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
#164of 655 stacks
52 / 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.
#411 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.
#385 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.
#311 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.
#468 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.
#503 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.
#421 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.
#535 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.
#655 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.
#171 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.
#6 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#225 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 85% | 3.08 s | — |
| Home services | 87% | 3.42 s | — |
| Insurance | 92% | 3.50 s | — |
| Customer support | 98% | 3.46 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 3.27 s | — |
| Spanish-accented English, city street | 76% | 3.17 s | — |
| Indian English, busy café | 98% | 3.20 s | — |
| Southern US, flustered, crying baby | 94% | 4.28 s | — |
| Fast and interrupting, construction outside | 91% | 3.21 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi Alex, I'm calling from a cafe because my home internet has been down for 2 hours now. I work from home, so it's been a real problem. There is a road crew digging up the street outside my place, so I'm wondering if that might be the cause. I already rebooted the gateway twice and checked all the cables. The internet light is blinking orange. Can you check what's happening on your end? My account number is BW883017. Sorry, last digit is 1.
AGENTThanks for the details, and I’m glad you called from somewhere with a connection. I’ve pulled up your account as BW883011 and checked your line—there’s no area outage showing for your address. I ran a test and your gateway initially showed as not registered, so I’ve just sent a remote reset from our side. It now shows as registered and online, and everything looks healthy on the line. Here’s what to expect:
- Your gateway at home should be finishing its restart now. - Wi‑Fi and devices may take up to 2 minutes to fully reconnect. When you get back home, you should see
- Powersolid
- Internet lightsolid (not blinking orange)
- Wi‑Fi lightson and stable
If you get home and
- The internet light is still blinking orange,
CUSTOMEROkay, Alex, actually I just checked and the internet light on my gateway went solid white. How long until my devices reconnect and I can get back online? Also, Also, since I lost 2 hours of work, can you apply a credit for the downtime?
AGENTSolid white is exactly what we want—that means the connection is up again. 1) Time for devices to reconnect - Most devices should reconnect within 1–2 minutes on their own. - If anything doesn’t: - Toggle Wi‑Fi off/on on that device, or - Forget and rejoin your Wi‑Fi network (entering the password again). 2) Credit for the downtime I’ve applied a $10.00 credit on account BW883011 for about 2 hours of service interruption. You’ll see it on your next bill. If you’re still at the café, by the time you get home everything should already be online. If any device can’t reach websites once you’re there, tell me which device
CUSTOMERAll right, thank you for the instructions, Alex. About the credit, $10 is helpful, but I lost 2 hours of work. Can you make it more than that?
AGENTI get why you’re asking, especially if it cost you real work time. On my side, I’m limited to a standard interruption credit, and I’ve already applied the maximum I’m allowed to give directly, which is the $10.00 you’ll see on your next bill for account BW883011. I can’t increase that amount myself. If you want to push for more, the next step is to contact Customer Care/billing (not tech support) and explain the impact on your work—they have more flexibility than I do. I can summarize what happened so you can reference it: about 2 hours of downtime, no area outage, line good, gateway needed a remote reset and is now online.
CUSTOMERAha, that's clear, Alex. I'll reach out to Customer Care/Billing then. Thanks for your help and for summarizing the issue. Goodbye.
AGENTYou’re welcome—glad
AGENTwe got you back online and at least a credit started. Quick recap for Billing when you call: - Account: BW883011 - Issue: ~2 hours of downtime, no area outage - Cause/resolution: gateway not registered, fixed by remote reset; now online - Credit already applied: $10.00 on next bill Take care, and goodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, uh, I need to reschedule my dermatology appointment. It was supposed to be next Wednesday morning, but I have to work then. My name is—
AGENTNo problem, I can help with that.
CUSTOMERThe CRM is— can you help me move it?
AGENTI can help you reschedule, yes. To get started, I
CUSTOMERSorry, I didn't catch that. Could you repeat what you—
AGENTI was saying I can help you reschedule your appointment.
CUSTOMEROkay, go ahead. I can only come after 3 PM, so
AGENTI can do that. First I need
CUSTOMERThat's right. So my appointment was next Wednesday morning.
AGENTI
CUSTOMERSure, go ahead. What do you need?
AGENTI just need to verify your record before
CUSTOMERSorry, I didn't get that. Could you say that again?
AGENTI just need to verify your record
CUSTOMEROkay, that's fine. What do you need to verify?
AGENTI need your: 1) Full name
CUSTOMERAll right, what do you need from me? My date of birth?
AGENTYes, please—I
CUSTOMERSure, my full name is Lucia Ramirez.
AGENTThanks, Lucia. I also
CUSTOMEROkay, my date of birth is March 7th.
AGENTThanks, Lucia. I also need the year of your birth to look you up. Could
CUSTOMEROh, actually it's Lucia Ramirez, not Lucila. So what else do you need?
AGENTThank you for correcting that—Lucia Ramirez. To look you up, I still need your full date of birth, including the year. You’ve given me March
CUSTOMERSorry, I misspoke earlier. It's March 7th.
AGENT7th;
AGENTThanks, I have your birthday as March 7th. I still need the year you were born so I can look you up and find your dermatology appointment. Could
CUSTOMERRight, sorry, no, it's March 17th, 1980.
AGENTThanks, Ms. Ramirez. I’ve verified your record with date of birth March 17th, 1980. I see your dermatology
CUSTOMERNo, it's March 17th, not March 7th. My full date of birth is March 17th, 1980.
AGENTThank you for the correction—your date of birth
CUSTOMERUh, just to confirm, it's 1984, March 17th, 1984.
AGENTThank you for clarifying—that’s March 17th, 1984.
CUSTOMERYes, that's right. So about rescheduling, do you have any openings after 3 PM?
AGENTI’ve got you as Lucia Ramirez, date of birth March 17th, 1984,
CUSTOMERNo, it's March 17th, 1984. Just wanted to make sure it's correct.
AGENTGot it: your full date of birth is March 17th, 1984. For rescheduling
CUSTOMERIt's Lucia Ramirez and March 17th.
AGENTThank you, I have you as Lucia Ramirez, date of birth March 17th, 1984. You mentioned you can only come after
CUSTOMERRight, I can only come after 3 PM, so do you have any slots?
AGENTI have you as Lucia Ramirez, date of birth March 17th, 1984. For your dermatologist,
CUSTOMERYes, after 3 PM. I can't do mornings or early afternoons.
AGENTThanks for your patience, Ms. Ramirez. I have you as Lucia Ramirez, date of birth March 17th,
CUSTOMERYes, that's correct. For my dermatologist appointment, what times are available?
AGENTI have you as Lucia Ramirez, date of birth March 17th, 1984.
CUSTOMERNo, it's March 17th, 1984. Just making sure you have the right information. So what time?
AGENTI have you as Lucia Ramirez, date of birth
CUSTOMEROkay, that's right. So what times are open after 3 PM for rescheduling?
AGENTHere’s what I can offer you after 3 PM with your dermatologist, Dr. Okafor:
- Tuesday
CUSTOMERYes, that's correct. Lucia Ramirez, March 17th, 1984. What availability
AGENTI have you as Lucia Ramirez, date of birth March 17th, 1984.
CUSTOMERAll right, right. What times are available after 3 PM?
AGENTFor Dr. Okafor, the first available options after 3 PM are:
- Tuesday
CUSTOMERJust to clarify, it's March 17th, 1984. What slots are open at
AGENTThanks for confirming: Lucia Ramirez, date of birth March 17th, 1984.
CUSTOMEROkay, go ahead. What are the times?
AGENTI have you as Lucia Ramirez, date of birth March 17th, 1984. For your dermatologist, Dr. Okafor,
CUSTOMERSorry, my name is Lucia Ramirez, not Lucifer.
AGENTThank you for correcting me—your name is Lucia Ramirez, and your date of birth is March 17th, 1984.
CUSTOMERYes, that's right. So what times are available after 3 PM?
AGENTThanks,
CUSTOMERIt's Lucia Ramirez and March 17th, 1984. So could you let me know the available— so what times are open after 3 PM for rescheduling?
AGENTThanks, Ms. Ramirez. I have you as Lucia Ramirez, date of birth March 17th,
CUSTOMERHello?
AGENTI’m here, Ms. Ramirez. Thanks for your patience. For your dermatologist, Dr. Okafor, the current openings I see that are after 3
CUSTOMERYes, that's correct.
AGENTThanks for hanging in there, Ms. Ramirez. I have you as Lucia Ramirez, date of birth March 17th, 1984. For your dermatology
CUSTOMERAll right, could you tell me what times are available
AGENTI have you as Lucia Ramirez, date of birth March 17th, 1984. For rescheduling your dermatology visit
CUSTOMERYes, that's right. So what times can you offer after—
AGENTThanks for sticking with this, Ms. Ramirez. I have you as Lucia Ramirez, date of birth March 17th, 1984.
CUSTOMERYes, that's correct. What times are available after 3 PM?
AGENTThanks for your patience, Ms. Ramirez. I have you as Lucia Ramirez, date of birth March 17th,
CUSTOMERJust to confirm, it's March 17th, 1984. What times are open?
AGENTI have you as Lucia Ramirez, date of birth March 17th, 1984.
CUSTOMERThat's right, March 17th, 1984. So what times are available after 3 PM?
AGENTHere are the current options I can offer you
CUSTOMERIt's Lucia Ramirez and March 17th, 1984. Can you tell me what appointments are open after 3 PM?
AGENTThanks for hanging in with all the repeats,
CUSTOMEROkay, what are the options after 3 PM?
AGENTHere are the options I can offer you after 3 PM with your dermatologist, Dr. Okafor:
-
CUSTOMERNo problem. So what times are available? Available after
AGENTThanks for your patience, Ms. Ramirez. I have you as Lucia Ramirez, date
CUSTOMERAll right, what time do you have available after 3 PM?
AGENTI can see a few options after 3 PM with your dermatologist, Dr. Okafor. The first available late-day
CUSTOMERYes, that's right. So what time to open after 3 PM?
AGENTLucia, thanks for sticking with this. For your dermatologist, Dr. Okafor, the openings
CUSTOMEROkay, could you tell me the time?
AGENTThanks for hanging in there, Ms. Ramirez. For your dermatologist, Dr. Okafor, the appointments I can offer that start after 3 PM
CUSTOMERIt's Lucia Ramirez. But yes, go ahead.
AGENTThanks, Ms. Ramirez. For your dermatologist, Dr. Okafor, the appointment times I can offer that start after 3 PM are:
-
CUSTOMERAll right, what times do you have available?
AGENTThanks for your patience, Ms. Ramirez. I have you as Lucia Ramirez, date of birth March 17th, 1984.
CUSTOMEROkay, I'm listening. What are the available times?
AGENTHere are the times I can offer you after 3 PM with your dermatologist,
CUSTOMERYes, that's correct. So what are the options after 3 PM for rescheduling?
AGENTThanks for hanging in with all the repeats, Ms. Ramirez. For your dermatologist,
CUSTOMERAll right, what time do you have available?
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, uh, I have an emergency. A pipe under my kitchen sink has burst and water is spreading across the floor toward a power strip. I haven't shut the water off yet. Can you help?
AGENTYes, I can help. First, let’s get you safe and stop the damage:
1. Stay away from the power strip. - Do not touch it or any plugs if there’s water nearby. - Keep kids and pets out of the area. 2. Shut off the water right away- Look under the kitchen sink for two small shutoff valves (one for hot, one for cold) on the pipes going up to the faucet. - Turn each valve clockwise until it stops. - If you can’t find or turn those valves,
CUSTOMEROkay, I see them. I'm turning both valves clockwise now. Yeah, the water has stopped. Oh, what do I do next?
AGENTGood—that’s a big first step. Next, let’s keep things safe and limit damage:
1. Power strip and electricity - Do not touch the power strip or plugs while the floor is wet. - If you can safely avoid the water, go to your breaker panel and flip off the breaker for the kitchen or the outlets in that area. - If you’re not sure which breaker, and you can reach the panel safely, you can shut off the main breaker until we arrive. 2. Water cleanup - Start soaking up water with towels, a mop, or a wet/dry shop vac if you have one. - Try to keep water from spreading into other rooms or under appliances. I want to get a plumber out to you on an emergency basis. Let me grab a few details so I can open a service request and check the earliest arrival window
1.
CUSTOMEROkay, I won't touch the power strip. Ooh, I'll head to the breaker panel and shut off the kitchen breaker now, and I'll start cleaning up the water. My address is 1480 Larkspur Avenue. I just moved I moved from unit 4B to 4D last month, so it's unit 4D now. The building gate code is #2719. My phone number is No, 0193. Can you tell me how much the visit will cost before you send someone? And is there any way someone can come before 2?
AGENTYou’re doing the right things so far—shutting off the sink valves and the kitchen breaker and mopping up is exactly what you should be doing. I’ve found you in our system at 1480 Larkspur Avenue, previously unit 4B. I’ll update this to unit 4D for this visit, and I’ve noted the gate code #2719. On cost and timing:
- You’re a Copperline Care member, so the emergency callout fee for today is $99. - That’s the fee for the plumber to come out, diagnose, and provide an upfront estimate for the repair. - Payment is by card or check on completion. Availability
- The earliest emergency window I can offer today is 200 PM to 4:00 PM. - There’s nothing available before 2 PM showing
CUSTOMEROkay, thanks for updating that to unit 4D. Just to confirm, the gate code is #2719, not 2799. So, um, the callout fee The fee is $99, right? Is there any chance someone could come before 2 PM? If not, I'll take the 2 to 4 PM window. Also, who will be coming and how will I know they're on the way? And can you tell me the ticket number, please?
AGENTYou’re all
CUSTOMERGo ahead. So I just need to know who's coming and how I'll know they're on the way and the ticket number, please.
AGENTYou’re all set; I’ve got everything booked. - The emergency callout fee for you as a Copperline Care member is $99. - The earliest emergency window we have is still today, 2:00 PM to 4:00
CUSTOMERRight, I'll take the 2 o'clock PM to 4 o'clock PM window. Who will be coming and how will I know when they're on the way? And can you give me the ticket number for this visit?
AGENTYou’re booked for today, 2:00 PM to 4:00 PM. A couple of quick clarifications and answers:
1) Who’s coming Our system has assigned
CUSTOMERHello?
AGENTYou’re all set—I’ve got you booked. Here are the details:
- Visit windowToday, 2:00 PM to 4:00 PM (emergency visit) - Service address: 1480 Larkspur Avenue, Unit 4D - Gate code: #2719 - Callback number: the number you’re calling from ending in 0193 - Ticket number: CPL-58210
On your questions
- Who will be coming? A licensed Copperline plumber will be dispatched for this emergency visit. I don’t have a specific name to share from the system, but it will be one of our on‑call emergency techs. - How you’ll know they’re on the wayYou’ll get a text message to your callback number about 30 minutes before arrival letting you know the technician is en route. While you’re waiting:
- Keep the kitchen breaker off and stay away from that power strip until everything is dry and the tech has had a look. - Keep soaking up any remaining water to prevent damage. Let me quickly read back the key info to be sure nothing’s off1480 Larkspur Avenue, Unit 4D, gate code #2719, callback ending in 0193, ticket CPL-58210, arrival window today 2:00–4:00
CUSTOMERThat's right, except the gate code is #2719. And thank you for the ticket number, CPL-58210. I'll wait for the text about 30 minutes before arrival. Thanks for your help. Goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I'm at home now. So I got a big crying background. Nobody's hurt, but a little stirred. Is that all right?
AGENTI’m glad to hear nobody’s hurt, and I’m sorry you all got shaken up—that’s completely understandable. Since everyone’s safe and there are no injuries, we can go ahead and set up your claim. First, I’ll need to pull up your policy. Could you please give me:
1. Your auto policy number, and 2. The policyholder’s last name as it appears on the policy?
CUSTOMERSure. The policy number is ND4. Four seven one nine zero three. No, sorry. Last one is two. Can you tell me if it's the right one? The last name is Carter. Is that be all right?
AGENTThanks, I’ve got your policy pulled up—Northgate Mutual auto policy ND44719032 under the name Carter. Now I need to get some details about what happened so we can open the claim. 1. When did the accident happen? 2. Where did it happen? 3. Can you tell me what happened, in your own words? 4. Do you know 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 CR‑V drivable and safe to drive, or is it damaged to the point you’re not comfortable driving it?
CUSTOMEROh, um, I think policy number you sound a little off. My Aunt G. Subject for me. Just want to make sure nothing's messed up. So, up two minutes ago, I stopped at red light, Southeast Avenue and Archer Street. Another car hit the back of my car. My bumper crushed the rear wheel, so I can't drive at all. No, God hurt. Goodness. The driver's name is Kevin Lund. Insurance is Pacificor. License plate is 7KS, like Trey, R214. I put it in code. Car's Honda, and I can't drive now. Is that enough for you, or do you need anything more?
AGENTThanks for all that detail—that’s very helpful, and I’m glad again that no one’s hurt. Let me first read back the key info to make sure I’ve got it right:
- Policy numberND44719032
- Location of accidentSoutheast Avenue and Archer Street
- What happenedYou were stopped at a red light, and another car hit you from behind, crushing your bumper into the rear wheel so the car can’t be driven.
CUSTOMERSorry, I think my policy number is ND447902. Please tell me that's the right one. Yeah, that's location: 85th Avenue and Alders. I was stopped at red light and hit me behind. Bumper's crushed, rear wheel rubs, I can't drive it. I'll come through on your end, I just want to make sure nothing gets lost.
AGENTYou did the right thing calling in, and nothing is getting lost—we’ve just updated everything with the correct details. Let me read it back to you carefully. Policy and accident details - Policy number: ND447902 - Policyholder last name: Carter - Vehicle: 2021 Honda CR‑V - Accident location: 85th Avenue and Alders - What happened: You were stopped at a red light when another vehicle hit you from behind. Your bumper is crushed, the rear wheel is rubbing, and you can’t safely drive the car. - Injuries: None reported - Other driver: Kevin Lund, insured with Pacificor - Other vehicle license plate: 7KST R214 - Police: No police responded Is all of that correct, including the policy number ND447902 and the license plate 7KST R214? Now, I’ve opened a claim for you: - Claim number: NGM-904417 - Assigned adjuster: Priya Shah - Contact: You’ll hear from Priya within one business day about next steps, repairs, and coverage. About your car and towing Since you can’t drive the car: - I’ve arranged a tow through Eastside Towing. - They’re headed to 85th Avenue and Alders. - Estimated arrival: about 45 minutes. - Destination: Our Northgate partner repair shop at 9th and Morrison. If you’d like the car towed somewhere else (like a different shop or your home), tell me now and I can update that. Do you want me to keep the tow going to the partner shop at 9th and Morrison, or would you prefer a different destination?
CUSTOMERUh, hey, I'm a little anxious about the details, right? My policy number ends in 1902. Please tell me that you have it all. Last name: Carter. The driver's plate is 7KSLAKEYRAYR214. Is that all matching up? I just wanna make sure it's correct. So, about tow, I really have a place to send it, so partners but 9 more is fine. Is that okay? And, um, how do I pay for all this? Am I gonna owe a deductible or anything?
AGENTYou’re doing exactly the right thing by double‑checking; I’ll go slowly and read everything back so you know it’s right. First, your policy and accident details as we have them now:
- Policy numberND4471902 - Policyholder last name: Carter - Vehicle: 2021 Honda CR‑V - Accident location: 85th Avenue and Alders - What happened: You were stopped at a red light and were hit from behind. The bumper is crushed, the rear wheel is rubbing, and the car can’t be driven safely. - Injuries: None reported - Other driver: Kevin Lund, insured with Pacificor - Other vehicle license plate: 7KSLAKEYRAYR214 (that’s what I have from what you just told me) Please listen to this part: - Policy number I have now is ND4471902. - License plate
CUSTOMERThank you for checking, but really make sure policy number is ND47902. Are you sure that's the one then? I just wanna be certain nothing gets fought. And the other is 7KXSR. 214. Is that cringe enough now? Sorry, I know I keep repeating. I'm just nervous about this. Could you tell me how y'all have a day? And, uh, do I have a car? Oh boy, is my premium gonna go up because of this?
AGENTYou’re not overdoing it—being nervous after a crash is completely normal, and it’s good you’re making sure the details are right. I’ll lock in exactly what you just gave me. Here’s what we have now, with your latest corrections: - Policy number: ND47902 - Last name: Carter - Vehicle: 2021 Honda CR‑V - Accident location: 85th Avenue and Alders - What happened: You were stopped at a red light and were rear‑ended. The bumper is crushed, the rear wheel is rubbing, and the car cannot be driven safely. - Other
AGENTdriver: Kevin Lund, insured with Pacificor - Other vehicle license plate: 7KXSR214 - Injuries: None reported - Police: No police responded Claim information - Your claim number: NGM-904417 - Assigned adjuster: Priya Shah - You’ll hear from Priya within one business day about repairs, next steps, and anything else you’re worried about. Tow destination You said sending the car to the Northgate partner shop at 9th and Morrison is fine—that’s what we’ll use as the destination. Coverage / “How do I pay for all this?” I’ve checked your coverage for policy ND47902: - Collision deductible: $500 — this is the amount you’re responsible for if your collision coverage is used for repairs. - Rental coverage: Up to $40 per day, for up to 30 days, starting from the day the claim is opened, if your car is not drivable or is in the shop for covered repairs. - Towing: Covered up to 25 miles per tow under your roadside/towing coverage. What this usually means for you - At the repair shop: If repairs are covered under collision, you’d generally pay your $500 deductible; we work with the shop for the rest, up to the amount of the covered loss. - For the tow: As long as the tow is within 25 miles, it should be covered under your towing coverage (your adjuster will confirm the final billing). - For a rental car: You can get a rental up to $40 per day, up to 30 days, while your car is being repaired or if it’s a total loss, subject to the adjuster’s direction. About your premium Possibly going up is something people worry about a lot. Whether your premium will change depends on several factors (fault determination, your state’s rules, prior history, etc.). I can’t say for sure if it will go up or by how much. Your adjuster, Priya, will review fault and how the claim is handled, and your rating department factors that in at renewal. You won’t see any immediate premium change today just because you reported the claim. To make sure we’re fully aligned, can you confirm these two details one more time: 1) Policy number: ND47902 2) License plate for the other driver: 7KXSR214 If both of those are correct, I’ll note in your file that you personally verified them so you don’t have to keep worrying about it.