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
#83of 655 stacks
56 / 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.
#260 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.
#464 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.
#191 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.
#133 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.
#578 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.
#528 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.
#547 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.
#537 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#646 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 98% | 4.71 s | — |
| Home services | 93% | 5.22 s | — |
| Insurance | 90% | 4.68 s | — |
| Customer support | 89% | 4.65 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 4.39 s | — |
| Spanish-accented English, city street | 83% | 4.65 s | — |
| Indian English, busy café | 98% | 4.62 s | — |
| Southern US, flustered, crying baby | 89% | 4.74 s | — |
| Fast and interrupting, construction outside | 95% | 5.22 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, Alex. Um, sorry, I'm a little flustered. I've got a baby crying in the background, and my internet's been out for about two hours now. I work from home, so this is a real problem. There's a road crew digging up the street outside, and I'm wondering if that might be the cause. I already rebooted the gateway twice and checked every cable, but the internet light is blinking orange. Y'all check what's going on?
AGENTNo problem, I'll check on it now. Can you give me your account number or the phone number on the account so I can pull it up?
CUSTOMERYeah, I think so. My account number is BW883017. Sorry, last digit is one, is that okay, or do you need my phone number too?
AGENTThat works, I'll use the account number.
CUSTOMERAll right. Thanks. So can you see if that road work outside is messing with my service? I just want to make sure it's not something on my end.
AGENTI noticed something: the account I pulled up is BW-883011, but you said your number ends in one, and I searched BW883017. Let me clarify that before going further. You said "last digit is one," but the number I entered ended in 7. Is your account number BW883011? I'd like to make sure we're looking at the right account before I check the outage.
CUSTOMERSorry.
CUSTOMERI might have talked too fast. I'm a bit frazzled. It's BW883011. So yeah, the last digit is one. Please tell me that's the right one.
AGENTYes, BW883011 is the account that came up, so we're on the right one. Let me check for an outage now.
AGENTI don't see any known outage or maintenance in your area, so it's not a reported area issue. The road crew could still have damaged a line, so I'll test yours directly.
CUSTOMEROkay. I appreciate you checking. Is there any way you can tell if the road crew messed up my line? I just want to be sure it's not something I did. And, uh, I already rebooted the gateway twice and checked all the cables, so I hope you don't ask me to do that again.
AGENTYou didn't do anything wrong, and I won't ask you to reboot or recheck cables. - Your line: The signal from our network to your gateway tested good, so I don't see any sign that the road crew damaged it. - The problem: Your gateway had dropped off our network ("not registered"). That's why the light was blinking orange, even though the line was fine. Your own reboots wouldn't have fixed that, since it had to be reset from our side. - Now: I sent a remote reset, and the gateway now shows as registered and online. It can take about two minutes for your devices to reconnect. Your account number is BW883011. Can you check whether the light has changed and you're back online? If it hasn't, I'll get a technician scheduled.
CUSTOMEROh, sorry. I just checked again, and the lights still blinking orange, so I guess it's not fixed yet. Can you please send a technician out? I really need this backup. I can't work without it. How soon can they come by?
AGENTUnderstood, I'll get that set up now.
CUSTOMERAll right. Thank you. Um, could you let me know when the tech will be here? I'm just real anxious about getting back online. Sorry for being a bother. I just want to make sure everything gets sorted.
AGENTYou're not a bother at all. I can offer two windows for account BW883011:
- Monday 800 AM to 10:00 AM
- Monday 100 PM to 3:00 PM
Those are the only openings the system returned, so I can't promise anything sooner. Which one works for you? I also can't confirm the appointment yet, because the tool only returned the available windows. Once you pick one, I'll tell you what I can confirm. One more thingthe reset showed your gateway as online, but your light is still blinking orange. That may need the technician to look at it in person.
CUSTOMERAll right. Thanks for explaining. I'd rather take the 1 p.m. to 3 p.m. window on Monday, if that's possible. Just want to make sure I'm here and can get work done after. Is it okay if I pick that slot? And, um, can you make sure the tech knows the lights still blinking orange so they check everything.
AGENTPicking that slot is fine, but I have to be upfront about two limits. - Booking: My scheduling tool only shows me the available windows. It has no way to book one, so I can't confirm that Monday 1:00 PM to 3:00 PM is reserved for you. I don't want to tell you it's set when I can't verify it. - Notes for the tech: I also can't attach a note about the orange light. I don't have a way to send one.
CUSTOMEROh. That's a bit worrying, but thank you for being honest. So just to be clear, I can't actually reserve the Monday 1 p.m. to 3 p.m. slot right now. Is there any way to make sure I get a tech out here, or should I try calling back later? And I guess since you can't leave a note, do you think the tech will know to check the gateway's light?
AGENTThat's right, I can't reserve the Monday 1:00 PM to 3:00 PM slot from here. I can see the open windows, but I have no way to book one, and I can't confirm a technician is on the schedule. Getting the tech booked: I don't have another route to book it myself. The best step is to call Brightwave support back, or use any scheduling option in your account, and ask for the Monday 1:00 PM to 3:00 PM window on account BW883011. I can't promise that slot will still be open when you do, so it's worth doing soon. The orange light: Since I can't leave a note, I can't say the tech will know about it. When you book, tell the agent that:
- The line test showed good signal, but the gateway was "not registered". - A remote reset showed it online, but the light is still blinking orange. - You've already rebooted twice and checked the cables. That should save time on the visit. You've had two hours of downtime on a work-from-home day. I haven't applied a service credit, since I'd rather not do that before the issue is resolved.
CUSTOMERAll right. Um. I understand. I'll call Bright Wave Support back soon and ask for the Monday 1 p.m. to 3 p.m. slot. I'll make sure to tell them about the light and everything you just said. Thanks for being clear with me. Even if it's not what I hoped for. Sorry again for all the trouble. I just want to get back online. Goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, this is Jordan Ellis. I need to reschedule my dermatology appointment next Wednesday morning. I just got scheduled for a work shift then, so I can only do something after 3 p.m.. Can you help me move it?
AGENTHappy to help, Jordan. First I need to verify your identity. Could you give me your full name as it appears on your record and your date of birth?
CUSTOMERSure. My full name is Jordan Ellis. March 17th, 1948. Sorry, no. 1984. March 17th, 1984.
AGENTThanks for the correction. I'll verify you with March 17th, 1984.
CUSTOMERRight. That's correct. Go ahead.
AGENTThanks, Jordan, you're verified.
CUSTOMEROkay.
AGENTI found your current appointment: Dr. Okafor, next Wednesday at 9:15 a.m. at Main Campus, Building B. Dr. Okafor has no openings after 3 p.m. on Wednesday itself. The openings that meet your after-3 p.m. requirement are:
- Tuesday at 345 p.m.
- Thursday at 410 p.m. If either works, tell me which one and I'll move your appointment. If you'd rather stay on Wednesday, I can look at other options.
CUSTOMERTuesdays don't work after all. Because I pick up my daughter. Then what about Friday? Are there any openings?
AGENTDr. Okafor's only Friday opening is at 11:30 a.m., which doesn't meet your after-3 p.m. requirement. That leaves Thursday at 4:10 p.m. as the one option that fits everything. Would you like me to move your appointment there?
CUSTOMERYes.
CUSTOMERRight. Please go ahead and move it to Thursday at 4:10 p.m. before we finish, is there any fee for changing the appointment?
AGENTI'll make the change and check the policy on fees at the same time.
AGENTThe policy is checked. The reschedule itself still needs to be done, so I'm doing that now.
CUSTOMEROkay. Thanks for letting me know. While you're making the change, could you tell me where to park for the appointment?
AGENTYour appointment is moved, Jordan. You're now booked with Dr. Okafor on Thursday at 4:10 p.m. 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. Fee: Changes made more than 24 hours before the appointment are free. Since you changed this well ahead of time, there's no fee. Changes within 24 hours carry a $40 fee. Parking: There's free patient parking in Lot C, with the entrance on River Road.
Is there anything else I can help you with?
CUSTOMERYes. One last thing. Does Doctor Okafor accept Aetna insurance?
AGENTI don't have any information on which insurance plans Dr. Okafor or the clinic accepts, and I don't want to guess. The best way to confirm is to call the clinic's billing or front desk, or check with Aetna directly. Since you'll be bringing your insurance card on Thursday, it's worth confirming before then. Is there anything else I can help you with?
CUSTOMERNo. That's everything. Thank you for your help. Goodbye.
AGENTYou're welcome, Jordan. Your appointment is Thursday at 4:10 p.m. with Dr. Okafor, confirmation code RVB-3M8P2. Goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. Uh. I'm sorry. I need help real quick. The pipe under my kitchen sink just burst. Water's everywhere, and it's heading for a power strip. My baby's crying and I haven't shut the water off yet. Can you tell me what to do? And, uh, can someone come out for an emergency repair?
AGENTYou're doing the right thing by calling. Here's what to do right now:
1. Stay away from that power strip and anything plugged into it. Don't touch it while there's water near it. If the breaker panel is dry and easy to reach, switch off the kitchen breaker or the main breaker.
CUSTOMERAll right. I'll make sure I don't touch the power strip. Uh, let me check if I can get to the breaker panel.
CUSTOMERYeah, I think I can reach it. Should I turn off the kitchen breaker or just the main one?
AGENTGo with the main breaker. With water spreading, it's the safest and fastest option, and you don't have to guess which circuit feeds that power strip. Only do it if the floor around the panel is dry and you aren't standing in water. If it isn't, skip it and stay clear. Next, shut off the water. First try the shutoff valve under the sink and turn it clockwise. If it's stuck or underwater, go to the main water shutoff, usually where the water line enters the house, near the water heater, or by the street meter. Turn that clockwise too. While you do this, I'll look you up. What's the phone number on your account, or the service address?
CUSTOMERAll right, I'll turn off the main breaker. The floor is dry around it, so I think it's safe. Okay, now I'm shutting the water off under the sink. Yeah. It stopped. Thank you. That helped a lot. My address is 1480 Larkspur Avenue. Uh, I just moved from unit four B to unit four D last month, so please use four D, and my phone number is (503) 555-0139. No, 0193. Is that enough to find me?
AGENTGlad the water's stopped. I'll look you up now and check emergency availability.
CUSTOMEROkay. Sorry for rushing. I just want to make sure someone can get out here soon. I'm waiting. Let me know if you need anything else from me. Thank you. Sorry. I just want to make sure you've got the right info. It's unit 4D now, and the phone number is (503) 555-0193. Is that okay?
AGENTNo need to apologize.
CUSTOMERAll right.
CUSTOMEROkay. Got it. What happens next? Can someone come before 2 p.m.? And, uh, how much will the visit cost?
AGENTI found your account, and I'll use unit 4D and (503) 555-0193 instead of what's on file. I only need one more thing from you. The earliest emergency window is today, 2:00 PM to 4:00 PM. It's the only emergency slot available, so I can't get anyone out before 2.
CUSTOMERAll right. Thanks for checking. So, just so I'm clear, 2 p.m. to 4 p.m. is the soonest. Is there any way to get someone out sooner, or is that really the only slot? And, um, could you tell me how much the visit will cost before I confirm it? I just want to make sure I know what to expect.
AGENTYes, 2:00 PM to 4:00 PM today is the soonest the system shows. It's the only emergency window, so I can't get anyone there sooner. You're a Copperline Care member, so the emergency callout fee for you is $99 (it would be $149 for a non-member). Would you like me to book the 2:00 to 4:00 PM window at $99? If so, I also need to know whether there's a gate code or any access instructions for getting to unit 4D.
CUSTOMERYes, please book that window. I'm nervous, but $99 is all right. I just want to make sure that covers the emergency visit. And, uh, there is a gate code. It's pound 2719. Do you need anything else from me? Who's coming out? And how will I know they're on the way? And could you give me the ticket number so I can keep track?
AGENTI'll open the request and book it now.
AGENTYou're booked.
CUSTOMEROkay. Thank you. That's exactly what I needed. I'm glad you've got it. All right. Please tell me who's the technician and how will I know they're on the way? And, uh, could you say the ticket number again? Just so I heard it right? I'm still a little anxious. Sorry.
AGENTNo need to apologize. Here are the details:
- TechnicianDana
- Arrival windowtoday, 2:00 PM to 4:00 PM
- How you'll know they're on the wayDana will text (503) 555-0193 about 30 minutes before arriving. - Ticket number: CPL-58210, which is C-P-L, 5-8-2-1-0
- Address1480 Larkspur Avenue, Unit 4D
- Gate codepound 2719
- Callback number(503) 555-0193
- Fee$99 emergency callout, the Copperline Care member rate
Until Dana arrives, leave the water off at the sink and keep the main breaker off if the area near the panel stays dry. Stay away from the power strip and any wet outlets. If you can, put towels down or use a bucket to keep the water from spreading. If anything changes, like water starting to flow again or a burning smell or sparks, call us right back. If you ever feel you're in danger, call 911. Is there anything else I can help with?
CUSTOMERNo, I think that covers everything. Thank you so much for your help and for explaining it all. I really appreciate it. I'll keep an eye out for Dana's text, and I'll stay clear of the power strip. Goodbye.
CUSTOMEROh. Hello.
AGENTHello again, I'm still here.
CUSTOMERNo, sorry. Nothing's changed. I just wanted to confirm. I got the ticket number. Right. CP L 58210, right? And Dana will text before coming. I think I'm all set. Thank you again. I'll let you know if anything changes. Goodbye.
AGENTYes, the ticket number is CPL-58210, and Dana will text (503) 555-0193 about 30 minutes before arriving. You're all set for 2:00 to 4:00 PM today at 1480 Larkspur Avenue, Unit 4D. If anything changes, call us right back. Take care of that little one, and goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I think so. Sorry. I'm at home right now. Just, uh. My baby's crying, and I'm a little flustered, but nobody's hurt, so I guess we're all right. Is that okay?
AGENTNo need to apologize, and yes, that's okay. Take whatever time you need with your baby. I'm glad everyone is safe and nobody is hurt. When you're ready, I'll start by verifying your policy. Can you give me your policy number and the last name on the policy?
CUSTOMERRight. Uh, let me get that for you. The policy number should be NG4471903.
CUSTOMERNo, sorry, last one is two, it's NG4471902. And the last name on the policy is Carter. Is that enough?
AGENTThat's enough, thank you. I'll use the corrected number, NG4471902.
CUSTOMERYeah that's right. Sorry again, I just want to make sure nothing gets mixed up. So, uh, can I ask what happens next?
AGENTThank you, Ms. Carter. I've verified policy NG4471902 for your 2021 Honda CR-V. You don't need to apologize. Double-checking is a good idea.
CUSTOMEROkay. Got it. Sorry. Uh, just before you go on, I do need to know what I'll have to pay. And if I can get a tow truck and a rental car. And, uh, will my premium go up? I'm pretty worried about all that. Is it okay if I ask about those as you work on the cleaning?
AGENTOf course you can ask, and I'll answer what I can. I'll check your coverage now.
AGENTHere's what your policy shows:
- DeductibleYour collision deductible is $500. - Rental: $40 per day for up to 30 days, starting from the day the claim is opened. - Towing: Covered up to 25 miles. I can arrange a tow if the car can't be driven safely. I can't tell you whether your premium will go up. I don't have anything that shows that, and I won't guess. Your adjuster or your agent can tell you more about that.
CUSTOMEROkay. He hit me. So I should not have to pay that deductible, right? And yeah, I definitely need a tow. The rear wheels rubbing bad. Where will they take the car? Can you tell me what the claim number is? Sorry. I just want to be sure everything's set.
AGENTI can't say whether you'll owe the deductible. Who was at fault gets decided during the claim, and I don't have anything that shows how that will turn out. Your adjuster can explain how the deductible works once they've looked at it. The policy shows a $500 collision deductible. I'll set up the tow once I know where the car is. I don't have information about where the tow company will take it, so I won't guess. I'll tell you anything the tow dispatch gives me. I don't have a claim number yet because I haven't opened the claim. I'll read it back to you as soon as I do.
CUSTOMERRight. Sure. Go ahead. Sorry. I'm just anxious about all this. Uh, the accident happened about 20 minutes ago at Southeast fifth Avenue and Alder Street. I was stopped at a red light. Another car hit the back of mine. The back bumper is crushed and the rear wheel rubbed, so I can't drive it. Nobody is hurt. And police did not come. The other driver's name is Kevin Lund. He's insured with Pacific Shore. His plate is 7KX, like X-ray R 214. Is that enough, or do you need anything else?
AGENTThat's very helpful, and you're doing fine. I have what I need to open the claim. First I want to check the plate with you: 7-K-X-R-2-1-4. Is that right? One more question: you said you're at home now, but the tow needs to know where the car is. Is it still at Southeast 5th and Alder, or did you move it?
CUSTOMERYeah, it's still at SW fifth and Alder. I haven't moved it. Just got it parked at the curb. Is that okay? Sorry. Do you need a street address or anything else for the tow?
AGENTParking it at the curb is fine. You said Southeast 5th earlier and Southwest 5th just now, and I want the tow driver to go to the right place. Which one is it, Southeast or Southwest? An intersection is enough for the tow. It would also help to have a phone number the driver can call you on. Once I have those, I'll open the claim and arrange the tow.
CUSTOMERSorry. It's southeast. Fifth and Alder, not southwest. I got flustered and said it wrong. And, uh, my phone number is (660) 998-8962. That's the number I'm calling from. Is that okay?
AGENTYes, that number is fine, and I'll use Southeast 5th and Alder. I'm opening the claim and arranging the tow now.
AGENTECB
CUSTOMERSorry. What's ECB? Is that something for the claim or the tow? Just want to make sure I get everything right.
AGENT"ECB" was a typo on my part. It isn't anything for your claim or the tow, so please ignore it. Here is where things stand.
CUSTOMEROkay. Thanks for clearing. That up. And, uh, the claim number is NGM904417, right? Please tell me if that's correct. I just want to be sure. Is there anything else I need to do right now?
AGENTYes, that's right. Your claim number is NGM-904417.
CUSTOMEROkay.
AGENTHere is everything for your records:
- Policy numberNG4471902
- Claim numberNGM-904417
- Other driver's plate7-K-X-R-2-1-4 (Kevin Lund, Pacific Shore). You haven't confirmed this plate yet, so please tell me if any of it is wrong. - Adjuster: Priya Shah. She will contact you within one business day. - Tow: Eastside Towing is on the way to Southeast 5th and Alder, about 45 minutes out. They'll take your CR-V to our partner repair shop at 9th and Morrison. The driver will call you at (660) 998-8962. - Rental: $40 per day for up to 30 days, counted from today, the day the claim was opened. - Deductible: $500 collision deductible. Ask Priya how it applies, since fault gets decided during the claim. What to do now:
- Stay safe, and let the tow driver know your CR-V is parked at the curb. - If you took photos of the damage or the other car, keep them for Priya. - Keep any information you got from Kevin Lund. Is the plate correct? Is there anything else I can help with?