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
#158of 655 stacks
53 / 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.
#393 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.
Not scored by this sweep.
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.
#231 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.
#393 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.
#440 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.
#523 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.
#570 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.
#28 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.
#308 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.
#329 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 | 87% | 3.54 s | — |
| Home services | 90% | 3.51 s | — |
| Insurance | 97% | 3.75 s | — |
| Customer support | 89% | 3.56 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 3.56 s | — |
| Spanish-accented English, city street | 88% | 3.55 s | — |
| Indian English, busy café | 87% | 3.54 s | — |
| Southern US, flustered, crying baby | 93% | 4.06 s | — |
| Fast and interrupting, construction outside | 88% | 3.52 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi Alex, my internet has been down for the past 2 hours. I work from home, so it's been a problem. There's a road crew digging up the street outside, and I'm wondering if That's the cause. I already rebooted the gateway twice and checked every cable. The internet light is blinking orange. Can you check what's happening on your end? My account number is BW888. 83017. Sorry, last digit is 1.
AGENTI’ve got you pulled up under account BW88883017, and I don’t see any area outage at your address, so it’s likely related to your line or the work in the street rather than a known network issue. I just ran a line test from here. Your signal to the gateway looks good, but the gateway had fallen out of registration with our network. I’ve sent a remote reset, and it’s now showing as registered and online on my side. A few things to check on your end now: 1. Look at the gateway lights: the internet light should turn solid (not blinking orange) within about 1–2 minutes. 2. Try loading a page
CUSTOMERAll right.
CUSTOMERThe internet light just went solid white. How long until my devices reconnect?
AGENTGood—that’s what we want. Most devices should reconnect within 1–2 minutes on their own. If they don’t: - Wi‑Fi devices: toggle Wi‑Fi off/on or briefly enable/disable airplane mode, then reconnect to your usual network name. - Wired devices: they should come back automatically; if not, unplug/replug the Ethernet cable once. If you’d like, tell me one device (laptop/phone) and I can walk you through a quick check to confirm you’re fully back online.
CUSTOMERI think my devices will reconnect on their own, thanks. Also, I lost 2 hours of work. Can I get a credit for the downtime?
AGENTI can help with that. I’ve added a service credit for the downtime: - Amount: $10.00. - Account: BW88883017. - It will appear on: your next bill. Sorry for the disruption while you were working from home. If anything drops again or that road work causes more issues, contact me right away and I’ll recheck the line.
CUSTOMERI lost 2 hours of work. Can you make it more than $10?
AGENTI understand why you’re asking, especially if you lost actual work, not just time online. I’ve already applied the $10.00 credit to account BW88883017, and I’m not able to increase that amount further from here. Our credits are based on the length of the service interruption, not on lost wages or productivity, and $10 is the maximum I can issue for a short outage like this. If you want to push for more, the only option would be to contact Billing directly so they can review the account and the timeline, but I want to set expectations that they typically follow the same policy. If the connection acts up again today—especially with that road work still going—tell me right away and I’ll rerun tests and document everything on your account so there’s a clear record.
CUSTOMERGot it. Thanks for your help today, Alex. Goodbye.
AGENTYou’re welcome—glad we got you back online.
AGENTQuick recap before you go: - Your gateway is registered and online now. - A $10.00 credit has been applied to account BW88883017 and will show on your next bill. If anything acts up again, just reach out. Take care and goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, I need to reschedule my dermatology appointment next Wednesday morning. I just got assigned a work shift then, so I can only come after 3 PM. Can we do this quickly? I'm on my lunch break and there's construction outside, so let's keep it brief.
AGENTI can help, and I’ll keep this as brief as possible. To reschedule, I’m required to verify you first. Please reply with: 1. Your full name. 2. Your date of birth (YYYY-MM-DD).
CUSTOMERBrooks, March 17th, 1948. Sorry, no, 1984. March 17th, 1984.
AGENTGot it, thanks. I need your full name plus the date of birth. Please send: - Full name (first and last). - Date of birth as: 1984-03-17
CUSTOMERYeah, I just gave you both. Nate Brooks, March 17th, 1984. Can we move on?
AGENTYou’re verified, thanks, and sorry for the earlier back‑and‑forth. You currently have dermatology with Dr. Okafor next Wednesday at 09:15 at Main Campus, Building B. Next available options with Dr. Okafor
CUSTOMERNo, just need something after 3 PM. What's the soonest you can do?
AGENTSoonest with Dr. Okafor after 3 PM: - Tuesday at 15:45. - Thursday at 16:10. Both are at Main Campus,
CUSTOMERNo, Tuesdays don't work after all. I pick up my daughter then. What about Friday?
AGENTGot it, no Tuesdays after all. Soonest after 3 PM with Dr. Okafor that fits what you’ve said is: - Thursday at 4:10 PM. - Friday has only 11:30 AM, nothing after 3 PM. Do you want me to move your appointment from next Wednesday at 9:15 AM
CUSTOMERRight.
AGENTJust to confirm:
CUSTOMERThursday at 4:10 PM.
CUSTOMERRight, keep going. I'm in a hurry.
AGENTYou’re all set. I’ve moved your dermatology visit with Dr. Okafor from next Wednesday at 9:15
CUSTOMERUh-huh.
CUSTOMEROkay.
CUSTOMERIs there a fee for changing the appointment?
AGENTNo fee for this change. Our policy: changes more than 24 hours before the appointment are free; within 24 hours
CUSTOMERYep, got it. Where should I park?
AGENTFree patient parking is in Lot C, entrance on River Road.
CUSTOMERDoes Dr. Okafor accept Aetna insurance?
AGENTI don’t have access to provider–insurance panel details, so I can’t safely say yes or no. Fastest way to confirm: - Call the clinic front desk so they can check Dr. Okafor’s current Aetna status in the system, and. - (Optionally) confirm with Aetna by giving them Dr. Okafor’s name and the clinic
CUSTOMERI'll check with the front desk. Can you read back the new time and the confirmation code for me?
AGENTYour new appointment is Thursday at
CUSTOMERThursday at 4:10 PM, right? And what's the confirmation code?
AGENTYes, Thursday at 4:10 PM. Your confirmation code is RVB-3M8P2.
CUSTOMERThat's all I needed. Thanks. Goodbye.
AGENTYou’re welcome—Thursday
AGENTat 4:10 PM, confirmation code RVB-3M8P2. Goodbye, and take care.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERYes, hello, I have a burst pipe under my kitchen sink. Water is spreading across the floor and it's heading toward a power strip. I need someone to come quickly, please.
AGENTThanks for telling me right away—let’s get you safe first. 1. Stay away from that power strip and any outlets the water is reaching. Do not touch the strip or anything plugged into
CUSTOMERUnderstood. I'm staying clear of the power strip and not touching anything plugged in. What should I do next?
AGENTGood, stay clear of that area. Next steps, in order: 1. Kill the power near the water: - Go to your main electrical panel. - Flip off the breaker that controls the kitchen. - If you’re not sure which one that is, and it’s safe to reach the panel without walking through water, you can switch off the main breaker at the top to shut power to the whole house. - If you’d have to walk through water to reach the panel, do not do it—stay where you are and tell me. 2. Shut off the water
CUSTOMEROkay, I'm shutting off the water now. The water has stopped. What should I do next?
AGENTGood job getting the water stopped—that’s the most important part. Next, a couple quick safety and damage‑control steps, then I’ll get a technician booked: 1. Power near the area.
CUSTOMEROkay.
CUSTOMERRight, I have already stayed away from the power strip and shut off the water. Is there anything else I should do now? And could you please let me know how much the visit will cost?
AGENTA few quick things you can do now, then I’ll get you scheduled: 1. Safety / cleanup. - If you can reach it without going near any water, unplug that power strip from the wall. If you’d have to step in water to get to it, leave it alone until a pro is there. - Put down towels or a mop to soak up as much water as you safely can, especially near cabinets and baseboards, to limit swelling and mold. - Move anything that can be damaged by water (rugs, boxes, small appliances) out of the wet area.
CUSTOMERGot it. I will put down towels and move anything that could be damaged, but I will not go near the power strip if there is water. Can you let me know how much the technician visit will cost, and can anyone come before 2 PM?
AGENTWe can get someone out on an emergency visit today between 2:00 PM and 4:00 PM—the earliest emergency window available. There’s nothing open before 2 PM, unfortunately. For pricing: - Emergency call‑out today: $149. - If you’re a Copperline Care member: $99 emergency call‑out. Next, I’ll get this booked for the 2:00–4:00 PM emergency window. I just need to grab a few details: 1. Your name. 2. The service address (including unit number if there is one, and any gate code or access instructions). 3. Best callback phone number. 4. Are you a Copperline Care member, if you know?
CUSTOMERNo, I am not a Copperline Care member. My name is Arjun Mehta. The service address is 1480 Larkspur Avenue, Unit 4D. I moved from from 4B to 4D last month. The building gate code is #2719. My callback number is 503-555-0139. No, 0193.
AGENTThanks, Arjun. I’ve got everything set up. First, just to confirm what you’re doing now: - Stay away from the power strip and any outlets near the water. - Keep soaking up water with towels and move items out of the wet area as you can do so safely. - Don’t turn the water back on to that sink until our plumber has been out. Now, for your visit details: - You are not a Copperline Care member (we’ll go with standard pricing). - Visit type: Emergency plumbing visit. - Fee: $149 emergency call‑out (card or check on completion). - Arrival window: Today, 2:00 PM to 4:00 PM. - The technician will text your callback number about 30 minutes before arrival. Service request details: - Name:
CUSTOMERYes, that's correct. My name is Arjun Mehta. My name is Arjun Mehta.
AGENTThanks, Arjun. I’ve got your name correct: Arjun Mehta. Let me read everything back so you know what’s on the ticket: - Name: Arjun Mehta. - Service address: 1480 Larkspur Avenue, Unit 4D. - Gate/access: Building gate code #2719. - Callback number: 503-555-0193. - Issue: Burst pipe under kitchen sink; water spread across floor toward a power strip. Water main is shut off and you’re staying clear of the power strip. - Urgency: Emergency. - Arrival window: Today, 2:00 PM to 4:00 PM. - Visit fee: $149 emergency call‑out (you’re not listed as a Copperline Care member). -
CUSTOMERYes, that's all correct. Could you tell me who will be coming and how I will know they are on the way? Also, can you give me the ticket number for this visit, please?
AGENTYou’re all set, Arjun. Here are the details you asked for: - Technician: One of our emergency plumbers will be dispatched for your window today between 2:00 PM and 4:00 PM. - How you’ll know they’re on the way: You’ll get a text to 503-555-0193 about 30 minutes before arrival with their name and ETA. Your service request / ticket number is: CPL-58210. Reading back your key details once more so you have them handy: - Name: Arjun Mehta. - Address: 1480 Larkspur Avenue, Unit 4D. - Gate code: #2719. - Callback: 503-555-0193. - Ticket: CPL-58210. -
CUSTOMER210. Yes, that's all correct. Thank you for your help. Goodbye.
AGENTYou’re welcome, Arjun.
AGENTI’ve got you set for today, ticket CPL-58210. If anything changes before the plumber arrives—like the power strip getting submerged or the leak starting again—keep clear of the area and call us right away. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I'm at home right now. I got the baby here. She's crying a bit in the background. Sorry about that. I'm standing by my car, but nobody's hurt or anything. Is that okay?
AGENTThat’s absolutely okay, and no need to apologize about the baby—I understand. Just to double‑check: you mentioned nobody’s hurt. Can you confirm that no one at the scene was injured and no one is in any danger right now? If anyone is hurt or starts to feel worse, please call 911 right away before we do anything else. Next, I’ll get your policy pulled up so we can open a claim. Can you give me: 1. Your auto policy number, and. 2. The policyholder’s last name?
CUSTOMERSure, I got the policy number right here. It's NG4471903. Oh wait, sorry, last one is 2. So NG4471903. 447-1902. Is that okay? And it's Carter for the last name. Is that gonna work?
AGENTYes, that works, thank you. I have policy NG4471902 under the last name Carter, covering a 2021 Honda CR‑V. I’ll start a claim for you. I need to ask a few questions about what happened: 1. When did the accident happen? 2. Where did it happen? 3. Can you tell me, in your own words, what happened? 4. Do you have the other driver’s: - Name. - Insurance company. - License plate number. 5. Did the police come to the scene, and is there a report number, if you have it? Also, is your Honda drivable and safe to drive, or is it badly damaged or not starting? That helps me know if we should set up a tow.
CUSTOMERYeah, so it happened about 20 minutes ago. I was stopped at a red light at Southeast 5th Avenue and Alder Street. The other car hit the back of my car right in the bumper. My The rear wheel's rubbing now and the bumper's crushed, so I can't drive it. Nobody's hurt though. The other driver's name is Kevin Lund. He's insured with Pacific Shore. Plate is 7KX, like X-ray, R214. Police didn't come, and there's no report number. So again, it's not drivable. Bumper's crushed, wheels rubbing, can't get it home. Sorry, is that gonna be a problem?
AGENTIt’s not a problem—we’ll take care of it. I’ve opened a claim for you with this information: - Policy number: NG4471902. - Claim number: NGM-904417. The other driver’s plate I have is: 7KXR214. Please listen to that: 7 – K – X – R – 2 – 1 – 4. If that’s not right, tell me the correct plate and I’ll fix it. Since the car isn’t drivable, I’ve arranged a tow: - Tow company: Eastside Towing. - ETA: about 45 minutes. - They’ll take it to a Northgate partner repair shop at 9th and Morrison. A few quick follow‑ups: 1. Are you still at Southeast 5th and Alder with the vehicle, or did you get it home already? 2. What’s the best
CUSTOMERSorry, I'm still at Southeast 5th and Alder with the car. Just wanted to make sure that's okay. What else do you need?
AGENTThat’s okay—you’re fine to stay there and wait for the tow. Let me just confirm a couple of details and then I’ll tell you what to expect next. Here’s what I have on file: - Policy number: NG4471902 - Claim number: NGM-904417 - Location of the car: Southeast 5th Avenue and Alder Street - Other driver’s plate: 7KXR214 Please correct me if any of that is wrong. I also need: 1. A good phone number for you, so the tow driver and your adjuster can reach you. 2. The best email address for claim documents. 3. The name of the person who was driving (you, or someone else on the policy). 4. The city and state where Southeast 5th and Alder is. Based on your policy, I can also share this with you now: - Collision deductible: $500 - Rental coverage: $40 per day, up to 30 days, starting today (the day the claim is opened) - Towing: Covered up to 25 miles Once I have your contact info, I’ll summarize everything and go over what will happen after the tow.
CUSTOMERSorry, I'm a little flustered here. So my phone number is 320-664-2024. Is that okay? For email, it's wade.carter@gmail.com.
CUSTOMERThat's A-D-E.
CUSTOMERWade Carter. 5th and Alder is in Portland, Oregon. Sorry,
AGENTThanks, Wade, that’s all okay—and you don’t need to apologize. Let me read everything back clearly so you don’t have to think too hard about it right now. Here’s what I have: - Policy number: NG4471902 - Claim number: NGM-904417 - Your name: Wade Carter (W-A-D-E) - Phone number: 320-664-2024 - Email: wade.carter@gmail.com - Accident location: Southeast 5th Avenue and Alder Street, Portland, Oregon - Other driver’s plate: 7KXR214 If any of that sounds off, tell me and I’ll fix it. A tow from Eastside Towing is on the way to Southeast 5th and Alder, with an ETA of about 45 minutes, going to our partner shop at 9th and Morrison. While you’re waiting: - If it’s safe, keep your hazard lights on. - Stay in the car with doors locked if you’re near traffic, or move to a safe spot nearby with the baby. Coverage details on your policy for this claim: - Collision deductible: $500 - Rental car: $40 per day, up to 30 days, starting today - Towing: Covered up to 25 miles Your assigned adjuster is Priya Shah. You’ll hear from her within one business day to go over repairs, rental setup, and next steps. Do you want me to go over what to expect with the repair shop and rental, or are you okay for now and just want to wait for the tow?
CUSTOMERSorry, quick question. So about the deductible, since he hit me, I shouldn't have to pay that, right? And, uh, is my premium gonna go up because of this? I'd like to know what happens next with the shop and the Rental, if you could walk me through it. I just want to make sure I'm not missing anything.
AGENTI’ll walk you through each part step by step. First, about the deductible and your premium: 1. Deductible (the $500): - Your policy has a $500 collision deductible. - Whether you actually end up paying that depends on fault and recovery: - If the other driver is found at fault and their insurer (Pacific Shore) pays for your damage directly, you typically would not pay your collision deductible
AGENTthrough us. - If we repair your car under your collision coverage first (which is common so you’re not waiting), you may see the $500 applied up front. - If we later recover the money from Pacific Shore, your deductible may be reimbursed. - Your adjuster, Priya Shah, will review the facts and confirm exactly how this will work in your case. I can’t decide fault or guarantee reimbursement myself; that comes from the claims investigation. 2. Will your premium go up? - I don’t have access to rating or pricing decisions, so I can’t say if or how your premium might change. - Generally, the company looks at things like who was at fault, your prior driving/claim history, and state rules. - Your adjuster can explain how the claim will be coded (for example, “not at fault rear-end”) and how that usually affects your policy, but any actual rate change would be handled at renewal by underwriting, not during this call. Now, what happens next with the shop and the rental: 3. The repair shop: - Your car is being towed to a Northgate partner repair shop at 9th and Morrison in Portland. - Once it arrives, the typical steps are: 1) They check in the vehicle and do an initial assessment. 2) An estimate is written—either by the shop, our appraiser, or both. 3) The estimate is sent to Northgate for approval. 4) Once approved, repairs start and they’ll update you on timing and any parts delays. - Using a partner shop usually means: - Streamlined communication with your adjuster. - Any guarantee/warranty on the repair work provided through our network (your adjuster can give the exact terms). 4. Rental car process: - Your policy includes rental coverage: $40 per day, up to 30 days, starting today (the day we opened the claim). - How it usually works: - After Priya (your adjuster) connects with you, she’ll either: - Set up a direct-bill rental with one of our partner rental companies, or. - Authorize you to rent and then submit receipts (up to $40/day), depending on what’s available in your area. - If the car is confirmed not drivable (which it sounds like it is), they’ll typically start the rental as soon as possible, not waiting for repairs to be finished. - If Pacific Shore ends up accepting full liability quickly, the rental might be switched to their policy; your adjuster will guide that so you’re not double-paying. 5. What you should do next (once the tow arrives): - Make sure you remove: - Car seat and baby items. - Garage door opener. - Any valuables, registration, and insurance card. - Confirm with the tow driver: - Destination: Northgate partner repair shop at 9th and Morrison. - Keep any paperwork or receipt they give you. 6. In the next day or so: - Your adjuster, Priya Shah, will contact you using: - Phone: 320-664-2024. - Email: wade.carter@gmail.com. - She’ll: - Confirm the facts of the accident. - Go over fault and how that affects your deductible. - Coordinate with the shop. - Help set up or confirm your rental arrangements. - Answer more detailed coverage/“what if” questions. To recap the key points for what you asked: - You do have a $500 collision deductible on this claim, but if the other driver is found fully at fault and we recover from their insurer, that deductible may be reimbursed. Your adjuster will confirm how that plays out. - I can’t say for sure whether your premium will go up; that depends on fault, company rating rules, and your overall history. - Your car is going to a partner shop, they’ll estimate and repair it, and you have rental coverage of $40/day up to 30 days starting today. Is there anything specific you’re most worried about—time without a car, out-of-pocket costs, or something else—so I can focus on that while you’re waiting for the tow?