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
#234of 655 stacks
51 / 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.
#572 of 662 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#100 of 662 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#13 of 662 on the board · best 5.0 / 5
Turn-taking
Barge-in handling
When the caller interrupts, how often the agent made the right call: yielding to a real correction, and holding the floor through a filler.
#1 of 347 on the board · best 100%
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 662 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#253 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.
#367 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.
#422 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.
#544 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.
#505 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.
#76 of 660 on the board · best 4.3 / 5
Voice consistency
Share of calls where every line the agent spoke was the same speaker, with no change of speaker, gender or language voice partway. It checks who is speaking, not how they sound.
Not scored by this sweep.
#567 of 660 on the board · best 100%
Latency
Response time
The silence between the caller finishing and the agent starting to speak, measured from the recording on every turn of the call.
#251 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.
#454 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#307 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 88% | 3.75 s | — |
| Home services | 87% | 3.31 s | — |
| Insurance | 91% | 3.36 s | — |
| Customer support | 84% | 3.51 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 3.48 s | — |
| Spanish-accented English, city street | 81% | 3.50 s | — |
| Indian English, busy café | 87% | 3.27 s | — |
| Southern US, flustered, crying baby | 88% | 3.72 s | — |
| Fast and interrupting, construction outside | 86% | 3.43 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERAlex.
CUSTOMERSorry. I'm a little flustered. My baby's crying, and my Internet's been down for about two hours now. I work from home, so it's been pretty stressful. There is a road crew digging up the street right outside, and I'm wondering if that's got something to do with it. I already rebooted the gateway twice and checked all the cables, but the Internet light is blinking orange. Can you help me figure out what's going on?
AGENTI can help. Let’s move fast so you can get back to work and the baby. First, I need to pull up your account and check for any outage at your address. What’s easier for you to give me right now: - Your Brightwave account number, or. - The phone number on the account? Once I have that, I’ll: 1) Check for an area outage (especially with that road work outside). 2) Run a line test to your gateway. You’ve already rebooted and checked cables, so we won’t repeat those.
CUSTOMERThank you. That's a relief. I've got my account number right here. It's BW883017. Sorry. Last digit is 1. Is that okay? And, yeah, my phone number is (320) 490-8305. Just in case.
CUSTOMERCan you let me know if the roadwork is what's causing this? I'm just worried. Something I can't fix on my end.
AGENTI checked everything on our side for you. First, just to confirm: I’ve got your account as BW-883011. 1) Roadwork / outage. - There is no area outage or maintenance showing for your address. - That means the road crew might have caused a very local issue, but nothing’s been reported on our network in that area. - The line test to your gateway looked good, so it doesn’t look like a cut line between us and your home. 2) What I just did. - Your gateway was showing as “not registered” on our end, even though the signal looked fine. - I sent a remote reset to your Brightwave BX7. - It’s now showing as “registered and online” on our side. 3) What you should see. - The Internet light should turn solid (not blinking orange) within about 2 minutes. - Your devices (laptop, phone, work computer, etc.) may drop off Wi‑Fi briefly and then reconnect. Can you check: - Is the Internet light solid now? - And can you try loading a website or your work VPN on one device? If it’s still blinking orange after a couple of minutes or things aren’t loading, tell me what you see and I’ll take the next step.
CUSTOMEROh, hang on. Yeah. The Internet light just went solid white now. Thank goodness. How long does it usually take for my devices to reconnect after the gateway comes back up? I wanna make sure nothing's wrong before I try logging in again.
AGENTGood news that it’s solid now. Most devices will reconnect within 1–3 minutes after the gateway is back online: - Phones/tablets/laptops on Wi‑Fi: usually auto‑reconnect in under a minute if they’ve connected before. - Work laptop / VPN: Wi‑Fi should reconnect quickly, but you may need to manually reconnect your VPN app once the internet is stable. - Smart devices (TV, smart speakers, etc. ): can take a couple of minutes; some may need you to wake them or retry. To be sure everything’s fine, after about a minute: 1. On one device (like your work laptop), confirm it shows as connected to your usual Wi‑Fi name. 2. Open a browser and go to a couple of sites (e.g., one news site and one work site). 3. If you use VPN for work, connect it and see if it stays stable for a minute. If any device doesn’t reconnect after a few minutes, tell me which device and what it shows (e.g., “connected, no internet” or can’t see the Wi‑Fi), and I’ll walk you through just that piece so you’re not juggling everything at once with the baby.
CUSTOMERAlright. I'll check all that in a minute. Thank you. I lost two hours of work today because of the outage. Can you put in a request for a credit on my account for the downtime? I just wanna be sure I get something back for this.
AGENTI’ve added a credit for you. Here are the details: - Account: BW-883011 - Credit amount: $10.00 - Reason: About 2 hours of downtime due to a gateway issue on our side - When you’ll see it: It will appear on your next bill. If you notice anything still acting weird once you start working again—especially your VPN or video calls—tell me what’s happening and which device, and I’ll help you tune it so it stays stable.
CUSTOMERThanks. But I lost two hours of work. You make it more than that? I'd really appreciate anything extra just to help me out.
AGENTI understand why you’re asking, especially if those two hours affected your paycheck. I don’t have the ability to increase or override the credit amount that was just applied—$10.00 is the maximum I can grant directly through this system for a short outage like this. What I can do for you, concretely, is: - Confirm again what’s been applied: - Account: BW-883011. - Credit: $10.00, showing on your next bill. - Make sure your connection is stable now so you don’t lose more time today. If you’d like to push for a larger adjustment, the next step would be to contact Billing or Customer Care by phone or chat and explain the impact on your work. They have more flexibility than I do on one‑time exceptions and can review your full account history.
CUSTOMERAlright. Thanks for confirming and explaining all that. I'll reach out to billing if I need more help. Appreciate getting me back online so quick. Goodbye.
AGENTYou’re welcome—glad we got you back online.
AGENTQuick recap before you go: - Account: BW-883011. - Credit applied: $10.00, will show on your next bill. If things act up again later, just reach out and mention the light was blinking orange and the gateway needed a remote reset—that’ll help us pick up right where we left off. Take care, and good luck with work and the little one.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, Alex. I need to move my dermatology appointment next Wednesday morning. I just got scheduled for work then. My name is Jordan Ellis. Can you help me reschedule?
AGENTI can help with that. To pull up your chart, I need to verify you first. Please provide: - Your full name as listed with the clinic (I have “Jordan Ellis,” please confirm), and. - Your date of birth (YYYY-MM-DD). Once I have that, I’ll look up your dermatology appointment for next Wednesday morning and check what other times are available.
CUSTOMERYes. Jordan Ellis is correct. My date of birth is 03/17/1948. Sorry. No. 1984. 03/17/1984. I can only come after 3PM.
AGENTThanks, Jordan, and I’ve got your date of birth as March 17, 1984. I see your current dermatology visit with Dr. Okafor is next Wednesday at 9:15 AM at Main Campus, Building B. Looking at Dr. Okafor’s schedule starting next Wednesday, the first options that fit your “after 3 PM” preference are: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. There’s also a Friday 11:30 AM slot, but that’s before 3 PM, so it doesn’t match what you asked for. Which would you like to move your appointment to: Tuesday at 3:45 PM or Thursday at 4:10 PM?
CUSTOMERTuesdays don't work after all. Because I pick up my daughter. What about Friday? Are there any slots after 3PM that day?
AGENTRight now, the only Friday slot I see for Dr. Okafor is at 11:30 AM, and there’s nothing after 3 PM on Friday. Given your schedule (after 3 PM and no Tuesdays), the next available options I can see with Dr. Okafor are: - Thursday at 4:10 PM. Would you like me to move your appointment from next Wednesday at 9:15 AM to Thursday at 4:10 PM?
CUSTOMERYes. Thursday at 04:10PM works for me. Please move my appointment to that time. Is there a fee for changing the appointment?
AGENTYou’re all set, Jordan. I’ve moved your dermatology appointment with Dr. Okafor from next Wednesday at 9:15 AM to Thursday at 4:10 PM at Main Campus, Building B. Your new confirmation code is RVB-3M8P2. Please arrive 15 minutes early with a photo ID and your insurance card. About fees: The clinic’s policy is that changes made more than 24 hours before the appointment are free. Changes made within 24 hours of the appointment have a $40 fee. Since we rescheduled this ahead of time, you won’t be charged a change fee for this move. Anything else you’d like to adjust or ask about for this visit?
CUSTOMERYes. Where should I park for the appointment? And does doctor Okafor accept Aetna insurance?
AGENTFor your appointment with Dr. Okafor at Main Campus, Building B: - Parking: Free patient parking is available in Lot C, with the entrance on River Road. From Lot C, follow the signs to Building B. - Aetna insurance: I don’t have access to the live insurance panel for individual providers, so I can’t confirm from here whether Dr. Okafor specifically accepts Aetna. To be sure, please either: - Call the clinic’s front desk and ask if Dr. Okafor accepts Aetna, or. - Check with Aetna’s “Find a Provider” tool and search for Riverbend Health Clinic / Dr. Okafor. If you’d like, tell me what type of Aetna plan you have (e.g., PPO, HMO, Medicare Advantage), and I can suggest what to ask when you call.
CUSTOMERGot it. I have Aetna PPO. I'll check with the front desk to confirm. Thanks for your help today. Goodbye.
AGENTYou’re welcome, Jordan. With an Aetna PPO, you usually have more flexibility, but confirming with the front desk is the right move. Your current appointment details, just to recap before you go: - Provider: Dr. Okafor (Dermatology). - Day: Thursday. - Time: 4:10 PM. - Location: Main Campus, Building B. - Parking: Free in Lot C, entrance on River Road. - Confirmation code: RVB-3M8P2. Take care, and goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. I need help right away. A pipe under my kitchen sink just burst, and water is spreading across the floor toward a power strip. Can you send someone out for emergency plumbing?
AGENTThanks for calling right away. Let’s get you safe first, then I’ll get an emergency plumber out. 1. Stay away from that power strip. Don’t touch it, the outlet, or anything plugged into it. 2. Unplug / kill power safely: - If you can safely reach the power strip without stepping in water, unplug the strip from the wall and move it out of the wet area. - If any part of the strip or cords are already in the water, do not touch them. Instead, go to your breaker panel and: - Flip the breaker for the kitchen/outlet off, or. - If you’re unsure which breaker, switch main power off until the water is away from the outlet area. 3. Shut off the water feeding that pipe: - Look under the sink for small shutoff valves on the hot/cold lines. Turn the knobs clockwise until they stop. - If you can’t find or turn those, go to your main water shutoff (often in a basement, garage, utility room, or outside by the street in a meter box) and turn it clockwise to shut off the house water. 4. Move items out of the
CUSTOMEROkay.
AGENTUnderstood.
CUSTOMERRight. I'm shutting off the water now. It stopped. I'll stay clear of the power strip. What's next?
AGENTGood—shutting the water off was exactly the right move, and staying clear of that power strip is important. Next, I’d like to get you an emergency plumber booked and then I’ll walk you through what to do while you wait. First, I want to confirm a couple of details I’m seeing on my end: 1. I’m showing a customer profile at: - 1480 Larkspur Avenue, Unit 4B. Is that the address where this is happening? 2. What’s the best phone number for the technician to call or text? Also, before we finalize anything: because this is an emergency plumbing visit and you’re a Copperline Care member, your emergency callout fee would be $99, due on completion (card or check). Any repair work or parts would be quoted on site before they proceed. Do you agree to the $99 emergency callout fee so I can lock in the earliest emergency window for today? While you answer, a few safe steps you can take (only if you can do them without going near that power strip or outlet area): - Put down towels or a mop to stop water from spreading further. - If water is close to any other outlets or appliances, stay clear of those as well. - Don’t turn the water back on until our plumber says it’s safe. Once you confirm the address and callback number and agree to the fee, I’ll read back your booking details and ticket number.
CUSTOMERUh-huh. So the address is 1480 Larkspur Avenue. But I actually moved from Unit 4 B to Unit 4 D last month. This is happening in Unit 4 D. For the callback number, it's (503) 555-0139. No. 0193. About the fee. That's fine. I agree to the $99 callout. Can anyone come before two?
AGENTThanks for the updates—that helps a lot. I’ve got you set for an emergency visit today from 2:00 PM to 4:00 PM. That’s the earliest emergency window available; there’s nothing sooner showing in our system, or I’d grab it for you. Let me read everything back so you can confirm: - Service address: 1480 Larkspur Avenue, Unit 4D. - Gate/access info: none noted. - Callback number: (503) 555-0193. - Ticket number: CPL-58210. - Arrival window: today, 2:00 PM to 4:00 PM. - Emergency callout fee (Copperline Care member): $99, due on completion (card or check), plus any approved repair costs. Please correct anything that’s not right. While you’re waiting, and as long as you can stay well away from that power strip and any outlets near the water: 1. Keep the main water off and don’t use the kitchen sink. 2. Lay down towels
CUSTOMERYeah.
AGENTGot it, thanks for confirming. Here’s what we have locked in for you: - Service address: 1480 Larkspur Avenue, Unit 4D. - Callback number: (503) 555-0193. - Ticket number: CPL-58210. - Arrival window: today, 2:00 PM to 4:00 PM. - Emergency callout fee: $99 as a Copperline Care member, plus any repair costs you approve on site. While you wait for the plumber: - Keep the water shut off and don’t use the kitchen sink. - Stay clear of the power strip and any outlets near the wet area. - If you can safely do it without getting near that outlet, keep soaking up any standing water with towels to prevent further spread. If anything changes—like the water starts coming from somewhere else, or you notice sparking, burning smells, or outlets buzzing—leave that area immediately and call us back or 911 if it seems dangerous. If you’d like, I can also note on the ticket that you’re especially concerned about the outlet/power strip so the plumber is prepared to assess that area carefully.
CUSTOMERYes. Please note that about the outlets and power strip. Who will be coming? And how will I know they're on their way?
AGENTI’ll add that note right now so it’s front and center for the technician: that water was spreading toward a power strip and you’re concerned about the outlets in that area. On your questions: - Who’s coming: I don’t get individual names from the dispatch system, just that an emergency plumber is assigned to ticket CPL-58210 for today’s 2:00–4:00 PM window. - How you’ll know they’re on the way: our system shows that the technician will text your callback number, (503) 555-0193, about 30 minutes before arrival. If they can’t reach you by text, they’ll call. While you’re waiting, just keep: - The water shut off. - Clear of that outlet and power strip area. - Soaking up any water you can safely reach, away from electrical. If anything changes or feels unsafe—sparks, burning smell,
CUSTOMERUnderstood.
AGENTYou’re all set, then. Quick recap so you don’t have to wonder about anything: - Ticket: CPL-58210
AGENT- Address: 1480 Larkspur Avenue, Unit 4D - Callback: (503) 555-0193 - Window: today, 2:00 PM–4:00 PM - Fee: $99 emergency callout as a Copperline Care member, plus any approved repairs - Note on file: water from burst pipe under kitchen sink, prior spread toward power strip; customer concerned about nearby outlets The plumber will text or call you about 30 minutes before they arrive. Until then, keep the water shut off and stay clear of that outlet/power strip area. If anything changes or starts to feel unsafe before we get there, call us back right away.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes. I am safe. I'm just standing next to my car. I am calling from a busy cafe nearby.
AGENTI’m glad you’re safe. Is anyone injured or in danger—either in your car or the other vehicle? If anyone is hurt or needs medical help, please hang up and call 911 first, then you can call us back.
CUSTOMERNo. Nobody is injured. We are both okay. I just need help with the claim and getting my car sorted.
AGENTUnderstood. We’ll get the claim started and then talk about getting your car taken care of. First, I need to locate your policy. 1. What is your auto policy number? 2. What is the policyholder’s last name? 3. Are you the policyholder, or calling on their behalf? After that, I’ll ask: - When the accident happened. - Where it happened. - What happened. - The other driver’s name, insurer, and license plate. - Whether police came to the scene. Then we can see if the car is safe to drive or if we should arrange a tow.
CUSTOMERSure. Can give you my details. My policy number is NG4471903. Oh, sorry. Last one is two. The policyholder's last name is Mehta. I'm the policyholder. Calling myself. The accident happened about twenty minutes ago. At SE 5th Avenue and Alders Street. I was stopped at a red light. And another car hit the back of my car. The back bumper is crushed, and the rear wheel rubs. So I cannot drive it. The other driver's name is Kevin Lund. He is insured with Pacific Shore. His license plate is 7KX like X-ray, R214. Police did not come to the scene. Kindly do the needful regarding the toll as the car is not safe to drive.
AGENTI’ve started your claim and arranged a tow. Let me read key details back to you and fill in a couple of gaps. First, your policy: -
CUSTOMEROh, yes. Go ahead.
AGENTThanks. I’ll walk through what we have and what’s next. 1) Policy verification.
CUSTOMERRight. Please verify my policy details.
AGENTHere’s what I have for you, and then I’ll answer your coverage questions. First, your policy details.
CUSTOMEROkay.
CUSTOMERYes. That's right. My policy number is NG4471902. And last name Mehta.
AGENTThank you for confirming. Here’s what I have on file for you, and what we’ve done so far. 1) Policy details. - Policy number: NG4471902. - Policyholder last name: Mehta. 2) Claim details I’ve recorded. - Claim number: NGM-904417. - Accident time: About 20 minutes before you called. - Location: Intersection of SE 5th Avenue and Alders Street. - What happened: You were stopped at a red light and were rear-ended. Rear bumper is crushed and the rear wheel is rubbing, so the vehicle is not safe to drive. - Other driver: - Name: Kevin Lund. - Insurer: Pacific Shore. - License plate: 7KXR214. - Police: Did not attend; no report number. - Injuries: None reported. 3) Your coverages (from your policy). - Collision deductible: $500. - Rental coverage: $40 per day, up to 30 days, starting from the day the claim is opened. - Towing: Covered up to 25 miles. 4) Tow arrangements. - Tow company: Eastside Towing. - Status: Dispatched. - Estimated arrival: About 45 minutes. - Planned destination: A Northgate partner repair shop at 9th and Morrison. If you’d prefer the car to go to a different repair shop, tell me the name and address and I can update the tow destination before they load the vehicle. Next steps: - The assigned
CUSTOMERThat's
CUSTOMERalright. You please tell me what happens next with the assignment? Also, I have a question about the deductible. Since he hit me, do I still have to pay that? And will my premium go up because of this accident?
AGENTHere’s what happens next, and then I’ll address your deductible and premium questions using what I’m allowed to see. First, reading back the key IDs: - Policy number: NG4471902. - Claim number: NGM-904417. - Other driver’s plate: 7KXR214. If any of that is off, tell me and I’ll correct it. ---. 1) What happens next with the claim assignment. Your claim is already open and assigned to an adjuster: - Adjuster: Priya Shah. - Contact: You should hear from her within one business day. What Priya will do: 1. Go over the accident details with you and, if needed, contact the other driver’s insurer (Pacific Shore). 2. Set up the vehicle inspection: - Either at the Northgate partner shop (9th and Morrison) where your car is being towed, or. - At another shop of your choice, if you decide to change it. 3. Confirm repair vs. total loss: - If repairable, she’ll work with the shop on an estimate and repairs. - If the car is a total loss, she’ll explain the valuation and payoff process. 4. Discuss rental car use: - Your policy shows rental coverage of $40 per day for up to 30 days from when the claim is opened. - She’ll explain how to set up a rental and with which rental partners. You don’t need to do anything right now except: - Be ready to take a call from a number you may not recognize (it could be Priya or the tow company). - Let the tow driver know if you want a different repair shop so they can take it there. ---. 2) Deductible: do you still have to pay it? From your policy, I can see: - Collision deductible: $500. How this usually works: - If the repairs are done under your Northgate collision coverage, the shop/claim will apply your $500 deductible to the repair bill. - If the other driver (Kevin Lund) is clearly at fault and his insurer (Pacific Shore) accepts full liability: - Sometimes, they pay the repairs directly and no deductible is taken from you, - Or, if we pay first under your policy, your adjuster may seek reimbursement from them and your deductible can be reimbursed later if recovery is successful. I’m not able to see fault decisions or guarantees of reimbursement in this system—that part will be decided by your adjuster after reviewing statements and any evidence. But: - Yes, if we repair the car under your collision coverage, the $500 deductible applies up front. - Whether you get that back later depends on the liability outcome and recovery from Pacific Shore. ---. 3) Will your premium go up? I don’t have access to rating or renewal calculations, so I can’t tell you exactly what will happen to your premium. In general terms: - A not‑at‑fault rear‑end (as you described) is less likely to affect your premium than an at‑fault accident, but: - Each state’s rules are different. - Prior history and other rating factors also matter. - Your adjuster, Priya, or a Northgate customer service rep can review: - How this claim will be coded (at‑fault vs. not‑at‑fault). - Whether it’s expected to affect your premium at renewal. So I can’t promise “no increase,” but you can ask Priya specifically: - “How will this claim be coded for rating?” - “Based on that coding, is this expected to impact my premium at renewal?” ---. 4) Anything else you should do right now. - Keep any photos you may have taken
AGENTof: - The damage to your car. - The other vehicle. - The intersection or traffic light. - Keep the other driver’s details handy: - Name: Kevin Lund. - Insurer: Pacific Shore. - Plate: 7KXR214. Would you like the car to stay going to the Northgate partner shop at 9th and Morrison, or do you have a different repair shop you prefer?