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
#328of 655 stacks
48 / 100
Leader AssemblyAI Universal-3.5 Pro + OpenAI GPT-6.1 Sol + ElevenLabs Turbo v2.5, 70 / 100
Where it ranks
Its models
Task completion
Task completion
How much of the caller’s task the agent completed: the share of the scenario’s checks a judge model found met in the transcript, averaged over calls. Before v1.3, the share of calls judged 4 or better out of 5.
#186 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.
#243 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.
#410 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.
#454 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.
#316 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.
#522 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.
#121 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.
#237 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.
#384 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#346 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 93% | 3.59 s | — |
| Home services | 88% | 3.74 s | — |
| Insurance | 98% | 3.28 s | — |
| Customer support | 96% | 3.33 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 96% | 3.32 s | — |
| Spanish-accented English, city street | 98% | 3.52 s | — |
| Indian English, busy café | 96% | 3.39 s | — |
| Southern US, flustered, crying baby | 96% | 4.02 s | — |
| Fast and interrupting, construction outside | 85% | 3.28 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, uh, sorry I got a baby crying here, so I might sound a little flustered. My internet's been down for about two hours now. I work from home, so it's kind of urgent. There's a road crew digging up the street outside. Could that be the reason I already rebooted the gateway twice and checked all the cables, the internet, lights, blinking orange. Can you help me figure out what's going on?
AGENTI can help. I’ll need to pull up your account and check for any outage first.
CUSTOMERNo. All right. My account number is BW 883017. Sorry. Last digit is one. Is that okay? You need anything else from me?
AGENTThanks, and yes, that account number works — I have you under BW8830171 at your service address on file. I checked your line: - No area outage at your address. - Your signal looks good, but the gateway had dropped its registration. - I’ve just sent a remote reset, and it’s now showing as registered and online on my side. The orange blinking light should turn solid (or change to the normal “online” pattern) within about 2 minutes, and your devices may need another minute or so to reconnect. While we wait: - If you’re on Wi‑Fi, watch for your network name to reappear and try reconnecting. - If you’re on a work PC
CUSTOMERNo. Okay. The light just went solid white. How long does it usually take for everything to reconnect? I got a bunch of devices for work. Just want to make sure I don't lose anything. And, um, since I lost two hours of work, can I get a credit for the downtime?
AGENTNow that the light is solid white, the connection itself is up. Here’s what to expect: - Most devices: 1–3 minutes to fully reconnect on their own. - Work gear with VPNs, remote desktops, or VoIP/softphones: you may need to manually reconnect apps or VPN sessions, but you shouldn’t lose files if they autosave. If anything’s in the middle of uploading, just re‑try the upload once your apps show you’re back online. I’ve also added a credit for the downtime: - Amount: $10.00 - Account: BW8830171 - It will appear on your next bill. If you can, try one quick test—open a browser on your work computer and load a site you don’t usually visit (like a news site). Tell me if that loads, and we’ll make sure everything’s solid before I let you go.
CUSTOMEROh. All right, so, uh, $10. Sorry. I lost two hours of work. Is there any way you can make it more than that? Okay, I'll try loading a new site real quick. Just want to make sure everything's set.
AGENTI get why that’s frustrating, especially when you’re working from home. The system approved a $10.00 credit on account BW8830171, and that’s the standard amount I’m allowed to apply directly for a short interruption like this. I don’t have the ability to increase it beyond that from here. If you feel that doesn’t reflect the impact on your work, you can contact our billing team through your account portal or by phone and ask for a supervisor review—they’re the only ones who can authorize anything larger. How did that new site load on your end—coming up normally, or still slow/not loading?
CUSTOMERAll right. I understand. Thanks for explaining. The new site's loading. Fine. Now. Looks good. I appreciate your help with all this. Guess I'll reach out to billing if I need to. Thanks again. Bye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMEROkay.
CUSTOMERHi, Alex. I'm short on time, so I'll be direct. I need to reschedule my dermatology appointment next Wednesday morning. I just gotta work shift then, so I'll need something after 3 p.m.. My name is Nate Brooks. Can you help with that?
AGENTI can help with that. I’ll need a couple details to look you up and see your appointment: 1) Your full date of birth (YYYY-MM-DD).
CUSTOMERYep. Got it. My date of birth is March 17th, 1948. Sorry. No. 1984. March 17th, 1984. Let's just find something. After 3 p.m.. March 17th, 1948. Sorry. No. 1984. March 17th, 1984.
AGENTThanks, Nate. I’ve got you pulled up with date of birth March 17th, 1984. You’re currently booked for dermatology with Dr. Okafor next Wednesday
CUSTOMERThat's right. And I need to move it to any slot after 3 p.m.. What's available?
AGENTHere’s what I can offer you with Dr. Okafor, starting from next week and only after 3
CUSTOMEROkay.
AGENTHere
CUSTOMERRight. I know the drill. Just tell me the soonest slot after 3 p.m., please.
AGENTYou got it. The soonest available dermatology slot with Dr. Okafor after 3 p.m. is: -
CUSTOMERYeah.
AGENTThe soonest available
CUSTOMERGo ahead. Okay. Just give me the next available. Time after 3 p.m..
AGENTThe soonest available dermatology slot with Dr. Okafor after 3 p.m. is:
CUSTOMERGot it.
CUSTOMERRight. Just let me. Know the exact day and time. Tuesdays don't work. Need something else?
AGENTThanks for hanging in with me, Nate. Here’s what I’ve got for Dr. Okafor, after 3 p.m., excluding Tuesday: - Thursday at 4:10 p.m. - (The other late slot is Tuesday at 3:45 p.m., but you said Tuesdays don’t work, so I’ll skip that.) The soonest that fits what you asked for is: > Thursday
CUSTOMERTuesdays don't work.
CUSTOMERPick up my daughter. Then. What about Friday? Yeah, Tuesdays are out Thursday at 4:10 p.m.. Works. Book it.
AGENTYou’re all set, Nate. I’ve moved your dermatology appointment with Dr. Okafor to: - Thursday
CUSTOMEROkay. Right.
CUSTOMERI just need. The new time and the. confirmation code to before I go. Is there any fee for changing the appointment?
AGENTHere you go, Nate: - New appointment time: Thursday at 4:10 p.m. with Dr. Okafor. - New
CUSTOMERGuide.
CUSTOMERThat works. Is there. A fee. For changing the appointment? Where should I park? Also, does Doctor Okafor accept Aetna Insurance. And I need the confirmation code for the new appointment.
AGENTHere’s everything you asked for, Nate: - New appointment: Thursday at 4:10 p.m. with Dr. Okafor. - Confirmation
CUSTOMERYep that's right. What's the confirmation code for that slot.
AGENTYour new dermatology appointment is confirmed for Thursday at 4:10 p.m. with Dr. Okafor. The confirmation code is: RVB-3M8P2.
CUSTOMEROkay. Got it. Is there a fee to change the appointment?
AGENTThere’s no fee for the change you just made. Riverbend’s policy is: changes made more than 24 hours before the appointment are free; within 24 hours there’s a $40
CUSTOMERUnderstood. Where should. I park when I come in?
AGENTYour dermatology visit with Dr. Okafor is at the Main Campus, Building B. Anything else you need before you go?
CUSTOMERJust one more thing. Does Doctor Okafor accept Aetna insurance?
AGENTI don’t have access to provider-by-provider insurance panel details, so I can’t safely confirm whether Dr. Okafor specifically accepts Aetna. To get an exact
CUSTOMERRight.
CUSTOMEROkay. That's fine. Thanks for your help. Goodbye.
AGENTYou’re welcome, Nate. Quick recap before
AGENTyou go: - New dermatology appointment: Thursday at 4:10 p.m. - Provider: Dr. Okafor. - Location: Main Campus, Building B. - Confirmation code: RVB-3M8P2. - No fee for this change since it was made more than 24 hours in advance. If anything else comes up, just reach out.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey, um, sorry I'm a little flustered right now. There's a pipe under my kitchen sink that's burst, and water is just spreading out across the floor. My baby's crying. I'm worried it's gonna reach this power strip. I haven't shut the water off yet. Can you help me, please?
AGENTI can help you. Let’s get things safe first. 1. Stay safe around electricity. - Keep yourself, your baby, and anyone else away from the water near that power strip. - If the water is close to the strip, do not touch the strip or anything plugged into it. - If you can safely reach it without stepping in water or touching anything wet, unplug the power strip or turn it off. - If there is any doubt, leave it alone and move on to shutting off the water. 2. Shut
CUSTOMEROh. Okay. Yeah. I'm keeping us away from it. The water's just about to reach it, so I won't touch anything. Sorry. This is just stressful. What do I need to do next to get the water shut off?
AGENTYou’re doing the right thing keeping clear of that power strip. Let’s get the water stopped. 1. Turn off the kitchen sink shutoff valves (fastest, if they work): - Open the cabinet under the kitchen sink. - You should see two small valves on the pipes (one for hot, one for cold), usually with small round or oval handles or little levers. - Turn each valve clockwise (to the right) until it stops. - Tell me: Do
CUSTOMEROh. All right, I'm turning those clockwise. Right. Okay. I think both are shut now. The water stopped. Is that right? Are you sure that's enough?
AGENTYes—that’s exactly what should happen. If the water has stopped flowing from that burst pipe, those shutoff valves are doing their job, and that’s enough for the moment. Let’s add one more safety step around the electricity, then I’ll get a plumber out to you. 1) Electrical safety right now. - Since the water was close to that power strip, keep everyone away from that area and don’t try to unplug anything. - If you can safely do it without going near the water, you can switch off just the kitchen circuit at your breaker panel—but only if it’s clearly labeled and you don’t have to stand in water or touch anything wet. - If that’s not easy or safe, just leave it and keep clear of that part of the floor. We’ll have the tech check the area when they arrive. 2) Contain the water if you can. - If it’s safe to move around: lay down towels or use a mop to keep the water from spreading, especially away from outlets, appliances,
CUSTOMERWow. Okay, I'll keep us clear of that area. I can grab some towels and start soaking up the water. Try to keep it from spreading. Is that all right? Sorry if I'm asking too much. I just want to make sure nothing else gets damaged. What happens next? Can you send someone out? And, uh, how much will it cost for the visit?
AGENTTowels are perfect—yes, go ahead and start soaking up and blocking the water, just stay clear of that power strip area and anything electrical near the wet floor. I can send someone out today. We have an emergency arrival window today from 2:00 PM to 4:00 PM for this kind of burst pipe. About cost: - The emergency call-out fee today is $149 for the visit. - If you’re on a Copperline Care plan, it would be $99 instead. - You’d pay by card or check on completion, and any repair work/costs would be explained and approved with you before they do it. If that fee and time window work for you, I’ll get this booked as an emergency
CUSTOMEROh. Thanks for explaining. Um, I really need someone sooner, if possible. Is there any way anyone could come before 2 p.m.? And, uh, I'm not on a care plan. I just moved into unit 4D last month at 1480 Larkspur Avenue. Is that okay?
AGENTYou’re not asking too much at all—this is exactly what we’re here for. On timing: I’ve checked our emergency schedule, and the earliest emergency arrival window we have today is 2:00 PM to 4:00 PM. There’s nothing available earlier showing on my end, even for emergencies. I know that’s not as soon
CUSTOMEROh. All right. I guess that'll have to do. Then please book that. 2 to 4.
CUSTOMERP m window for me. It's just, uh, can you confirm who's coming and how? I'll know they're on the way. And could you give me a ticket number for the visit? I want to make sure nothing gets missed.
AGENTI’ve got you scheduled. Here’s what’s set up: - Service window: Today, 2:00 PM to 4:00 PM. - Ticket number: CPL-58210. - Issue on file: Burst pipe under kitchen sink; water shut off at the under-sink valves; water on floor near a power strip. For your questions: - Who’s coming / how you’ll know: A Copperline plumbing technician will come out in that 2–4 PM window. They’ll text your callback number about 30 minutes before arrival to let you know they’re on the way. - Visit fee for you: I see you listed in our system, but you mentioned you’re not on a care plan and that you’re in Unit 4D, not 4B, so I’m going with what you told me. For today’s emergency visit, the call-out fee is $149, plus any approved repair costs. You’ll pay by card or check on completion. Let me read back what I have to be sure nothing gets missed: - Service address: 1480 Larkspur Avenue, Unit 4D. - Ticket number: CPL-58210. I don’t have a callback number written down yet—. What’s the best phone number for the technician to text and call before they arrive? Until they get there, you’re doing the right things: - Keep everyone, especially the baby, away from the wet area and the power strip. - Keep using towels to stop the water from spreading, especially away from outlets and appliances. - If anything changes—like the water starts flowing again—tell me right away.
CUSTOMERThank you.
CUSTOMERI really. Appreciate you double checking. My callback number is (503) 555-0139.
CUSTOMERNo, sorry, 0193. Please tell me that's all said. And can you confirm the gate code for the building? It's pound 2719. Is that going to be okay for the tech to get in?
AGENTGot it, and I’m glad you corrected it. Here’s what I have on file now: - Service address: 1480 Larkspur Avenue, Unit 4D. - Gate code / access: Gate code is #2719 for the building. - Callback number: (503) 555-0193. - Ticket number: CPL-58210. - Arrival window: Today, 2:00 PM to 4:00 PM. - Visit fee: $149 emergency
CUSTOMEROh. All right. I think. That covers everything. Thanks for helping me through all this. Really? I was pretty worried. I'll keep the area clear and watch for the text. Text. Goodbye.
AGENTYou’re all set, and you handled a really stressful situation exactly right. Quick recap before you go: - Water to the sink is shut off. - Area around the power strip stays off-limits. - Towels to contain the water is perfect. - Ticket: CPL-58210. - Today’s window: 2:00 PM–4:00 PM. - Tech will text you at (503) 555-0193 about 30 minutes before arrival and use gate code #2719. If
AGENTanything changes—like the water starts again or you notice anything electrical acting strange—call us right away. Take care of yourself and the baby; we’ll take it from here.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes. I'm standing next to my car. I am at a busy cafe, so there are many people around I am safe.
AGENTI’m glad you’re safe. Is anyone injured at the scene—either in your car, the other car, or any pedestrians? If anyone is hurt or in danger, please hang up and call 911 immediately before we continue.
CUSTOMERI know nobody is hurt. There are no injuries in my car or the other car and no pedestrians are involved. It is just damage to my car.
AGENTThank you for letting me know. Next, I’ll pull up your policy
CUSTOMEROkay.
AGENTI’ll
CUSTOMERRight. Go ahead.
AGENTI’ll look up your policy now so we can open a claim. What’s your auto policy number, and the policyholder’s last name?
CUSTOMERSure. My policy number is N 4471903. No, sorry. Last one is two. The policyholders last name is Martha.
AGENTThank you. I’ve verified policy N4471902 under the last name Martha for a 2021 Honda CR‑V. Now I’ll get the details of the accident so we can open your claim. 1)
CUSTOMERYes, that's right, it is for a 2021 Honda CRV. Go ahead.
AGENTI’ll get the details now so we can open your claim. 1) When did the accident happen? 2) Where did it happen? 3) Please briefly describe what happened. Then I’ll need a few details about the other driver: 4) The other driver’s name. 5) Their insurance company (if you were able to get it). 6) Their license plate number. And finally: 7) Did the police come to the scene, and is there a police report number? 8) Is your Honda CR‑V drivable and safe to drive, or does it need a tow?
CUSTOMERRight. Let me give you all the details. Once the accident happened about 20 minutes ago. Two, it was at the intersection of SW fifth Avenue and Alder Street. Three I was stopped at a red light and another car hit the back of my car. The back bumper is crushed and the rear wheel is rubbing so I cannot drive it for the other driver's name is Kevin Lund five. His insurance company is Pacific Shore six. His license plate is 7KX, like X-ray r 2147. Police did not come, so there is no police report. Number eight my Honda CRV is not drivable and needs a tow.
AGENTI’ve got everything I need, and I’ve opened your claim and set up a tow. First, let me read key details back to you: - Policy number: N4471902. - Other driver’s license plate: 7KXR2147. - Claim number: NGM-904417. If any of that is not correct, tell me and I’ll fix it. Now, about the tow: - I’ve dispatched Eastside Towing to the intersection of SW 5th Avenue and Alder Street. - Estimated arrival: about 45 minutes. - They’ll take your 2021 Honda CR‑V to a Northgate partner repair shop at 9th and Morrison. Your assigned adjuster is Priya Shah. You should hear from her within one business day about next steps, repairs, and coverage details. While you’re waiting, if it’s safe to do so: - Take photos of the damage to your car and the other car. - Take a photo of the intersection and any traffic lights/signs. - Keep the other driver’s info handy (name: **Kevin Lund**, insurer: **Pacific Shore**). Is there a safe place you can wait for the tow truck, and do you have any questions about what will happen next with this claim number NGM-904417?
CUSTOMEROkay. Yes, I am safe. I'm waiting at a busy cafe right next to my car. I do have a few questions. How much do I have to pay for this claim? Will I be getting a rental car and is my premium going to go up? Since he hit me, I should not have to pay a deductible, right? Also, can you confirm where my car will be taken? And I have noted the claim number n GM 904417.
AGENTI’ll walk through each of your questions one by one and confirm the tow destination at the end. First, just to confirm what you said: your claim number is NGM-904417 — that’s correct. 1) “How much do I have to pay for this claim? Since he hit me, I should not have to pay a deductible, right?” - Your policy shows a $500 collision deductible. - Whether you actually end up paying that depends on how the claim is handled: - If we pay for your repairs under your collision coverage first, the $500 deductible applies. - If Pacific Shore (the other driver’s insurer) accepts full liability and pays the claim directly, then you typically would not pay your collision deductible. - If we pay first and then recover from the other company (a process called **subrogation**), your adjuster will work to get your deductible reimbursed if the other driver is found fully at fault. I can’t decide fault or guarantee who pays what from here — your adjuster, Priya Shah, will review the details and explain exactly how your deductible will work on this claim. 2) “Will I be getting a rental car?” Your policy includes rental reimbursement coverage for: - $40 per day, - for up to 30 days, - starting from the day the claim is opened (that’s today). How that works in practice: - Priya (your adjuster) will help you set up a rental through one of our preferred rental companies, or you can rent on your own and submit receipts up to $40 per day. - If the other driver’s insurance accepts liability quickly, they may also
CUSTOMERAha, that's clear. So if the other driver's insurance accepts liability, I might not have to pay the deductible. And my adjuster will explain it. I do have rental coverage which is $40 per day for up to 30 days. And Priya Shah will help me arrange it. What about my premium? Is it going to go up because of this claim? Also, can you confirm again, my car will be taken to the partner repair shop at ninth and Morrison.
AGENTYou’ve got it exactly right on the deductible and rental. On your new questions: 1) Will your premium go up because of this claim? I’m not able to see or predict premium changes or make any promises about your future rate. A few things generally matter: - Who is found at fault (if the other driver is clearly at fault, that’s usually better for you than if you share fault). - Your prior claims and driving history. - State rules and Northgate’s underwriting guidelines. Your adjuster, Priya Shah, can review how the claim is being rated and let you know what to expect or who in underwriting can answer more specific pricing questions. I don’t want to guess or overpromise on something that affects your bill. 2) Tow destination confirmation Yes — your Honda CR‑V is set to be towed to: - Northgate partner repair shop at 9th and Morrison. And to read back the key items again: - Policy number: N4471902 - Other driver’s license plate: 7KXR2147 - Claim number: NGM-904417 - Tow: Eastside Towing, ETA
AGENTabout 45 minutes, going to our partner shop at 9th and Morrison. While you wait, you’re fine to stay at the cafe as long as you can still see the car when the tow arrives. Do you want Priya to use the phone number you’re calling from today as your main contact, or is there a different number or email you’d like on the claim?