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
#500of 655 stacks
42 / 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.
#344 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.
#273 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.
#611 of 662 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 662 on the board · best 0.0 per call
Speech-to-Text
Semantic word error rate
The caller's words the agent's transcriber got wrong in a way that changes the meaning, as a judge reads each difference.
#457 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.
#534 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.
#586 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.
#601 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.
#384 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.
#362 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.
#562 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#111 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 94% | 3.84 s | — |
| Home services | 85% | 3.79 s | — |
| Insurance | 96% | 3.66 s | — |
| Customer support | 91% | 4.11 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 96% | 3.67 s | — |
| Spanish-accented English, city street | — | — | — |
| Indian English, busy café | 89% | 4.43 s | — |
| Southern US, flustered, crying baby | 91% | 3.76 s | — |
| Fast and interrupting, construction outside | 87% | 3.71 s | 97% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi, Alex.
CUSTOMERI am working from home today, but my internet has been down for two hours now.
CUSTOMERThere is a road crew digging up the street outside, so I'm not sure if that is related. I have already rebooted the gateway twice and checked all the cables.
CUSTOMERThe internet light is blinking orange.
CUSTOMERCan you check what is happening?
CUSTOMERMy account number is BW88.
CUSTOMER3017.
CUSTOMERSorry, last digit is one.
AGENTI’ve got you pulled up as account BW8830171, on our Brightwave 500 plan. There’s no area outage showing for your address. I ran a line test and your signal looks good, but the gateway wasn’t registered, so I just sent a remote reset from here. It’s now showing as registered and online on my side. Over the next couple of minutes you should see:
- The internet light go solid (not blinking orange)
- Your devices start reconnecting on their own
Please give it about 2 minutes, then
1. Check the internet light on the gateway (should be solid). 2. Try loading a couple of sites on your work computer and maybe your phone (on Wi‑Fi). Tell me
- Is the internet light solid now? - Are you able to get online on at least one device?
CUSTOMERYeah.
CUSTOMERThe internet light just went solid white.
CUSTOMERHow long until my devices reconnect?
CUSTOMERShould I expect everything to work right away, or is there a delay?
AGENTYou’re in good shape now that the light is solid white. Most devices will reconnect within 1–2 minutes after the gateway comes fully online. In practice:
- Wi‑Fi devices (laptops, phones, tablets)usually reconnect automatically within seconds to a minute. - Wired devices (desktop, work PC, VOIP phone): should be back as soon as the connection is restored, typically under a minute. If anything doesn’t come back on its own after about 2 minutes, do this on that specific device:
- Wi‑Fitoggle Wi‑Fi off and back on, then reconnect to your usual network. - Wired: unplug and replug the Ethernet cable once, then retry. If you want, try a speed test or loading a few work sites now and tell me if everything looks normal.
CUSTOMEROkay.
CUSTOMERI will.
CUSTOMEREverything in a minute.
CUSTOMERBy the way, can you give me a credit for the downtime? I lost two hours of work because of this issue.
AGENTI’ve added a service credit for you on account BW8830171. It’s for $10.00 and will appear on your next bill. Since the light is solid now, your devices should all be back within about a minute. If anything is still offline after that—especially your work computer—tell me:
- Wired or Wi‑Fi? - What exactly happens when you try to load a site? I’ll help you get it sorted quickly if anything’s still acting up.
CUSTOMER$10.
CUSTOMERI lost. Two hours of work.
CUSTOMERCan you make it more than that?
AGENTI understand why that feels frustrating, especially when you’re trying to work from home. I can’t change the amount the system just applied myself, but here’s what I can do from my side:
- I’ve already added the $10.00 credit to account BW8830171, which will show on your next bill. - I can document your account with notes that you experienced about two hours of downtime while working, and that you requested a larger credit. If you’d like to push for a higher adjustment, billing or customer care can review it since they’re the only ones who can override standard credits. I can add a clear note now so you don’t have to re‑explain everything when you contact them. Do you want me to add those notes to your account?
CUSTOMERYes. Please add the notes about the downtime. And my request for a higher credit. I will follow up with billing if needed.
CUSTOMERThank you for your help, Alex.
CUSTOMERGoodbye.
AGENTI’ve added notes on account BW8830171 that you had about two hours of downtime while working from home and that you’re requesting a higher credit than the $10.00 already applied, so billing sees that context when you contact them. Glad we could get you back online. Take care, and goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, Alex.
CUSTOMERI need to reschedule my dermatology appointment next Wednesday morning. Something came up at work, and I can only come after 3 p.m.. Could you help me move it? My name is Jordan Ellis.
AGENTI can help with that. I’ll just need your date of birth to look up your chart and find the appointment under “Jordan Ellis.”
CUSTOMERMarch 17th.
CUSTOMER1948.
CUSTOMERSorry. No. 1984. March 17th, 1984.
AGENTI’ve found your dermatology visit with Dr. Okafor next Wednesday at 9:15 a.m. at Main Campus, Building B. Looking at Dr. Okafor’s schedule starting next Wednesday, there actually aren’t any open slots with her after 3 p.m. that same day. The closest available options with Dr. Okafor are:
- Tuesday at 345 p.m.
- Thursday at 410 p.m. There’s also Friday at 11:30 a.m., but that’s before 3 p.m.
Would you like me to move your appointment from next Wednesday at 915 a.m. to either:
- Tuesday at 345 p.m., or
- Thursday at 410 p.m.? And do you want to stay specifically with Dr. Okafor, or are you open to another dermatologist if that’s the only way to get a late-afternoon slot on Wednesday?
CUSTOMERI need to. Stick with Doctor Okafor.
CUSTOMERTuesdays don't work after all.
CUSTOMERI pick up my daughter. Then. What about Friday? Any openings after 3 p.m.?
CUSTOMERIf not, let's go with Thursday at 4:10 p.m..
AGENTI checked Dr. Okafor’s schedule for Friday—she only has an opening at 11:30 a.m., nothing after 3 p.m. I’ve gone ahead and moved your dermatology appointment with Dr. Okafor from next Wednesday at 9:15 a.m. to:
- Thursday at 410 p.m.
- LocationMain Campus, Building B
- Confirmation codeRVB-3M8P2
Please arrive about 15 minutes early with a photo ID and your insurance card. Can I help you with anything else for this visit—like directions or parking info for Building B?
CUSTOMERYes.
CUSTOMERActually.
CUSTOMERIs there a fee for changing the appointment? And where should I park for building B? Also, does Doctor Okafor accept Aetna insurance?
AGENTHere’s the info for you, Jordan Ellis, with date of birth March 17th, 1984:
1) Change fee
Your reschedule is free as long as the change was made more than 24 hours before the original appointment time. The clinic’s policy is
“Changes made more than 24 hours before the appointment are free; later changes carry a $40 fee.” 2) Parking for Building B
You can park in the free patient parking in Lot C, with the entrance on River Road. That’s the lot used for Main Campus, including Building B. 3) Aetna insurance
I don’t have a tool that lets me see plan-specific participation for Aetna or for individual providers like Dr. Okafor. To confirm whether your particular Aetna plan is accepted for visits with Dr. Okafor, please either
- Call the clinic’s front desk, or
- Check with Aetna (website or member services) using “Riverbend Health Clinic” and Dr. Okafor’s name. If you’d like, I can summarize your current appointment details once more so you have everything in one place.
CUSTOMERYes please.
CUSTOMERCan you read back the new appointment time and the confirmation code.
AGENTHere are your updated details:
- PatientJordan Ellis
- Date of birthMarch 17th, 1984
- ProviderDr. Okafor (Dermatology)
- DayThursday
- Time4:10 p.m.
- LocationMain Campus, Building B
- Confirmation codeRVB-3M8P2
Parking is free in Lot C, entrance on River Road.
CUSTOMERYes.
CUSTOMERThat's right.
CUSTOMERThank you for your help. Alex.
CUSTOMERGoodbye.
AGENTYou’re welcome, Jordan. Your appointment for Thursday at 4:10 p.m. with Dr. Okafor is all set under confirmation code RVB-3M8P2. Goodbye, and take care.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey, Alex. Um.
CUSTOMERSorry I'm a little flustered right now.
CUSTOMERI got a pipe burst under my kitchen sink, and water's spreading all over the floor. Heading right toward a power strip.
CUSTOMERI need help as soon as possible.
CUSTOMERCan you send someone out?
AGENTThanks for hanging in there with me. Let’s get you safe first, then I’ll get someone out as fast as we can. 1) Immediate safety steps (please do these now if you can):
- Stay away from that power strip and any outlets near the water. Don’t touch it, don’t try to unplug anything if water is near it. - If you can reach the power strip’s switch safely without stepping in water, turn it off. If not, leave it alone. - If water is already at the outlets or power strip, it’s safest to turn off power to the kitchen at your breaker panel (or the main breaker) if you can reach the panel without going through water. 2) Shut off the water
- Look under the kitchen sink for the small shutoff valves on the pipes (usually one for hot, one for cold).
AGENT- Turn each one clockwise until it stops. - If those don’t work or you can’t reach them safely, go to your main water shutoff (often in a basement, garage, utility room, or outside by the street in a ground box) and turn it clockwise to shut off the house water. Please tell me:
- Are you able to stay clear of the water and the power strip right now? - Were you able to shut off the under-sink valves or the main water? Once you answer that, I’ll treat this as an emergency plumbing call and get the earliest possible arrival window for you. I’ll need a few details to open your service request
1. Your name
2. Service address (including unit/apartment number and any gate code)
3. Best callback phone number
4. Have we been out to your home before, or is this your first time with Copperline? After that, I’ll
- Check our emergency availability and fees,
- Tell you the exact fee that applies,
- Get your okay,
- Then book the earliest available emergency window and read everything back to you, including your ticket number.
CUSTOMERYeah. Okay.
CUSTOMERSo I've got the water shut off now.
CUSTOMERSorry.
CUSTOMERI should have said that sooner.
CUSTOMERIt stopped.
CUSTOMERSo that's good.
CUSTOMERI stayed clear of the power strip. Didn't try to unplug anything.
CUSTOMERI can reach the breaker if you need me to, but right now, nothing's sparking or anything.
CUSTOMERMy name's Wade Carter.
CUSTOMERAddress is 1480 Larkspur Avenue, unit 4D, not four B. I moved last month.
CUSTOMERThe gate code is 2719.
CUSTOMERCall back number is 503555.
CUSTOMER0139.
CUSTOMERNo. Oh. 193.
CUSTOMERI think you all have been out before, but not since I moved units.
CUSTOMERCan you tell me how much this will cost before you send someone?
CUSTOMERAnd, uh.
CUSTOMERIs there any way someone can come before 2 p.m.?
AGENTThanks, Wade, and no worries—you did the right things. First, on safety:
Since water was heading toward a power strip, I do recommend you flip off the breaker for the kitchen or the outlets that feed that area if you can get to the panel without walking through any wet floor. That just removes any lingering risk while things dry out.
CUSTOMERSorry. It's.
CUSTOMERTwo. Seven. One nine.
CUSTOMERIs that okay?
CUSTOMERJust want to make sure you have the right gate code.
AGENTYes, that’s perfect—thank you for catching that. I’ve got the gate code as 2719. Let me answer what you asked a minute ago and then I’ll confirm all your details:
1) Cost for today’s visit
You’re a Copperline Care member, and this is an emergency plumbing call.
CUSTOMERI.
CUSTOMERAll right. Thanks.
CUSTOMERIt's $99 just to visit.
CUSTOMEROr does that include the fix? If it's something simple. Sorry.
CUSTOMERI'm just anxious about the cost.
CUSTOMERCan
AGENTYou’re okay, Wade—asking about cost is completely reasonable. Here’s how it works for you as a Copperline Care member:
- $99 emergency call-out = the trip/diagnostic fee for today’s emergency window. - That $99 does *not* include the repair itself. - Once the plumber sees the burst pipe, they’ll
- Diagnose what failed,
- Give you a clear estimate for the repair (parts + labor),
- Get your approval before doing any chargeable work beyond the $99. If it turns out to be something simple and quick, the cost may be on the lower side; if parts or more time are needed, they’ll explain options so you can decide. On timing
- The earliest emergency window I have is today, 200–4:00 PM. - There’s nothing earlier than 2 PM showing on my end for emergency slots, or I’d offer it. Right now I have you set up as:
- NameWade Carter
- Address1480 Larkspur Avenue, Unit 4D
- Gate code2719
- Callback number503-555-0193
- IssueBurst pipe under kitchen sink; water is off; water reached floor and approached a power strip, no active electrical issues. - Urgency: Emergency
- Earliest available windowToday, 2:00–4:00 PM
- Emergency Copperline Care call-out fee$99, plus any approved repair costs
Your service request ticket number is CPL-58210. Do I have your okay to book the 200–4:00 PM emergency window today for a $99 call-out, with any additional repair work only done after the technician gives you an estimate and you approve it?
CUSTOMERyou. Tell me who's coming out and how. I'll know when they're on the way.
CUSTOMERYeah. That's
CUSTOMERfine. Please go ahead and book the
CUSTOMERtwo. Thank you, Alex, I.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes.
CUSTOMERI am.
CUSTOMERI am standing next to my car in a cafe parking lot.
CUSTOMERNobody is hurt.
AGENTI’m glad to hear nobody is hurt. Let’s get your claim started. I’ll first look up your policy. 1) What is your auto policy number? 2) What is the policyholder’s last name? After that, I’ll ask:
- When the accident happened
- Where exactly it happened
- What happened
- The other driver’s name, insurer, and license plate
- Whether police came to the scene
Also, can your car be driven safely, or does it need a tow?
CUSTOMERSure.
CUSTOMERMy policy number is NG44719030. Sorry.
CUSTOMERLast one is two. The policyholder's last name is Mehta.
CUSTOMERThe accident happened about 20 minutes ago.
CUSTOMERI was stopped at a red light at SW fifth Avenue and Alder Street. Another car hit the back of my car.
CUSTOMERThe other driver's name is Kevin Lund.
CUSTOMERInsured with Pacific Shaw.
CUSTOMERHis license plate is 7KX, like X-ray.
CUSTOMERR 214.
CUSTOMERPolice did not come to the scene.
CUSTOMERMy back bumper is crushed and the rear wheel is rubbing, so I cannot drive the car. It needs a tow.
AGENTI’ve got everything I need to open the claim and get you a tow started. First, let me read a few key details back to you:
- Policy number I haveNG44719032
- Other driver’s plate7KX R214
Please tell me if either of those is not correct. Here’s what I’ve recorded about the accident; stop me if anything needs changing
- You’re the policyholderMehta, driving a 2021 Honda CR‑V. - The accident happened about 20 minutes ago at SW 5th Avenue and Alder Street, near the café parking lot. - You were stopped at a red light when another car hit you from behind. - Other driver: Kevin Lund, insured with Pacific Shaw, plate 7KX R214. - No one is injured and police did not come, so there’s no report number. - Your rear bumper is crushed, the rear wheel is rubbing, and the car cannot be safely driven. I’ve opened your claim:
- Your claim number isNGM-904417
- The assigned adjuster is Priya Shah. - The note I have says she will contact you within one business day. Now, about the tow
- A tow truck has been dispatched to the café parking lot near SW 5th and Alder. - Tow companyEastside Towing
- Estimated arrivalabout 45 minutes
- Destinationa Northgate partner repair shop at 9th and Morrison. A couple of quick questions so I can finalize the tow and notes:
1) What phone number should the tow driver use to reach you when they arrive? 2) Is it okay that the vehicle goes to that partner shop at 9th and Morrison, or do you have another repair shop you prefer? If you have any questions about what’s covered (rental car, towing, repairs), tell me what you’re wondering about and I’ll look up your specific coverages.
CUSTOMERThe tow driver can use my number.
CUSTOMERIt is 91123026272.
CUSTOMERThe partner shop at ninth and Morrison is fine. I do not have another preference.
CUSTOMERI am wondering.
CUSTOMERHow much will I have to pay for this repair? Is there a deductible? But he hit
AGENTI’ve added your phone number, 91123026272, for the tow driver, and confirmed it’s okay to take your car to the partner shop at 9th and Morrison. Here’s what your policy shows for costs and deductibles:
1) Repair costs and deductible
- Your collision deductible is $500. - Because you were rear‑ended, we will still handle your repairs under your policy if you choose, but
- You would initially be responsible for the $500 deductible on your claim. - If we confirm the other driver (Mr. Lund, Pacific Shaw) is at fault and recover money from his insurer, we will seek to recover your $500 deductible for you. If/when that happens, you may get that money back, in whole or in part, depending on recovery. 2) Tow cost
- Towing is covered up to 25 miles under your policy. - The tow to the partner shop at 9th and Morrison should fall within that, so you should not owe anything out of pocket for the tow, as long as it’s within that distance. 3) Rental car coverage
- Your policy includes rental reimbursement up to $40 per day, for up to 30 days, starting from today when the claim was opened. - That means if your vehicle is in the shop for covered repairs, you can rent a car and we’ll reimburse up to $40 per day, up to the 30‑day limit. Next steps
- The shop will inspect the damage and send an estimate to Northgate. - Your adjuster, Priya Shah, will review fault, coordinate with Pacific Shaw, and talk with you about the deductible and any recovery from the other driver’s insurer. To recap the key numbers I have for you
- Policy numberNG44719032
- Other driver’s plate7KX R214
- Claim numberNGM-904417
Do those all look correct to you, especially your policy number and the license plate? And would you like help understanding how the deductible works if Pacific Shaw accepts full fault?
CUSTOMERme. So I should not have to pay that right? Also, will I get a rental car while.
CUSTOMERYes. That's right.
CUSTOMERMy policy number. Is n g.
CUSTOMER4471902.
CUSTOMERThe other driver's plate is seven.
CUSTOMERK.
CUSTOMERX like X-ray.
CUSTOMERR.
CUSTOMER214.
CUSTOMERClaim number.
CUSTOMERNGM.
CUSTOMER904417.
CUSTOMERThose are correct.
CUSTOMERIf Pacific Shore accepts full fault.
CUSTOMERI would like to know how that works.
CUSTOMERWill I get my deductible back?
CUSTOMERAnd will my premium
AGENTYou’re right on all the key numbers, and I’ve updated what you corrected:
- Policy numberNG4471902
- Other driver’s plate7KXR214
- Claim numberNGM-904417
Now to your questions, assuming Pacific Shaw accepts full fault for their driver
1) Do you have to pay the deductible? - On your policy, there is a $500 collision deductible. - In many rear‑end situations, we still handle your repairs under your policy so things move faster. - At the repair stage, you may still be asked to pay your $500 deductible to the shop or have it applied against the repair amount. - Then Northgate will go after Pacific Shaw to recover what we paid, including your deductible. 2) Will you get your deductible back? - If Pacific Shaw accepts full fault and pays Northgate back, we will also seek to recover your $500 deductible. - If we recover it in full, you get the full $500 back. - If we only recover part of the loss (for example, if liability is split), you may get only a portion of the deductible back, depending on how much is recovered. - Your adjuster, Priya Shah, will tell you
- When we’ve made a demand to Pacific Shaw
- If they’ve accepted fault
- How much of your deductible we were able to recover for you
3) Will your premium go up? I can’t see or predict specific premium changes, but here’s how it usually works
- Fault matters
- If Pacific Shaw accepts 100% fault for their driver, this is generally treated as an at‑fault accident for them, not you. - In that situation, insurers often do not surcharge your policy for an at‑fault loss. - However, Northgate’s rating rules and your overall history (prior claims, violations, etc.) also play a role, and I can’t see or guarantee how your future premium will change. - Your adjuster can
- Confirm how we’re recording fault on your claim. - Let you know if this claim is expected to be treated as not‑at‑fault on your record once liability is final. 4) Rental car while your car is in the shop
- You do have rental coverageup to $40 per day, for up to 30 days, starting from today (the day the claim was opened). - That means:
- If your car is in the shop for covered repairs, you can get a rental and Northgate will pay/reimburse up to $40 per day, up to the 30‑day limit. - If Pacific Shaw accepts fault, they may also provide a rental directly; your adjuster can coordinate so you’re not paying out of pocket where we can avoid it. Summary in plain terms
- For now, expect that you may have to pay your $500 deductible when the repairs are done. - If Pacific Shaw accepts full fault and pays Northgate back, we’ll work to refund that $500 to you. - A rear‑end where the other driver is at fault is less likely to raise your premium, but only underwriting can say for sure; your adjuster can at least confirm how the claim will be coded (at‑fault vs not‑at‑fault). Would you like me to walk through what happens next step‑by‑step—from the tow and shop estimate through to when you might see any deductible reimbursement?
CUSTOMERgo up?