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
#298of 655 stacks
49 / 100
Leader AssemblyAI Universal-3.5 Pro + OpenAI GPT-6.1 Sol + ElevenLabs Turbo v2.5, 70 / 100
Where it ranks
Its models
Task completion
Task completion
How much of the caller’s task the agent completed: the share of the scenario’s checks a judge model found met in the transcript, averaged over calls. Before v1.3, the share of calls judged 4 or better out of 5.
#333 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.
#289 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.
#591 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.
#339 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.
#579 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.
#600 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.
#590 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.
#67 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.
#371 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#44 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 91% | 2.87 s | — |
| Home services | 88% | 2.19 s | — |
| Insurance | 98% | 2.89 s | — |
| Customer support | 89% | 3.10 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 87% | 2.73 s | — |
| Spanish-accented English, city street | 94% | 3.34 s | — |
| Indian English, busy café | 92% | 3.12 s | — |
| Southern US, flustered, crying baby | 89% | 2.91 s | — |
| Fast and interrupting, construction outside | 96% | 2.27 s | 94% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi, Alex. Oh, yeah. I'm calling because my internet has been down for two hours now. I work from home and there's a road crew digging up the street outside, so I'm wondering if that's the cause. I already rebooted the gateway twice.
CUSTOMERAnd checked all the cables. The infinite light is blinking orange.
CUSTOMERCan you help me get it back online?
AGENTI see your account as BW-883011, on Brightwave 500 at your service address on file. There’s no area outage showing for your location, but the line test saw your gateway as “not registered,” so I pushed a remote reset from here. It’s now showing as registered and online. Let’s do two quick checks on your side:
1. Gateway lights The Infinite light that was blinking orange should turn solid white (or your normal “online” color) within a minute or two. - Can you take a look now and tell me what that light is doing? 2. Device test Once that light is solid, try loading a site on a device that’s wired (if you have one) or your main Wi‑Fi device. - - If it doesn’t work right away, give it about 2 minutes for everything to fully reconnect, then try again. Tell me
- What color/state the Infinite light is in now, and - Whether you can get online on your work device. If it’s still not working after the reset, we’ll skip the basics you’ve already done and move straight to the next level of troubleshooting.
CUSTOMEROkay.
CUSTOMERLet me check the gateway now. Yeah, the internet light just went solid white.
CUSTOMERSo how long until my device is reconnect?
CUSTOMERShould I wait a bit before testing?
AGENTYou’re in good shape now that the light is solid white. You should only need to wait about 1–2 minutes after it goes solid for everything to fully come back:
1. Wait another 60–90 seconds. 2. Then
- If you’re on Wi‑Fireconnect to your usual Wi‑Fi name if it doesn’t reconnect automatically, then try a couple of sites or a speed test. - If you’re wired: just refresh a few pages or reconnect your VPN/work tools. If it’s been 2–3 minutes and your work device still isn’t online (or VPN won’t connect), tell me exactly what you see (no Wi‑Fi, “no internet,” VPN error, etc.) and we’ll dig into that next.
CUSTOMERRight. Got it.
CUSTOMERI'll wait a minute or two and test my devices. Oh, while I have you. Since I lost two hours of work.
CUSTOMERCan you give me a credit for the downtime?
AGENTYes, I can do that. I’ve applied a $10.00 service credit on account BW-883011 for about two hours of downtime while you were working from home. That credit will show on your next bill. Once you’ve tested in a couple of minutes, if anything still isn’t working—especially VPN or work apps—tell me what’s failing and any error messages, and we’ll sort it out.
CUSTOMEROkay, I appreciate the credit, but I lost two hours of work. Can you make it more than that?
AGENTI understand why you’re asking, especially if it cost you real work time. On my side, I’m limited in how much I can credit per short outage, and $10 is the maximum I can apply for about two hours of downtime like this. I’ve already applied that full amount to account BW-883011, and it will appear on your next bill. If you start seeing this happen repeatedly—multiple outages in a billing cycle—then support can review a larger or additional credit based on the overall impact. For today’s incident, though, I can’t increase it beyond the $10 already applied. How are your devices looking now—are you back online and able to reach your work tools/VPN?
CUSTOMEROkay, that makes sense. I'll keep an eye on it if it happens again. My devices are coming back online now, so I think I'm all set.
CUSTOMERThanks for your help, Alex. Goodbye.
AGENTYou’re welcome—glad
AGENTwe got you back online. Quick recap before you go: - Account: BW-883011 - Credit: $10.00 applied for about two hours of downtime, will show on your next bill. If anything acts up again—especially after that road work—reach out and we’ll run tests right away. Take care, and have a good rest of your day.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, Alex.
CUSTOMERI'm calling on my lunch break, so I need to be quick. I need to reschedule my dermatology appointment next Wednesday morning. Work. Just put me on the schedule, then.
CUSTOMERCan you move it to something after 3 p.m.?
AGENTI can help with that. I just need to verify you before I look up your appointment. Please tell me:
- Your full name - Your date of birth (YYYY-MM-DD)
CUSTOMERMarch 17th, 1948. Sorry. No, 1984.
CUSTOMERMarch 17th, 1984.
AGENTI’ve got your date of birth as March 17th, 1984—thank you. I also need your full name to look up your chart and reschedule that dermatology appointment.
CUSTOMERYep. That's right. March 17th, 1984.
CUSTOMERAny slots after 3 p.m.?
AGENTI’ve got your date of birth as March 17th, 1984. I still need your full name before I can look up your chart and see your dermatology appointment and the available
CUSTOMEROkay.
AGENTI have your date of birth as March 17th, 1984—thank you. I still need your full name before I can look up your chart
CUSTOMERGot it.
AGENTI still can’t see your chart yet. To reschedule that dermatology appointment and check for anything after 3
CUSTOMERGot it.
AGENTI still don’t have
CUSTOMERNate Brooks.
CUSTOMERYeah. Nate Brooks.
CUSTOMERCan we just move ahead and check the afternoon slots?
AGENTThanks, Mr. Brooks. I’ve verified you with date of birth March 17th, 1984. Your current dermatology appointment is with Dr. Okafor next Wednesday at 9:15 a.m. I checked Dr. Okafor’s schedule starting next Wednesday.
CUSTOMERGot.
AGENTHere are the first
CUSTOMERYep.
AGENTHere are the
CUSTOMERYeah.
AGENTI see a few options with Dr. Okafor at or after 3 p.m., starting from next week:
- Tuesday at 345 p.m. - Thursday at 4:10 p.m.
Friday’s slot is 1130 a.m., so that one doesn’t meet your “after 3 p.m.” requirement.
CUSTOMERTuesday.
CUSTOMERDoesn't work after all.
AGENTNo problem, we can change it again. Your dermatology visit with Dr. Okafor is currently moved to Tuesday at 3:45 p.m., confirmation code RVB-3M8P2.
CUSTOMERWhat about Friday? Any slots after 3 p.m.?
CUSTOMERHold up. Tuesdays aren't good.
CUSTOMERI need something after 3 p.m., but not Tuesday. Thursday at 410. Works. Can you move it there instead?
CUSTOMERWhat's the confirmation code?
AGENTGot it. I’ve moved your dermatology appointment with Dr. Okafor to Thursday at 4:10 p.m. Here are the details: - Patient: Nate Brooks - Date of birth: March 17th, 1984 - New appointment: Thursday at 4:10 p.m. with Dr. Okafor,
CUSTOMERGot it.
AGENTYou’re
CUSTOMERYeah. That's correct.
CUSTOMERCan you give me the confirmation code for the new appointment?
AGENTYour current dermatology appointment with Dr. Okafor is confirmed for Thursday at 4:10 p.m. The confirmation code is RVB-3M8P2.
CUSTOMERRight.
AGENTYour dermatology appointment with Dr. Okafor is set for Thursday at 4:10 p.m.
The confirmation code is RVB-3M8P2.
CUSTOMERRight.
CUSTOMEROkay. Got
AGENTYou’re all set, Mr.
CUSTOMERit. Is there a fee for changing
CUSTOMERthe. Right.
AGENTThere’s no fee for the changes you’ve made today. Our policy is: changes made more than 24 hours before the appointment are free; changes within 24
CUSTOMERWhy should I park when I come in? Yep. That
CUSTOMERworks. So
CUSTOMERwhere do I. Park for the appointment.
AGENTFor your dermatology appointment with Dr. Okafor on Thursday at 4:10 p.m., you can use our free patient
CUSTOMERGot. It.
CUSTOMEROkay. Does Doctor Okafor accept. Aetna insurance?
AGENTI don’t have access to Dr. Okafor’s insurance panel details in this system, so I can’t safely confirm Aetna coverage. To be sure: - Please call our main line on your insurance card or the clinic front desk, and - Have your Aetna member ID ready so they can verify your specific plan. If you’d like, I can also summarize what you already have set: - Patient: Nate Brooks - DOB: March 17th, 1984 - Appointment: Thursday at 4:10 p.m. with Dr. Okafor - Confirmation code: RVB-3M8P2 - Parking: Free patient parking in Lot C, entrance on River Road.
CUSTOMERAll right. Thanks for
AGENTYou’re welcome. Quick recap before you
CUSTOMERyour help. Goodbye.
AGENTgo:
- NameNate Brooks - DOB: March 17th, 1984 - Appointment: Thursday at 4:10 p.m. with Dr. Okafor (dermatology) - Confirmation code: RVB-3M8P2 - Parking: Free patient parking in Lot C, entrance on River Road - Change policy: Changes more than 24 hours ahead are free; within 24 hours there’s a $40 fee. If you think of anything else later, just call back on a break and I’ll help you out.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. Yes, I have a pipe that just burst under my kitchen sink. Water is spreading across the floor. It's heading toward a power strip. I need someone to come as soon as possible.
AGENTUnderstood. First let’s keep you safe and stop the water. 1. Stay away from that power strip and any outlets the water is reaching. - Don’t touch the strip, any cords, or plugs. - If water is already touching it, do not step into the water to get closer. 2. Can you see a shutoff valve under the kitchen sink? - It’s usually a small oval or round handle on the pipe going to the faucet (often one for hot, one for cold). - If you can safely reach it without stepping in water, turn both handles clockwise until they stop. 3. If you can’t safely reach those, or the water isn’t slowing: - Do you know where your main water shutoff is? Common spots: - In the basement near the front foundation wall - In a utility room, near the water heater - In a closet or behind a panel near where water enters the home - If you can access it safely, turn the main valve clockwise until it stops. 4. If water is already at the power strip/outlets and you cannot shut off power from a dry location (like a main breaker panel that you can reach without crossing water), tell me right away. If there’s any sparking, smoke, or burning smell, you should leave that area and call 911. Let me know:
- Were you able to turn off the under-sink valve or the main water? - Is anyone in the home in immediate danger right now? Once we confirm that, I’ll get an emergency plumbing visit set up for you as soon as possible. To open the service request, I’ll need
1. Your name 2. The service address (including unit number if applicable, and any gate code or access instructions) 3. The best callback phone number
If you’ve used Copperline Home Services before, tell me the phone number or address we’d have on file and I’ll look you up. Then I’ll check our earliest emergency arrival window and the fee that applies, and I’ll confirm that with you before booking.
CUSTOMEROkay. I managed to shut off the water under the sink. So.
CUSTOMERYeah, it's stopped now. No one is in danger, and the water hasn't hit the power strip yet. My name is Lucia Ramirez. The address is one 480 Larkspur Avenue, unit 4D. I moved from unit four B to 4D last month.
CUSTOMERSo please update that.
CUSTOMERThe gate code is pound 2719. My callback number is 503.
CUSTOMER5550139. No, 0193. So can you tell me how much the visit will cost? And if anyone can come before two?
AGENTThanks for getting that water shut off; that helps a lot. You’re safe to stay clear of the power strip and keep it unplugged until everything’s dry. Don’t plug anything back in near that area until the technician has checked the plumbing and things are fully dried out. Here’s what I can do for you:
- You’re in our system as a Copperline Care member. - I’ve updated your unit to1480 Larkspur Avenue, Unit 4D. - Gate code on file: #2719
- Callback number on file503-555-0193
For today, our earliest emergency plumbing window is
- Today, 200 PM to 4:00 PM
Because you’re a Copperline Care member, the emergency callout fee is $99, due on completion (card or check). Any repair work or parts would be additional, and the technician will go over pricing with you before proceeding. I’ve gone ahead and booked the earliest emergency slot
- Ticket numberCPL-58210 - Arrival window: Today, 2:00 PM–4:00 PM - Service address: 1480 Larkspur Avenue, Unit 4D - Gate code: #2719 - Callback number: 503-555-0193
You’ll get a text at that number about 30 minutes before the technician arrives. While you wait
- Keep the area around the power strip dry; don’t move it if there’s any standing water near it. - If water starts reaching outlets or that strip, stay back and let the technician handle it. If any of that info is wrong—especially the address, unit, gate code, or phone—tell me and I’ll fix it on the ticket.
CUSTOMERThat's all correct.
CUSTOMERSo who will be coming and how will I know they're on the way? And can you repeat the ticket number for me?
AGENTYou’re all set. - The technician assigned is from our plumbing team; you’ll get their name in the text update before arrival. - You’ll receive a text at 503-555-0193 about 30 minutes before they arrive, confirming they’re on the way and the approximate time. Your ticket number is: CPL-58210. If anything changes on your end—like the leak starting again or the power strip getting wet—call us right away and mention that ticket number.
CUSTOMERGot it.
CUSTOMERThe technician's name will be in the text.
CUSTOMERAnd the ticket number is.
CUSTOMERT l?
CUSTOMER58212. Thank you for your help. Goodbye.
AGENTLet me just
AGENTcorrect that before you go: your ticket number is CPL-58210 — C as in Charlie, P as in Paul, L as in Larry, then 5–8–2–1–0. You’ll get a text with the technician’s name and ETA before they arrive. Thanks for calling, Lucia. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMEROh, yes. I'm safe. I'm just standing next to my car on the sidewalk. There's traffic going past, but I'm fine.
AGENTI’m glad you’re safe. Is anyone injured or in any danger at the scene—either in your car, the other car, or any pedestrians? If anyone is hurt or in danger, please call 911 right away before we go any further.
CUSTOMERNo. Nobody's hurt. There is no danger here. It was just the cars.
CUSTOMERNobody was injured.
AGENTUnderstood, thank you for confirming that. Let’s get your claim started. I’ll first look up your policy. Please provide:
1. Your auto policy number 2. Your last name as it appears on the policy
CUSTOMERSure. My policy number is NV4471903. Oh no, sorry, last one is two. My last name is Ramirez.
AGENTThank you, Ms. Ramirez. I’ve found your policy ending in NV4471902 for your 2021 Honda CR‑V. Now I’ll gather some details about the accident so we can open the claim. 1. When did the accident happen? 2. Where did it happen? 3. What happened? Just a brief description in your own words. 4. Can you share the other driver’s:
- Name - Insurance company (if known) - License plate number (please read it slowly and I’ll repeat it back) 5. Did the police come to the scene, and is there a police report number if you have it?
CUSTOMEROkay.
CUSTOMERAccident happened about 20 minutes ago. It was at the intersection of SW fifth Avenue and Alder Street. I was stopped at a red light and another car hit the back of my car. The other driver's name is Kevin Lund. His insurance company is Pacific Shore. His license plate is seven.
CUSTOMERK.
CUSTOMERX like X-ray.
CUSTOMERR 214. No, the police did not come. And there is no police report.
AGENTI’ve got everything I need to open the claim, thank you. Let me read key details back to you. - Verified policy number: NV4471902 - Date/time of accident: about 20 minutes ago today - Location: intersection of SW Fifth Avenue and Alder Street - What happened: You were stopped at a red light and were rear‑ended by another vehicle. - Other driver: Kevin Lund, insured with Pacific Shore - Other vehicle license plate: 7KXR214 - Police: Did not attend; no police report. - Injuries: None reported at the scene. I’ve opened your claim:
- Claim numberNGM-904417 - Assigned adjuster: Priya Shah - The adjuster will contact you within one business day to go over coverage, repairs, and next steps. First, can you tell me: Is your Honda CR‑V drivable and safe to operate? - For example, are the lights working, no fluids leaking, and the rear wheels and hatch area intact enough that nothing is rubbing or exposed? If it’s not safe to drive, I can arrange a tow for you right now.
CUSTOMEROh, no. It is not drivable.
CUSTOMERThe back bumper is crushed.
CUSTOMERAnd the rear wheel is rubbing, so I cannot drive it. Please arrange a tow truck for me. Also, can you tell me where the car will be taken?
AGENTThanks for letting me know. Since the rear wheel is rubbing, you’re right not to drive it. I’ll take care of the tow and explain where it’s going. I’ve dispatched a tow for you with these details: - Tow company: Eastside Towing - ETA: about 45 minutes - Pickup location: intersection of SW Fifth Avenue and Alder Street - Destination: a Northgate partner repair shop at 9th and Morrison That shop will receive your vehicle and coordinate with your adjuster, Priya Shah, once she reviews the claim. About your coverage, based on your policy NV4471902: - Towing: Covered up to 25 miles, so this tow to our partner shop is covered. - Collision deductible: $500 (this is what you’d be responsible for if your collision coverage applies). - Rental car: Up to $40 per day for up to 30 days, starting today when the claim was opened. Your adjuster can go over repair options, any choice of shop questions, and how payment will work once they review everything. While you’re waiting for the tow: - Please remove any valuables from the car. - Keep your phone nearby in case the tow driver calls for directions. Is there a best phone number for the tow driver and your adjuster to reach you?
CUSTOMERYes. My phone number is 1779.
CUSTOMER218.
CUSTOMER4760. That is the best number to reach me.
AGENTThank you, I’ve got that. I’ll read it back to you to make sure it’s right: - Best contact number: 1‑779‑218‑4760 The tow driver from Eastside Towing and your adjuster, Priya Shah, will use that number if they need to reach you. Quick recap of the key details: - Policy number: NV4471902 - Other driver’s license plate: 7KXR214 - Your claim number: NGM‑904417 The tow should arrive in about 45 minutes and take your Honda CR‑V to our partner repair shop at 9th and Morrison. Do you have any other questions about what happens next while you wait for the tow?
CUSTOMERYes, I have a couple of questions.
CUSTOMERYou said the deductible is $500, but.
CUSTOMERHe hit me, so I should not have to pay that. Right?
CUSTOMERAlso, will my premiums go up? Because on the rental car.
CUSTOMERDo I just wait for the adjuster to contact me or can I get it right away?
AGENTI’ll walk through each of those for you. 1) Deductible when the other driver is at fault Your policy’s collision deductible is $500. Whether you actually end up paying that can depend on how the claim is handled: - If Northgate pays for your repairs under your collision coverage first, the $500 deductible would apply on your claim. - If Pacific Shore (the other driver’s insurer) accepts full liability and pays your damages directly, then you typically would not pay your collision deductible. - Sometimes Northgate pays first (with your deductible), then we seek reimbursement from the other insurer. If we recover the deductible from them, that $500 can be reimbursed to you. Your adjuster, Priya Shah, will contact Pacific Shore, review fault, and then explain exactly how your deductible will work in this case. I can’t decide fault or waive the deductible myself, but your coverage limit is clear: collision deductible is $500. 2) Will your premiums go up? I don’t have access to rating or premium decisions here, so I can’t say if your premium will change or by how much. That depends on things like: - Who is found at fault - Your state’s rating rules and your overall driving/claims history Your adjuster can explain how this claim will be coded and how to get more information about any possible premium impact. 3) Getting a rental car Your policy shows: - Rental coverage: up to $40 per day, up to 30 days, starting from the day the claim is opened (which is today). How to get the rental: - You do not have to wait for the adjuster to physically inspect the car first, but you should coordinate with Northgate or a partner rental company so it bills correctly under your claim. - The adjuster will usually: - Confirm your car is not drivable (which you’ve reported and we’ve towed). - Help set up a direct-bill rental with a preferred rental company, so you only pay for amounts above $40/day or outside the 30-day limit. Until you speak with Priya, you can: - Wait for her call (within one business day), or - If you need a rental urgently, you can get one on your own today and keep the receipts. Just know that reimbursement would still be subject to the $40/day
AGENTand 30‑day limits and how the claim is ultimately handled. To keep it simple, I’d recommend: - Let the tow take the vehicle to the partner shop. - When Priya calls you (using 1‑779‑218‑4760), tell her you need a rental right away and prefer a direct‑bill setup if possible. Before we wrap up, I’ll repeat your claim information so you have it handy: - Policy number: NV4471902 - Other driver’s plate: 7KXR214 - Claim number: NGM‑904417 Do you want me to go back over any of that—deductible, rental, or what happens next with the other driver’s insurance?