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
#172of 655 stacks
42 / 100
Leader AssemblyAI Universal-3.5 Pro + OpenAI GPT-6.1 Sol + ElevenLabs Turbo v2.5, 70 / 100
Where it ranks
Its models
Task completion
Task completion
How much of the caller’s task the agent completed: the share of the scenario’s checks a judge model found met in the transcript, averaged over calls. Before v1.3, the share of calls judged 4 or better out of 5.
#302 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.
#372 of 662 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 662 on the board · best 0.0 per call
Understanding & effort
Caller effort
How hard the caller had to work: repeating themselves, correcting, re-explaining. 1 = effortless.
Not scored by this sweep.
Repeated-info loops
Times per call the agent re-asked for something the caller had already given.
#180 of 494 on the board · best 0.0 per call
Speech-to-Text
Semantic word error rate
The caller's words the agent's transcriber got wrong in a way that changes the meaning, as a judge reads each difference.
#629 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.
#628 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.
#232 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.
#296 of 648 on the board · best 1.9%
Voice
Human-likeness
How human the agent's voice sounds, scored by an audio model on intonation, rhythm and expressiveness. 5 = hard to tell from a person.
#158 of 660 on the board · best 4.3 / 5
Voice consistency
Share of calls where every line the agent spoke was the same speaker, with no change of speaker, gender or language voice partway. It checks who is speaking, not how they sound.
Not scored by this sweep.
#1 of 660 on the board · best 100%
Latency
Response time
The silence between the caller finishing and the agent starting to speak, measured from the recording on every turn of the call.
#490 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.
#383 of 662 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#568 of 662 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 94% | 4.67 s | — |
| Home services | 86% | 4.73 s | — |
| Insurance | 95% | 4.22 s | — |
| Customer support | 93% | 4.50 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 93% | 4.79 s | — |
| Spanish-accented English, city street | 92% | 4.33 s | — |
| Indian English, busy café | 89% | 4.18 s | — |
| Southern US, flustered, crying baby | 96% | 4.66 s | — |
| Fast and interrupting, construction outside | 90% | 4.78 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, uh, sorry. I'm a little flustered right now. My baby's crying in the background and I've been trying to get this sorted for a couple hours. My internet's been down since this morning. I work from home, so it's been real stressful. There's a road crew digging up the street right outside. I already rebooted the gateway twice and checked every cable I could find. The internet light is blinking orange. Is the road crew the reason it's out? Can you check on that for me?
AGENTWe’ll get this sorted as fast as we can so you can get back to work and the baby. First I need to pull up your account and check for any outage on our side. What’s easier for you right now: - Your Brightwave account number, or. - The phone number on the account? Tell me one of those and I’ll check right away if there’s an outage related to that road work or anything else in your area.
CUSTOMERThanks. I really appreciate you moving quick. Sorry, I'm just a little anxious about all this. I've got my account number here. It's BW883017... Oh, sorry, last digit is one. Can you check if there's an outage? And if the road crew's the cause?
AGENTI’ve got your account pulled up—BW8830171—and I checked your line and the area. 1. Road crew / outage check. - There is no area outage showing for your address. - Your line signal from the street to your gateway looks good, so whatever the road crew is doing doesn’t appear to have cut your line on our side. They could still be working near your drop, but nothing’s showing as damaged in our system. 2. What I just did. - Your gateway was showing as “not registered” even though the signal looked fine. - I sent a remote reset to your Brightwave BX7. - It’s now showing as “registered and online” on my end. 3. What you should see. - The internet light on the gateway should turn solid (not blinking orange) within about 2 minutes. - Wi‑Fi devices may drop and then reconnect on their own. If they don’t: - On a laptop/phone, toggle Wi‑Fi off and back on, then reconnect to your usual network. - For a work computer, you might need to re‑launch VPN or remote‑desktop after the connection comes back. Can you take a quick look at the gateway for me? - Is the internet light solid now, or still blinking orange? - And on your work device, does a website load if you try it now?
CUSTOMERAlright, um, hang on, let me check real quick. Okay, the light just went solid white, so that's good, right? How long till my devices reconnect? Should I just toggle Wi-Fi, or will they come back on their own? Sorry, I'm just nervous about messing anything up.
AGENTSolid white is exactly what we want—that means the connection is back and online. For your devices: 1. What will happen on its own. - Most phones, tablets, and laptops will reconnect to the same Wi‑Fi automatically within 1–2 minutes. - Some work laptops (especially with VPN) may just sit there until you manually reconnect. 2. What I recommend you do now (simple and safe). Do this one at a time, starting with your work device: - On the device, turn Wi‑Fi off, wait 5 seconds, then turn it back on. - Select your usual Wi‑Fi network name and connect. - If you use a VPN or remote desktop for work, open that after you see normal internet working (e.g., you can load a website). You won’t mess anything up by toggling Wi‑Fi—that’s completely safe and often faster than waiting. If you want, tell me which device you use for work (Windows laptop, Mac, etc.), and I’ll give you the exact clicks/taps to reconnect.
CUSTOMEROkay, that's real helpful. Thank you. I use a Windows laptop for work, so I'll try toggling Wi-Fi. Is there a way to do that quick, or should I just use the little icon down by the clock? Sorry if I sound frantic, I just want to make sure I don't make things worse. And, um, can I ask about a credit for the downtime? I lost two hours of work because of this.
AGENTYou’re not making anything worse, and you’re not being frantic—you’re just trying to get back to work. You’re doing fine. First, the quick Wi‑Fi toggle on Windows: 1. On your keyboard, press Windows key + A (opens Quick Settings). 2. In the panel that pops up, click the Wi‑Fi icon to turn it Off. 3. Wait about 5 seconds. 4. Click the Wi‑Fi icon again to turn it On. 5. Click the little arrow or the Wi‑Fi name, pick your usual network, and connect. 6. Once a website works, start your VPN or remote desktop if you use one. Using the little Wi‑Fi icon by the clock works too; the shortcut is just faster. About the credit: - I’ve applied a $10.00 service credit to your account BW8830171 for today’s downtime. - You’ll see it on your next bill. When you get a second, let me know if your Windows laptop is back online after that Wi‑Fi toggle or if it’s still not connecting, and I’ll walk you through the next step.
CUSTOMERThank you, that's reassuring. I'll do that right now. Um, about the credit... Sorry, but I lost two hours of work. Is there any way you could make it more than ten dollars? I'd really appreciate it.
AGENTI understand why you’re asking, especially if you lost paid hours. I do have to stay within what I’m allowed to issue directly, and I’ve already applied the $10.00 credit to account BW8830171, which is the standard amount I can grant for a short same‑day outage. Two important points, though: 1. That $10.00 is guaranteed and will show on your next bill. 2. If you want to request more because of lost income, that kind of claim has to go through our customer care/billing team—they can review your situation in more detail than I can here. If you’d like, I can: - Summarize what happened and what I see on the line today so you can reference it when you speak with billing, and. - Tell you the best way/time to reach them so you’re not stuck on hold with a crying baby in the background. Meanwhile, how’s the Windows laptop looking after that Wi‑Fi toggle—are you back online yet?
CUSTOMERAlright, I appreciate you being up front. I'll reach out to Billing later for that then. My laptop's reconnecting now. Looks like the website's loading again, so I think I'm good. Thanks for walking me through all this. I was pretty stressed. I'm all set now, so I'll let you go. Have a good day.
AGENTYou’re back online and that’s what matters most right now. Quick recap before you go: - Your gateway is up and stable (solid white light). - Your Windows laptop is reconnected and browsing. - A $10.00 credit is already applied to account BW8830171 and will show on your next bill. If things act up again—especially with that road work going on—just tell support you already had a remote reset today and the modem came back as “registered and online,” and they’ll know where to pick up. Take care of yourself and the baby, and good luck with the rest of your workday.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
AGENTRiverbend
CUSTOMERRiverbend Health Clinic, this is Alex. How can I help you today? Hi, I'm calling about my dermatology appointment next Wednesday morning. I need to move it because I have a work shift then. My name is Lucia Ramirez. Can you help me reschedule?
CUSTOMERHi, I'm calling about my dermatology appointment next Wednesday morning. I need to move it because I have a work shift then. My name is Lucia Ramirez. Can you help me reschedule?
CUSTOMERI can help with that. To get into your chart, I need to verify you first. Sorry, could you repeat that? The street is noisy. I didn't catch what you said.
AGENTI can help with that. To get into your chart, I need to verify you first. Please
CUSTOMERSorry, could you repeat that? The street is noisy. I didn't catch what you said.
CUSTOMERNo problem. I just need to verify your identity before I change anything. Please tell me. One, your full name as it appears on your records, and two, your date of birth, YYYYMMDD.
AGENTNo problem. I just need to verify your identity before I change anything. Please tell me: 1) Your full name as it appears on your records, and. 2) Your date of birth (YYYY-MM-DD).
CUSTOMEROkay, my full name is Lucia Ramirez. My date of birth is March 17, 1948. Sorry, no, 1984. March 17, 1984.
CUSTOMEROkay, my full name is Lucia Ramirez. My date of birth is March 17, 1948. Sorry, no, 1984. March 17, 1984.
AGENTThanks, Ms. Ramirez.
AGENTThanks, Ms. Ramirez. I’ve found your dermatology appointment: - Department: Dermatology. - Provider: Dr. Okafor. - Day: next Wednesday. - Time: 09:15 AM. - Location: Main Campus, Building B. You mentioned you need to move it because of a work shift. What times or days would work better for you? For example: - Same day but later in the day? - A different day (e.g., later in the week, only afternoons, only mornings)? Tell me your constraints (days and time ranges), and I’ll look for openings that fit.
CUSTOMERThanks, Ms. Ramirez. I found your dermatology appointment. Department, Dermatology, Provider, Dr. Okafor. Day, next Wednesday. Time, 915 a.m. Location, main campus, building B.
CUSTOMEREat. Eat. Eat. Eat. Eat. Yeah, I can only come after 3 p.m. Mornings don't work for me anymore. Is there anything later in the day?
CUSTOMERYou mentioned you need to move it because of a work shift. What times or days would work better for you? For example, same day but later in the day? A different day, for example, later in the week? Only afternoons? Only mornings? Tell me your constraints, days, and time ranges, and I'll look for openings that fit.
CUSTOMERYeah, I can only come after 3 p.m. Mornings don't work for me anymore. Is there anything later in the day?
AGENTI checked Dr. Okafor’s schedule starting from next Wednesday, and there are a couple of options that fit your “after 3 p.m.” requirement: - Tuesday at 3:45 p.m. - Thursday at 4:10 p.m. Both are at the Main Campus, Building B. Which would you prefer: Tuesday at 3:45 p.m. or Thursday at 4:10 p.m.?
CUSTOMERI checked Dr. Okafor's schedule starting from next Wednesday, and there are a couple of options that fit your after 3 p.m. requirement, Tuesday at 3.45 p.m., Thursday at 4.10 p.m. Both are at the main campus, Building B. Which would you prefer, Tuesday at 3.45 p.m. or Thursday at 4.10 p.m.? Tuesdays don't work after all, because I pick up my daughter then. What about Friday? If not, I can do Thursday at 4.10pm.
CUSTOMERTuesdays don't work after all, because I pick up my daughter then. What about Friday? If not, I can do Thursday at 4.10pm.
AGENTFor Fridays with Dr. Okafor, the only slot I see is 11:30 a.m., which is before 3 p.m., so that won’t work with your schedule. The next best fit is: - Thursday at 4:10 p.m. Do you want me to move your current appointment from next Wednesday at 9:15 a.m. to Thursday at 4:10 p.m.? If you say yes, I’ll reschedule it and read back the new details and confirmation code.
CUSTOMERFor Fridays with Dr. Okafor, the only slot I see is 11.30am, which is before 3pm, so that won't work with your schedule. The next best fit is Thursday at 4.10pm. Do you want me to move your current appointment from next Wednesday at 9.15am to Thursday at 4.10pm? If you say yes, I'll reschedule it and read back the new details and confirmation code. Yes, please go ahead and move it to Thursday at 4.10pm.
CUSTOMERYes, please go ahead and move it to Thursday at 4.10pm.
AGENTYou’re all set, Ms. Ramirez. I’ve moved your dermatology visit with Dr. Okafor from next Wednesday
CUSTOMERYou're all set, Ms. Ramirez. I've moved your dermatology visit with Dr. Okafor from next Wednesday.
CUSTOMEROkay, before we finish, can you tell me if there is a fee for changing the appointment?
CUSTOMEROkay, before we finish, can you tell me if there is a fee for changing the appointment?
AGENTThere’s no fee for the change you just made. Our policy is: “Changes made more than 24 hours before the appointment are free; later changes carry a $40 fee.” Since you rescheduled well more than 24 hours in advance, there’s no charge.
CUSTOMERThere's no fee for the change you just made. Our policy is, changes made more than 24 hours before the appointment are free. Later changes carry a $40 fee. Since you rescheduled well more than 24 hours in advance, there's no charge. Got it. Where should I park for the appointment?
CUSTOMERGot it. Where should I park for the appointment?
AGENTFor your appointment at the Main Campus, Building B, you can park in: - Free patient parking in Lot C, entrance on River Road. Give yourself a few extra minutes to find a spot and walk over, and remember to arrive about 15 minutes early with a photo ID and your insurance card.
CUSTOMERFor your appointment at the main campus, Building B, you can park in Free Patient Parking in Lot C, entrance on River Road. Give yourself a few extra minutes to find a spot and walk over, and remember to arrive about 15 minutes early with a photo ID and your insurance card. Okay, thank you. And does Dr. Rocafort accept Aetna insurance?
CUSTOMEROkay, thank you. And does Dr. Rocafort accept Aetna insurance?
CUSTOMERI'm not able to see which insurances individual providers accept. Also, I don't see a Dr. Roquefort in the dermatology schedule I have access to. Your dermatologist is listed as Dr. Okafor. To get an accurate answer on Aetna coverage for Dr. Roquefort, I recommend either calling the Riverbend Health Clinic front desk or checking your Aetna member portal or calling the number on your insurance card to search for Dr. Roquefort by name. If you'd like, you can also confirm the spelling and specialty of Dr. Roquefort, and I can note that for when you speak with the front desk.
AGENTI’m not able to see which insurances individual providers accept. Also, I don’t see a Dr. Rocafort in the dermatology schedule I have access to—your dermatologist is listed as Dr. Okafor. To get an accurate answer on Aetna coverage for Dr. Rocafort, I recommend either: - Calling the Riverbend Health Clinic front desk, or. - Checking your Aetna member portal or calling the number on your insurance card to search for Dr. Rocafort by name. If you’d like, you can also confirm the spelling and specialty of Dr. Rocafort, and I can note that for when you speak with the front desk.
CUSTOMERUh-huh, no worry. I'll double check with the front desk. Can you please read back the new appointment time and the confirmation code?
AGENTI’m glad
CUSTOMERUh-huh, no worry. I'll double check with the front desk. Can you please read back the new appointment time and the confirmation code?
CUSTOMERYour current appointment details are Provider, Dr. Okafor. Department, Dermatology. Day, Thursday. Time, 410 p.m. Location, Main Campus, Building B. Confirmation code, RVB3M8P2. Please arrive about 15 minutes early with a photo ID and your insurance card. Perfect, yes, that's all correct. Thank you for your help. Good-bye!
AGENTYour current appointment details are: - Provider: Dr. Okafor. - Department: Dermatology. - Day: Thursday. - Time: 4:10 p.m. - Location: Main Campus, Building B. - Confirmation code: RVB-3M8P2. Please arrive about 15 minutes early with a photo ID and your insurance card.
CUSTOMERPerfect, yes, that's all correct. Thank you for your help. Goodbye.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERhello yes I'm having an urgent problem at my apartment the pipe under my kitchen sink has burst water is spreading across the floor heading toward a power strip I have not shut the water off yet can you send someone out to fix this
AGENTFirst, let’s get you safe and stop the damage. 1. Stay away from that power strip right now. - Do not touch it or anything plugged into it. - If you can safely do so without stepping in water, move away from that area. 2. Shut off the water immediately: - Look under the sink for two small shutoff valves (one for hot, one for cold) on the pipes. • Turn both knobs clockwise until they stop. - If you can’t find or reach those, or they won’t turn, go to your main water shutoff for the apartment (often: in a utility closet, near the water heater, or by the entry). Turn that valve clockwise to off. - If you’re not sure where the main is and the water is still heading toward the power strip, step away from the water and tell me; we may need you to contact building maintenance or emergency services. 3. If water has already
CUSTOMEROkay.
CUSTOMERRight, the water has not reached the power strip yet. I am shutting off the valves under the sink now. It has stopped flowing. What should I do next?
AGENTGood job getting the water stopped—that’s the most important part. Next safety steps:
CUSTOMERAha, go ahead. What are the next steps I should follow for safety?
AGENTGood, since the water’s stopped and hasn’t reached the power strip, here’s what to do next: 1. Deal with the electricity safely. - If the floor is still wet anywhere near that power strip, do not touch the strip or any cords. - If you can safely reach the wall outlet without stepping in water, you can unplug the power strip from the wall. If there’s any doubt, leave it alone and keep the area clear. 2. Control and clean up the water. - Put down towels, a mop, or a bucket under the sink to catch any remaining drips. - Wipe up standing water on the floor so it doesn’t spread to outlets, baseboards, or cabinets. - If you have a fan, you can point it at the damp area to start drying things out. 3. Don’t turn the water back on to that sink. - Leave those under-sink valves off until a plumber repairs the pipe. - You can still use other fixtures in the home as long as they’re not affected. Next, I’d like to get a plumber out to you on an urgent basis. Can you tell me: - Your name. - The service address including any apartment/unit number and gate code if there is one. - The best phone number to reach you. And is this your first time using Copperline Home Services at this address, or have we been out to you before?
CUSTOMERYes. So, my name is Arjun Mehta. The address is 1480 Larkspur Avenue, Unit 4D. I moved from 4B to 4D last month, so please make sure it is 4D. The building gate code is £2719. My phone number is 503 555 0139. No, 0193. Copperline has been out to this address before, but I am in a different unit now.
AGENTThanks, Arjun.
CUSTOMERRight, so can you let me know how much the visit will cost before I confirm the booking?
AGENTYou’re a Copperline Care member, and this is an emergency same‑day visit, so the callout fee will be $99. That’s just to get the emergency plumber out and diagnose/stop the leak; any repair work, parts, or drying/cleanup beyond basic mop-up would be additional and the technician will quote those on-site before proceeding. Would you like me to book the emergency window today from 2:00 PM to 4:00 PM at: - 1480 Larkspur Avenue, Unit 4D. - Gate code: £2719. - Callback number: 503-555-0193. Please confirm you’re okay with the $99 emergency callout fee and that this address/unit and phone number are all correct, and I’ll
CUSTOMERYes, that's right. I'm okay with the $99 emergency call-out fee. The address, unit, gate code and phone number are all correct. Is it possible for anyone to come before 2pm? If not, I will take the 2-4pm window. Who will be coming and how will I know they are on the way? Also, I would like to hear the ticket number for the visit.
AGENTopen
AGENTThanks for confirming everything, Arjun. On your questions: 1) Earlier than 2 PM. I’ve checked what we have for emergency slots, and the earliest available window today is 2:00 PM to 4:00
CUSTOMEROkay. Thank you. Thank you.
CUSTOMERThat's fine. I will take the 2 o'clock p.m. to 4 o'clock p.m. window. Please let me know who is coming, how I will know they are on the way and what the ticket number is for this visit.
AGENTYou’re all set,
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes, I'm somewhere safe. I'm standing next to my car. Just wanted to call about the accident I was in a little while ago.
AGENTI’m glad you’re safe. Is anyone injured at the scene—either in your car or the other vehicle? If anyone is hurt or in danger, please hang up and call 911 right away before we continue.
CUSTOMERNo, nobody is hurt. We're both okay. It's just the cars that are damaged.
AGENTUnderstood, thanks for letting me know. Let’s get your policy pulled up first. What’s your auto policy number, and the policyholder’s last name?
CUSTOMERMy policy number is NG4471903. No, sorry, the last one is 2. The policy holder's last name is Ellis.
AGENTThanks, I’ve got your policy pulled up under Ellis, policy number NG4471902. Now I’ll get the accident details so we can open your claim. 1) When did the accident happen? - Date and approximate time. 2) Where did it happen? - Street
CUSTOMERIt happened today, about 20 minutes ago, so June 19th, around 3pm. The accident happened about 20 minutes ago. I was stopped at a red light at Southeast 5th Avenue and Alder Street.
AGENTThank you. I have: today, June 19th, around 3:00 p.m., at SE 5th Avenue and Alder Street. Next, I need a quick description of what happened. - What were you doing just before the impact? - What did the other driver do? Also, please tell me: 1) The other driver’s name (as best you have it), 2) Their insurance company (if you’ve exchanged cards), and. 3) Their license plate number. And did the police come to the scene, and if so, is there a report number yet, or just that an officer responded?
CUSTOMERI was stopped at a red light, waiting. The other driver hit the back of my car. His name is Kevin Lund. He's insured with Pacific Shore, and his plate is 7KXR214. The police did not come, so there's no report number.
AGENTThanks, I’ve got everything I need to open the claim. Here’s what I have on file and what we’ve set up: - Policy number: NG4471902. - Other driver: Kevin Lund, insured with Pacific Shore, license plate 7KXR214. - What happened: You were stopped at a red light at SE 5th Avenue and Alder Street when the other driver hit the back of your car. - Date/time of loss: Today, June 19, about 3:00 p.m. - Injuries: None reported. - Police: No police responded; no report filed. Your claim is now open. Your claim number is: NGM-904417. Your assigned adjuster is Priya Shah; you should hear from her within one business day. From your coverage lookup, I can tell you: - Collision deductible: $500. - Rental coverage: $40 per day for up to 30 days, starting today (the day the claim is opened). - Towing: Covered up to 25 miles. A couple of quick questions about your car right now: 1) Is your Honda CR‑V safe to drive? 2) If it’s not safe to drive, where is the vehicle located right now, and what’s a good phone number for the tow driver to reach you? If it isn’t drivable, I can arrange a tow for you under your towing coverage.
CUSTOMERNo, it's not safe to drive. The back bumper is crushed and the rear wheel rubs when I try to move it. The car is at SE 5th Avenue and Alder Street, right where the accident happened. My phone number is 907-416-2631. Could you arrange a tow for me? And where will the car be taken?
AGENTI can help with that. I’ve arranged a tow for you. Here’s what’s set up: - Tow location: Intersection of SE 5th Avenue and Alder Street. - Tow company: Eastside Towing. - Estimated arrival time: About 45 minutes. - Call-back number they’ll use: 907-416-2631. The car will be taken to: - A Northgate partner repair shop at 9th and Morrison. You’re covered for towing up to 25 miles, so this tow will fall under that coverage. Let me quickly read back the key details we have: - Policy number: NG4471902. - Other driver’s license plate: 7KXR214. - Your claim number: NGM-904417. If any of that isn’t right, tell me and I’ll fix it. While you’re waiting for the tow: - If it’s safe, remove any valuables from the car. - Keep your phone nearby so Eastside Towing can reach you. Do you have any questions about the tow, the repair shop at 9th and Morrison, or what happens next with your claim?
CUSTOMERThat all sounds correct. I do have a couple of questions. How much will I actually have to pay out of pocket? You mentioned a $500 deductible, but since he hit me, I should not have to pay that, right? Also, is my premium going to go up because of this accident?
CUSTOMERHello?
AGENTYou’re still connected—I was just pulling up your coverage again so I don’t guess at anything. Here’s what I can tell you, and where I have to defer to your adjuster: 1) What you pay out of pocket / the $500 deductible. - Your policy shows a $500 collision deductible. - Whether you actually end up paying that depends on how liability is decided and which company ultimately pays for the repairs. - From here, I can only confirm the deductible amount; I can’t see or decide fault, or say for sure whether your deductible will apply or be reimbursed. Your adjuster, Priya Shah, will: - Determine how the claim is being handled (through your policy, the other driver’s insurer, or both). - Explain if/when your $500 deductible would be collected and under what circumstances it might be recovered from the other carrier. 2) Whether your premium will go up. - I don’t have access to rating or pricing decisions, so I can’t say if your premium will increase. - Premium changes depend on several factors: claim outcome, state rules, your prior history, and company underwriting, which I don’t see from here. Priya will be the one who can walk you through: - How this accident is being coded on your policy, and. - Whether it’s likely to affect your rate at renewal. You should hear from her within one business day at the contact information we have on file. If you’d like, I can summarize the specific questions you want her to cover (deductible responsibility and premium impact) so she addresses them first when she calls.
CUSTOMERYes, that would be helpful. Please make sure she covers whether I'll have to pay the deductible and if my premium will go up. I'd also like to know if there's anything else I need to do right now, or if I just wait for her call.
AGENTI’ll note on your claim that you specifically want Priya to go over: 1) Whether you’ll actually have to pay the $500 deductible, and 2) Whether this accident is likely to affect your premium. She should address those when she contacts you. As for what you need to do right now: - At the scene: - Stay put
AGENTand wait for Eastside Towing to arrive (about 45 minutes). - If it’s safe, take photos of: overall scene, damage to your Honda, damage to the other car, and the intersection/traffic lights. - Keep the other driver’s info handy (you’ve already given us his name, insurer, and plate). - After the tow: - The tow will take your car to the Northgate partner repair shop at 9th and Morrison. - You don’t need to authorize any major repairs until you’ve spoken with the adjuster, but the shop can usually do an initial inspection and estimate. - Documents to keep together for Priya: - Any photos you took. - The other driver’s insurance information (Pacific Shore) and plate 7KXR214. - Any receipts related to this loss (taxis, rideshares, etc. ), just in case they’re needed later. Otherwise, you can wait for Priya’s call. Your key numbers, just to repeat: - Policy number: NG4471902. - Claim number: NGM-904417. Is there anything else you’re unsure about right now—like rental cars, timing for repairs, or what to say if the other driver’s insurance calls you before Priya does?