone or chat through your Brightwave account portal—they can review your history and see if they can do more as a one-time exception. If you’d like, I can help you draft exactly what to say to them so you don’t have to think about it while you’re juggling work and the baby.
CUSTOMERRight, I understand you've got limits. I'll reach out to billing if I need to. Thanks for helping me get back online so fast. I really appreciate it. Okay, I gotta go. Bye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, yes, um, I need to reschedule my dermatology appointment. It was set for next Wednesday morning, but I have a work shift now, so I can't make it. My name is Lucia Ramirez.
AGENTI can help with that. I’ll just need to verify your record first. Please tell me: - Your full name as it appears with the clinic (first, middle if you use one, and last), and. - Your date of birth (YYYY-MM-DD). Once I have that, I’ll look up your dermatology appointment for next Wednesday and then we can find a new time that works for you.
CUSTOMERSure. My full name is Lucia Ramirez. My date of birth is March 17th, 1948. Sorry, no, 1974. March 17th, 1974.
AGENTThanks, Ms. Ramirez. I have you as Lucia Ramirez, born 1974-03-17, verified. I see your dermatology
CUSTOMERJust to clarify, my birth year is 1984, not '74. Is that all right? So I need to move my appointment. I can only come after 3 PM.
AGENTThanks for the correction. I have you as Lucia Ramirez, born 1984-03-17, verified. You mentioned you can only come after 3 PM. With Dr. Okafor, the next available options after 3 PM are: - Tuesday
CUSTOMEROkay, I'm listening. What are the available times?
AGENTFor Dr. Okafor, the next available times that are after 3 PM are: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. Both are standard dermatology visits at the Main Campus, Building B. Which would you prefer: Tuesday at 3:45 PM or Thursday at 4:10 PM? Once you choose, I’ll move your existing “next Wednesday 9:15 AM” appointment and read back the new details.
CUSTOMEROh, Tuesdays don't work actually. I pick up my daughter then. What about Friday? If not, Thursday at 4:10 PM is good.
AGENTI checked Friday for you—Dr. Okafor only has an 11:30 AM slot that day, which is before 3 PM,
CUSTOMERHello?
AGENTI’m here—thanks for waiting. I went ahead and moved your dermatology visit to the time you said would be good. Here
CUSTOMERAll right then, let's go.
AGENTYou’re all set, Ms. Ramirez. I’ve rescheduled your dermatology appointment with Dr. Okafor
CUSTOMERRight.
AGENTLet me read everything back so we’re on the same page: - Patient: Lucia Ramirez,
CUSTOMERCan you read back the new time and the confirmation code for me?
AGENTHere are the details: - Patient: Lucia Ramirez,
CUSTOMERYes, that's right.
AGENTHere are your updated appointment details: - Patient: Lucia Ramirez. - Date of birth: 1984-03-17.
CUSTOMERYes, that's correct. Can you please continue with your point?
AGENTContinuing with the key details of your rescheduled
CUSTOMERSorry, it's Lucia Ramirez. My date of birth is March 17th.
CUSTOMEROkay, go ahead.
AGENTThanks, Ms. Ramirez. Let me read everything back clearly. - Patient: Lucia Ramirez.
CUSTOMERHello?
AGENTThanks for your patience, Ms. Ramirez. Here
CUSTOMERYes, that's right.
AGENTThanks for staying on the line, Ms.
CUSTOMEROkay, can you read back the new appointment time?
AGENTYes. Here are your updated appointment details: - Patient: Lucia Ramirez. - Date of birth: March 17th, 1984. - Provider:
CUSTOMERSo I have Thursday at 4:10 PM. Right.
AGENTYes, that’s correct. You are scheduled for: - Day: Thursday. - Time: 4:10
CUSTOMERThat's correct.
AGENTPerfect, we’re on the same page. Here are the key details, read back clearly: - Patient: Lucia Ramirez. - Date of birth: March 17th, 1984. - Provider:
CUSTOMER4:10 PM.
AGENTCorrect: your new dermatology appointment is on Thursday at 4:10 PM with Dr. Okafor, at Main Campus, Building B. Your confirmation code is RVB-3M8P2.
CUSTOMERDr. Okafor. Yes, that's right.
AGENTExactly: - Patient: Lucia Ramirez. - Date of birth: March 17th, 1984. - Provider: Dr. Okafor.
CUSTOMERCould you repeat the confirmation code, please?
AGENTYour confirmation code is RVB-3M8P2.
CUSTOMERDr. Okafor? Yes, that's right. And, uh, what is it?
AGENTYou’re seeing Dr. Okafor on Thursday
CUSTOMERGot it. RVB-3M8P2. Just a quick question, is there a fee for changing the appointment?
AGENTThere’s no
CUSTOMERRight, but is there a fee for changing the appointment?
AGENTNo, there isn’t a fee for this change. Riverbend’s policy is: changes made more than 24
CUSTOMERMm-hmm. Where should I park for the appointment?
AGENTFor your appointment with Dr. Okafor at the Main Campus, Building B: you can use the free patient parking in Lot C, with the entrance on River
CUSTOMEROkay, so where do I park when I come for the appointment?
AGENTWhen you come
CUSTOMERGot it. Lot C. And that's Dr. Okafor, except—
CUSTOMERDoes Dr. Okafor accept Aetna insurance?
AGENTI don’t have insurance-plan details for individual providers in this system,
CUSTOMERHello?
AGENTI’m here. I don’t have insurance-plan details for individual providers in this system, so I can’t see directly whether Dr. Okafor accepts Aetna. To confirm that for sure, you have two
CUSTOMEROkay, can you check?
AGENTI’m not able to look up insurance participation for individual providers in this system, so I can’t directly check whether Dr. Okafor accepts Aetna. To get an accurate
CUSTOMERAll right, is there a way I can check with your—
AGENTYes. The best ways to check whether Dr. Okafor accepts Aetna are: 1. Call the clinic’s main line and ask about insurance for Dr.
CUSTOMEROkay, I understand. Thank you for
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, uh, I need help fast. The pipe under my kitchen sink just burst and water's spreading across the floor toward a power strip. I haven't shut the water off yet. Could you help me with this?
AGENTYes, I can help you with this right now. First, safety: 1. Stay away from the power strip and any outlets the water is reaching or about to reach. - Do not touch the power strip or anything plugged into it. - If it’s safe and dry to do so, unplug the power strip from a dry section of the cord. If any part is wet or you’re not sure, leave it alone. 2. Shut off the water: - Look under the kitchen sink for two small shutoff valves (one for hot, one for cold) on the pipes going to the faucet. - Turn each valve clockwise until it stops. - If you can’t find or can’t turn those valves, go to your main water shutoff: - Often in the basement, garage, utility room, or near where the water line enters the house. - Turn the main valve clockwise to shut off the water to the whole house. Please tell me: - Are you able to reach the under-sink valves safely without stepping in water near that power strip? - Have you shut anything off yet? While you’re doing that, don’t stand in water that’s near any outlets, appliances, or the power strip. If water has already reached outlets or the strip and you can’t avoid standing in it, step back to a dry area and wait; we’ll treat this as an emergency. Once you’ve either: - Turned off the under-sink valves, or. - Turned off the main, or. - Found that you can’t safely
CUSTOMEROkay, I'm staying away from the power strip. I can reach the shutoff valve without stepping in water. I'm turning the valves now. Yes, the water has stopped. What should I do next?
AGENTGood job getting the water stopped and staying clear of the power strip. Next, a couple of quick
CUSTOMERYeah.
CUSTOMEROkay, go ahead. What else should I do?
AGENTNext steps for safety and damage control: 1. Keep clear of the power strip and any wet outlets. - Don’t touch the strip or anything plugged into it. - If water is close to the strip, leave it alone until a professional can check it. 2. Start cleanup to
CUSTOMEROkay, how should I do the cleanup?
AGENTSince the water is off and you can stay clear of that power strip, here’s how to handle cleanup safely: 1. Stay safe around electricity. - Keep at least several feet of distance between any standing water and the power strip/outlets. - Don’t unplug or move the strip if any part of it or the cord is wet or in the water. Just leave it alone. 2. Get the standing water up. - Use towels,
CUSTOMERAnd
CUSTOMERMm-hmm, so just use towels, right? I can do that. What else should I do?
AGENTYes, towels are perfect. Blot and wring them into a sink or tub until you’ve got most of the water up. Next steps: 1. Protect your cabinets and floor. - Open the cabinet doors under the sink so the area can dry out. - If you have a fan, aim it toward the open cabinet and wet floor (but don’t put the fan in any water, and plug it into an outlet far from the wet area). - If you have any rugs that got wet, pick them up and hang them to dry. 2.
CUSTOMERRight, what's the second step?
AGENTSecond step is to get a plumber on the way so the pipe is properly repaired and you don’t get another leak. Since you’ve got an active leak under the sink that already spread across the floor, we should treat this as an emergency visit. Because you’re a Copperline Care member, your emergency callout fee is $99, and you’d pay by card or check on completion. Parts and labor for the repair would be additional once the plumber sees exactly what failed. The earliest emergency window I can offer is today, 2:00 PM to 4:00 PM. Do you want me to book that 2–4 PM emergency window at: 1480 Larkspur Avenue, Unit 4B, with the $99 Copperline Care emergency callout fee? And what’s the best callback number for you in case the technician needs to reach you?
CUSTOMERActually, I moved last month. I'm at Unit 4D now, not 4B. Same address, 1480 Larkspur Avenue. And for the callback, it's 503-555- 0139— no, sorry, 0193. About the time, uh, can anyone come before 2? The water spread pretty far.
AGENTThanks for the updates—that
CUSTOMERHello?
CUSTOMEROkay, so can anyone come earlier than 2 PM, or is that the earliest? And who will be coming out, and how will I know when they're on the way? Also, can I get the ticket number for this?
AGENTThe 2:00–4:00 PM emergency window today is the earliest we have; there’s nothing sooner showing on my end right now. You’re all set, though—I’ve booked this as an emergency visit. Here are the details: - Arrival window: today, 2:00 PM to 4:00 PM. - Service address: 1480 Larkspur Avenue, Unit 4D. - Callback number: 503-555-0193. - Ticket number: CPL-58210. - Fee: As a Copperline Care member, your emergency callout is $99. Parts and labor for the actual repair are additional and will be reviewed with you on site. For your other questions: - Who’s coming: A licensed Copperline emergency plumber will be dispatched on this ticket. - How you’ll know they’re on the way: You’ll get a text to 503-555-0193 about 30 minutes before arrival. Quick recap of what to do until they arrive: - Keep away from the power strip and any wet outlets; don’t
CUSTOMERGot it. Thanks for all your help. Goodbye.
AGENTYou’re welcome. I’m glad you got the water stopped—help is on the way. Just to confirm
AGENTyour details before we hang up: - Service address: 1480 Larkspur Avenue, Unit 4D. - Callback number: 503-555-0193. - Ticket number: CPL-58210. - Arrival window: today, 2:00–4:00 PM. If anything changes with the leak or the power strip before we arrive, stay clear of the water and outlets and call us right back. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I'm somewhere safe. I'm standing next to my car. It's not drivable, but no one was hurt. I was stopped at a red light and another driver hit the back of my car. Can I give you the details?
AGENTI’m glad to hear no one was hurt. Since the car isn’t drivable, we’ll also look at getting you a tow once we have the basics. Yes, please
CUSTOMERAll right.
CUSTOMERSure.
AGENTOkay, let’s walk through this step by step. First, I’ll need to verify
CUSTOMERThat works.
CUSTOMERGo ahead, I'm ready.
AGENTGreat, thank you. Let’s start with your policy so I can pull up your information. 1) What’s your auto policy number with Northgate Mutual? 2) And the policyholder’s last name, please?
CUSTOMERMy policy number is NG4471903. No, sorry, last one is 2. And the policyholder's last name is Ellis.
AGENTThanks, I’ve got your policy pulled up: NG4471902 under the name Ellis. Let’s get the accident details. 1) When did the accident happen? - Date and approximate time, please. 2) Where did it happen? - City and state, and if you know it, the street or intersection. 3) You mentioned you were stopped at a red light and were hit from behind. - Is that a good brief description of what happened, or is there anything you want to add? 4) Information about the other driver: - Their name. - Their insurance company (if you were able to get it). - Their license plate number. 5) Did the police come to the scene? - If yes, do you have a report number or officer’s name? And since you said the car
CUSTOMERThe accident happened about 20 minutes ago at SE 5th Avenue and Alder Street in Portland, Oregon. I was stopped at a red light and another driver hit the back of my car. That description is accurate. The other driver is Kevin Lund, insured with Pacific Shore. His license plate is 7KXR214. X like X-ray. Police did not come to the scene, so there's no report number or officer's name.
AGENTI’ve got everything I need to open the claim, and I’ve started a tow for you since the car isn’t drivable. Here’s what I have on file: - Policy number: NG4471902. - Vehicle: 2021 Honda CR‑V. - What happened: You were stopped at a red light at SE 5th Avenue and Alder Street in Portland, Oregon, when you were rear‑ended by another driver. - Other driver: Kevin Lund, insured with Pacific Shore, license plate 7KXR214. - No injuries and police did not attend the scene. I’ve opened your claim: - Claim number: NGM-904417. - Assigned adjuster: Priya Shah – you’ll hear from her within one business day. Your coverage for this policy: - Collision deductible: $500. - Rental car: $40 per day for up to 30 days, starting today. - Towing: Covered up to 25 miles. Tow details: - Tow company: Eastside Towing. - ETA: about 45 minutes. - They’re taking the car to our Northgate partner repair shop at 9th and Morrison. Let me read back the key numbers once more so you can note them down: - Policy number: NG4471902. - Other driver’s plate: 7KXR214. - Your claim number: NGM-904417. Would you like to use your rental coverage right away once the car is at the shop, or wait to speak with the adjuster first?
CUSTOMERI'd like to use the rental coverage right away, once the car is at the shop. About the deductible, since he hit me, I shouldn't have to pay that, right? And is my premium going to go up because of this?
AGENTYou can absolutely use the rental right away. Once the car is checked in at the shop, you can arrange a rental up to $40 per day, for up to 30 days, under this claim NGM-904417. On your questions: 1) Deductible. Based on your policy, you do have a $500 collision deductible. How that plays out depends on fault and how the claim is handled: - If we repair your car under your collision coverage first: - The $500 deductible applies up front. - If the other driver (Kevin Lund / Pacific Shore) is found at fault and his insurer pays us back, we will seek to recover your deductible from them. - If we successfully recover it, we reimburse you for all or part of that $500, depending on what we collect. - If the other driver’s insurance handles the repairs directly: - Typically you would not pay your Northgate deductible at all, because your policy wouldn’t be used for the repairs. - Whether they charge you anything depends on Pacific Shore’s handling, but usually, when their driver is clearly at fault, they pay the full repair cost with no deductible to you. Your adjuster, Priya Shah, will confirm which route makes the most sense and go over exactly when (or if) you’d actually have to pay that $500. 2) Will your premium go up? I can’t see or quote future premium changes from here, and we don’t make rate decisions at the claims desk. What I can tell
CUSTOMERUnderstood.
CUSTOMERRight, go ahead.
AGENTOn the two points you asked about—deductible and premium—here’s the clean summary: 1) Deductible. - Your policy has a $500 collision deductible. - If Northgate repairs your car under your policy, that deductible applies up front. - If the other driver is confirmed at fault and Pacific Shore reimburses Northgate, we will try to recover your $500 and refund it to you if we’re successful. - If Pacific Shore handles the whole repair directly, your Northgate deductible would typically not come into play. 2) Premium changes. - I can’t see or decide future premium changes from here. - In general, rear-end collisions where you’re hit from behind are often treated as “not at fault” for the front driver, but the final determination is made by the adjuster and underwriting, not by me. - Your adjuster, Priya Shah, will review fault, how the claim is paid, and how that may affect your policy, and can give you more specific guidance. For the rental: - You’re covered up to $40 per day for up to 30 days. - Once your car is at the shop on 9th and Morrison, you can start that right away under claim NGM-904417. The shop or your
CUSTOMERBut that's
CUSTOMERGot it. The shop on 9th and Morrison. I'll wait for the tow. I've noted the claim number: NGM-904417. Thanks for walking me through everything. Goodbye.