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
#324of 655 stacks
48 / 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.
#478 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.
#312 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.
#294 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.
#1 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.
#557 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.
#480 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.
#593 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.
#638 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.
#158 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.
#236 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.
#447 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#445 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 3.68 s | — |
| Home services | 78% | 3.46 s | — |
| Insurance | 94% | 3.09 s | — |
| Customer support | 93% | 3.68 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 3.26 s | — |
| Spanish-accented English, city street | 92% | 3.36 s | — |
| Indian English, busy café | 87% | 3.37 s | — |
| Southern US, flustered, crying baby | 94% | 4.07 s | — |
| Fast and interrupting, construction outside | 80% | 3.49 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s
AGENTgoing on with your service?
CUSTOMERHey, Alex. Sorry. I'm a bit flustered. My baby's crying in the background, and I work from home. My Internet's been down for about two hours now. There's a road crew digging up the street outside, and I'm worried that might be the cause. I already rebooted the gateway twice and checked all the cables, but the Internet light is still blinking orange. Could you help me figure out what's going on?
AGENTWe’ll get this fixed as fast as possible so you can get back online. First, I need to pull up your account and check for any outage at your address. Please give me either: - Your Brightwave account number, or - The
AGENTphone number on the account.
CUSTOMERYeah. I think the account number is what you need. It's BW883017. Sorry. Last digit is 1. Is that okay? And my phone number is (907) 921-4887, if that helps. Can you if there's an outage from that road crew?
AGENTI’ve got your account pulled up as BW883011, and there’s no area outage showing at your address, so it’s likely not a widespread issue from the road crew. I ran a line test: your signal looks good, but the gateway wasn’t registered properly. I’ve just sent a remote reset to your Brightwave BX7, and it’s now showing as registered and online on my side. Let’s do two quick checks on your end (no need to reboot again): 1. Look at the gateway lights: is the Internet light now solid (usually solid white/green) instead of blinking orange? 2. On a device that’s plugged in by Ethernet or on Wi‑Fi, try loading a website or your work VPN. It can take up to about two minutes for everything to reconnect
AGENTafter that remote reset. Tell me what you
CUSTOMERYeah. The Internet light's solid white, just like you said. Is that okay? I'm waiting for things to reconnect, but I'm still not seeing a website load yet. How long should I wait before everything's back up?
AGENTSolid white is exactly what we want—that means the connection to us is good and the gateway is online. Timing-wise: - Most devices: 1–2 minutes after the light turns solid - Some work VPNs / laptops: up to 3–5 minutes to sort themselves out Let’s do a quick check while we wait, in this order: 1. On your phone (using Wi‑Fi, not cellular), try a simple site like: - example.com or news.google.com 2. If that still doesn’t load after 2–3 minutes: - Turn Wi‑Fi off and back on on that device, then try again. 3. If your work laptop is the issue: - First confirm a normal website works. - Then reconnect the VPN if you use one. If it’s been a full 5 minutes from when the light turned solid and nothing will load on any device, tell me: - Whether wired or Wi‑Fi devices are affected (or both) - Which device you’re testing on (phone, laptop, etc.) I’ll walk you through the next step based on that, but you should
AGENTvery likely see things start coming back within
CUSTOMERThanks for explaining. I'm just checking my phone on Wi Fi right now. Still loading, but I'll give it another minute or so. I was mostly worried because I lost about two hours of work. Is there any way I could get a credit for the downtime? Sorry. I just wanna make sure it's all squared away.
AGENTThat makes sense, and I’m glad you asked. I’ve added a $10.00 service credit on your account BW883011 for about two hours of downtime. It will appear on your next bill. While we’re talking, has that page on your phone finished loading yet after the reset and a bit of waiting? If it’s still not loading, try toggling Wi‑Fi
AGENToff and back on once, then test a
CUSTOMERI appreciate you putting the credit on, but I lost two hours of work. Is there any way you can make it more than $10?
CUSTOMERSorry. I just feel like I really got hit hard by this. I'll try toggling Wi Fi and check that site. But can you help with that credit?
AGENTI hear you—losing two hours of work is a big deal, especially with a baby crying and you working from home. I’ve already applied the $10.00 credit to account BW883011, and that’s the maximum I can issue directly on a single visit like this. I don’t have the ability to increase it further from here without misrepresenting what I can do. What I can do for you: - Make sure the issue is fully documented on your account (including that you work from home and lost about two hours of productivity). - If this happens again or you see a pattern, we can add additional notes and credits where appropriate so billing can see the full history. Let’s also make sure your connection is solid so this doesn’t keep disrupting you: 1. After toggling Wi‑Fi off and on, did that test site load on your phone? 2. Once that
AGENTworks, we’ll quickly
CUSTOMERAlright. Thank you for documenting it and explaining. I just toggled Wi Fi, and that site loaded fine now. So looks like things are coming back. I'll check my laptop and VPN next, but I think I'm alright for now. Thanks for your help, Alex. Goodbye.
AGENTYou’re welcome, and I’m glad to hear things are loading again on your phone. Quick recap before you go: - Your account is BW883011. - I ran a line test, remotely reset your Brightwave BX7, and it’s now online with a solid Internet light. - A $10.00 credit has been applied for the downtime and will show on your next bill. If your laptop or VPN gives you any trouble, just reach out and we’ll pick up from there. Take care, and good luck with the little
AGENTone.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERYes. Hello. I am Arjun Mehta. I am having an appointment for dermatology Wednesday morning. But I need to reschedule it. I have a work shift now at that time. Can you help me move it to a time after 3PM?
AGENTI can help with that. I’ll just need to verify your record first. Please tell me: 1) Your full name spelled out (first and last), and 2) Your date of birth in YYYY-MM-DD format.
CUSTOMERSure. My name is Arjun Mehta. That's a r j u n n e h t a. My date of birth is 03/17/1948. Sorry. No. 1984. 03/17/1984.
AGENTThanks, Mr. Mehta. I have you as Arjun Mehta, date of birth 1984-03-17, with dermatology scheduled next Wednesday at 09:15 with Dr. Okafor. Here are the next available
CUSTOMERYeah. That's right. So I need to move that appointment. I can only come after 3PM. What times are available?
AGENTI see a few options with Dr. Okafor that are after 3 PM: - Tuesday at 15:45 - Thursday at 16:10
CUSTOMERTuesdays actually do not work for me after all. Because I pick up my daughter. What about Friday?
AGENTGot it, no Tuesdays. With Dr. Okafor after 3 PM, I’m only seeing: - Thursday at 4:10 PM Friday’s only opening right now is 11:30 AM, which is before 3 PM. Would you like me to move your appointment to Thursday at 4:10 PM, or would you prefer to keep the current time
AGENTfor now?
CUSTOMERThursday at 04:10PM works for me. Please move my appointment to that time. Go ahead and move it to Thursday at 04:10PM. That will be good.
AGENTYou’re all set, Mr. Mehta. I’ve moved your dermatology visit with Dr. Okafor. Here are the details: - Patient: Arjun Mehta - Date of birth: 1984-03-17 - New appointment: Thursday at 4:10 PM - Location:
CUSTOMERCan you please read back the confirmation code for me? I need to note it down.
AGENTCertainly. Your new appointment confirmation code is: R V B – 3 M 8 P 2 That’s: R-V-B-3-M-8-P-2.
CUSTOMERUh-huh. Noted. Is there any fee for changing the appointment?
AGENTThere’s no fee for the change you just made. Our policy is: - Changes made more than 24 hours before the appointment are free. - Changes less than 24 hours before the appointment have a $40 fee. Since you rescheduled well in advance, there’s
AGENTno charge.
CUSTOMEROkay. Where do I park for this appointment?
AGENTFor your appointment, you can park in our free patient parking: - Lot: Lot C - Cost: Free - Entrance: Off River Road Just allow a few extra
CUSTOMERRight. Does doctor Okafor accept Aetna insurance?
AGENTI don’t have access to Dr. Okafor’s current insurance panel from here, so I can’t safely confirm Aetna coverage. To check whether Dr. Okafor accepts Aetna, you have two good options: 1) Call the clinic’s main line and ask for insurance/benefits verification for “Dr. Okafor in Dermatology” with Aetna. 2) Check Aetna’s provider directory online and search for Riverbend Health Clinic and Dr. Okafor by name. If you’d like,
AGENTI can also note in your chart that
CUSTOMERYeah. Kindly note in my chart that I have Aetna. That will be helpful. Thank you for your assistance today. Goodbye.
AGENTYou’re very welcome, Mr. Mehta. I’m
AGENTglad I could help with the rescheduling. I don’t have the ability to add notes directly into your chart from here, so please mention that you have Aetna at check‑in or when you next call the clinic, and they’ll add it to your record. Take care, and goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I
AGENThelp you with?
CUSTOMERHi. Yeah. I have an emergency. A pipe under my kitchen sink just burst, and water is spreading across the floor toward a power strip. I haven't shut the water off yet. Can you help me?
AGENTYes, I can help you. First, let’s keep you safe and stop the water: 1. Stay away from that power strip and any outlets near the water. - Don’t touch the strip, any cords, or plugs. - If the water has already reached the strip, do not step in the water to get closer. 2. Shut off the water as quickly as you safely can: - If there is a small shutoff valve under the sink (usually a small oval or round handle on the pipe), turn it clockwise until it stops. - If you can’t find or reach that, or it doesn’t stop the flow, go to your main water shutoff: - Common places: basement near the front wall, utility room, garage, or where the water line enters the house. - Turn the main valve clockwise until fully closed (lever
CUSTOMEROkay.
AGENTUnderstood.
CUSTOMERI'm doing that now. Okay. The water has stopped. What do we do next?
AGENTGood job getting the water shut off—that’s the most important part. Next, let’s get a plumber out and keep things safe and contained until they arrive. A couple quick safety/cleanup steps while we set this up: - Keep clear of that power strip and any outlets the water got near. - If you can do it without going into standing water, you can unplug the power strip from the wall. If you’d have to stand in water to reach it, leave it alone until a pro can check it. - Start soaking up water with towels or a mop so it doesn’t spread further, especially near cabinets and walls. Now I’ll get a service request started and book an emergency visit for you. We have an emergency arrival window today from 2:00 PM to 4:00 PM. The emergency callout fee is $149 (that’s just to come out; parts and additional labor are extra). Payment is by card or check on completion. Is that window and fee okay to proceed? If so, I’ll need: 1. Your full name 2. The service address (including unit number, if any) 3. Any gate code or access
CUSTOMERBefore
AGENTNo problem—go ahead. What would you like to take care of or ask about before
AGENTwe book the visit?
CUSTOMERCan anyone come before 2PM? If not, I'll take the two to four window. Also, who will be coming out? And how will I know they're on the way?
AGENTRight now the earliest emergency arrival window I’m seeing is 2:00–4:00 PM; there isn’t anything sooner showing as available. I recommend we grab that 2–4 window so you’re locked in. On your other questions: - I don’t get the individual technician names from this system, so I can’t tell you exactly who it will be. - You’ll get a notification when the tech is dispatched—typically a call or text to your callback number before they head your way, and they’ll confirm they’re from Copperline when they arrive (uniform/vehicle and work order). If you’re okay with the 2–4 PM emergency window and the $149 emergency callout fee, I’ll book
CUSTOMERThat
CUSTOMERSure. My name is Jordan Ellis. The address is 1480 Larkspur Avenue. Unit 4 D. I moved from 4 B to 4 D last month. So it's 4 D. The building gate code is Pound 2719. My callback number is (503) 555-0139. No. 0193. And, yes, I'm okay with the two to 4PM emergency window and the $149 fee.
AGENTThanks, Jordan. I’ve
AGENTgot everything set up for you. You’re booked for an emergency plumbing visit: - Today, arrival window: 2:00 PM to 4:00 PM - Ticket number: CPL-58210 - Emergency callout fee: $149 (parts and any additional labor are extra, paid by card or check at completion)
CUSTOMERYeah.
AGENTYou’re all
AGENTset, Jordan. Here’s what I have for your visit: - Ticket number: CPL-58210 - Arrival window: today, 2:00 PM to 4:00 PM (emergency) - Service address: 1480 Larkspur Avenue, Unit 4D - Gate code: #2719 - Callback number: (503) 555-0193 - Emergency callout fee: $149 (parts and any additional labor are extra, paid by card or check at completion) You’ll get a text about 30 minutes before the technician arrives at that callback number. Until we get there: - Keep the main water shut off if you can. - Stay away from the power strip and any outlets that got wet. - You can keep mopping up or using towels to dry the floor and under the cabinets as much as possible. Do you want any help finding your main shutoff again or checking if it’s okay to turn part
AGENTof the water back on before we arrive?
CUSTOMERNo. I'm good on the shutoff. I'll leave it off until someone gets here. Thanks for your help. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe
AGENTright now?
CUSTOMERYeah. I'm at home now. Sorry. My baby's crying in the background. It's a little hectic. I'm safe. Just a little flustered. I was in an accident about twenty minutes ago. Stopped at a red light at Southeast 5th Avenue and Alder Street. Another car hit the back of mine. Nobody's hurt, but I can't drive my car. Can you help me figure out what to do?
AGENTI’m glad you’re safe, and no need to apologize—totally understand it’s hectic with a baby. First, since you said nobody’s hurt and you’re home safe, we don’t need 911. If that changes at all, call 911 right away. I can absolutely help you with the next steps. We’ll do two things: 1) Open a claim 2) Arrange a tow since you can’t drive the car To start your claim, I need to verify your policy. 1. What’s your auto policy
AGENTnumber? 2. And the policyholder’s
CUSTOMERSure. Let me give you that. The policy number is NG4471903 Oh, wait. Sorry. Last one is two. So... NG4471902. And my last name is Carter. Is that alright?
AGENTYes, that’s perfect, thank you. I’ve verified your policy under Carter with policy number NG4471902. I’ve opened a claim and arranged a tow for you. Let me walk you through what we’ve got and then I’ll just need a couple more details. 1. Safety and injuries - You mentioned nobody is hurt. If anyone starts to feel pain later—especially you or the baby—please get medical attention, and call 911 if it’s an emergency. 2. Claim details so far - Policy number: NG4471902 - What happened: You were stopped at a red light at SE 5th Avenue and Alder Street and another car hit you from behind. Your car can’t be driven. - No injuries reported. I’ve opened claim number NGM-904417. Your assigned adjuster is Priya Shah, and you should hear from her within one business day. 3. Tow truck - I’ve dispatched Eastside Towing to your vehicle at SE 5th & Alder. - Estimated arrival: about 45 minutes. - It’s set to go to our partner repair shop at 9th and Morrison. - If the car isn’t still at the intersection (for example if it was moved somewhere else), tell me where it is now so I can update the tow. 4. I still need a few details for the claim file: - Other driver’s information - Their name (as best you remember) - Their insurance company (and policy number if you have it) - Their license plate number - Police - Did the police come to the scene? - If yes, do you have a report number or the officer’s card? Also,
AGENTwhat’s the best phone
CUSTOMEROkay.
CUSTOMERLet me try to get all that straight. The other driver's name is Kevin Lund. His insurance is with Pacific Shore. I don't have his policy number. Sorry. But his license plate is 7KX like X-ray, R214. The police didn't come to the scene, so there's no report or officer card. For my phone number, please use (907) 215-3251. Is that alright? Sorry. Is that going to be a problem?
AGENTThanks, that’s very clear, and no, it’s not a problem at all. Here’s what I have from you: - Policy number: NG4471902 - Claim number: NGM-904417 - Other driver: Kevin Lund - Other driver’s insurer: Pacific Shore - Other vehicle license plate: 7KX R214 - Police: Did not come to the scene; no report - Best phone number for you: (907) 215-3251 Not having his policy number or a police report is common in rear‑end accidents. We can still handle your claim with the info you gave: name, insurer, and plate are all very helpful. Your adjuster, Priya Shah, will contact you at (907) 215-3251 within one business day to go over coverage, repairs, and next steps. Before we wrap up, two quick checks: 1. Is 7KX R214 exactly right for the plate, or did I mis-hear anything? 2. Is the car still at SE 5th & Alder, or was it moved somewhere else after the accident?
CUSTOMERYeah. I just wanna double check the plate. It's 7KX like x-ray, R214. Not South African rand or anything. Just the letter R. Sorry. I know that's confusing. Yes. The car is still right at Sassy 5th Avenue in Alders Street. Hasn't been moved. Is that okay?
AGENTThank you for double-checking—that helps. Here’s what I have, reading it back carefully: - Other driver’s license plate: 7KX R214 (seven – K – X – R – two – one – four) - Vehicle location: still at the intersection of Southeast 5th Avenue and Alder Street, not moved That’s perfectly okay. The tow I arranged is for your disabled vehicle at SE 5th & Alder, so that matches. A truck from Eastside Towing is on the way with an ETA of about 45 minutes, going to our partner repair shop at 9th and Morrison. Key details for you to have handy: - Policy number: NG4471902 - Claim number: NGM-904417 Your adjuster, Priya Shah, will call you at (907) 215-3251 within one business day to go over coverage, repairs, and the next steps. While you’re waiting for the tow: - If you’re not already at the car, bring your keys and, if it’s safe, remove any valuables from the vehicle before it’s towed. - When the tow driver arrives, you can confirm the destination (Northgate partner repair shop at 9th and Morrison). Is there anything specific
AGENTyou’re worried
CUSTOMERYeah. I'm a little worried about a few things. First, how much am I going to have to pay? Is there a deductible? But he hit me, so I should not have to pay that. Right? And, will I get a rental car while mine's being fixed? So is my premium going to go up because of this? Sorry. I just wanna make sure I don't miss anything important.
AGENTabout I’ll walk through each of those one by one, using what I can see on your policy, and I’ll flag where your adjuster will need to make the final call. Here’s what your policy shows for NG4471902: 1) Deductible / what you might pay - Your policy has a $500 collision deductible. - Because the other driver rear‑ended you, your adjuster will look at making a claim against his insurance (Pacific Shore) as the at‑fault carrier. - If his insurer accepts fault and pays for the damage directly, you typically would not pay your collision deductible. - If we need to use your collision coverage first (for example, while liability is still being investigated), you could
AGENTtemporarily pay the $500 deductible, and then we may seek reimbursement from Pacific Shore. The exact way that’s handled (whether you ever actually pay it out of pocket) will be confirmed by your adjuster, Priya Shah. 2) Rental car coverage Your policy includes rental reimbursement: - $40 per day, up to 30 days, starting from the day the claim is opened. - Your adjuster will help you set up a rental through one of our partner companies or explain how reimbursement works if you arrange your own. So yes, you do have rental coverage; the main limits are the $40/day and up to 30 days. 3) Towing You also have towing coverage: - Towing is covered up to 25 miles. - The tow I already set up to the partner shop at 9th and Morrison is intended to be within that limit. If anything ends up beyond 25 miles, your adjuster or the tow company will explain any extra cost before it happens. 4) Will your premium go up? This part I cannot see or decide from here. Whether your premium changes depends on: - The final fault decision (if Kevin Lund is clearly at fault, that’s in your favor), - Your state’s rating rules and prior history, - How the claim is ultimately paid (through his insurer, yours, or both). I’m not allowed to promise anything on premiums. Your adjuster will go over how this kind of loss is usually treated under your policy and in your state. To recap the key numbers for you: - Policy number: NG4471902 - Claim number: NGM-904417 - Other driver’s plate: 7KX R214 Next concrete steps: 1) Tow truck: When Eastside Towing arrives, remove valuables and confirm it’s going to the Northgate partner shop at 9th & Morrison. 2) Photos (if you can, and only when you’re not juggling the baby): Take a few pictures of the damage and where it was hit. 3) Adjuster call: Priya Shah will call you at (907) 215-3251 within one business day to: - Confirm fault and how that affects your out‑of‑pocket costs, - Set up/confirm the rental, - Explain repair options and timing. Is there one of those items—deductible, rental, or premiums—you’d like me to have your adjuster focus on first when they call?