Roark Live Bench · Suite v1.3 · Sweep of 15 November 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
- Best overallSoniox v6 + GPT-6.1 Terra + Sonic-3.5Level with 35 othersRoark score75 / 100Task completion93%Median response3.7 sCost per minute$0.035
- Best valueSoniox v6 + Muse Ember 1.0 + TTS-1Level with 7 othersRoark score74 / 100Task completion92%Median response2.2 sCost per minute$0.012
- FastestLinden-1 (own VAD) + Claude Haiku 4.5 + TTS-1Roark score54 / 100Task completion84%Median response1.2 sCost per minute$0.032
- Best speech-to-speechGPT Live 1 (Sol)Level with 4 othersRoark score66 / 100Task completion85%Median response2.3 sCost per minute$0.061
- Best in customer supportGrok Voice 3.0Level with 6 othersRoark score86 / 100Task completion95%Median response1.7 sCost per minute$0.083
- Best in healthcareSoniox v6 + Claude Haiku 5.5 + Flash v2.5Level with 22 othersRoark score78 / 100Task completion87%Median response2.5 sCost per minute$0.11
- Best in home servicesSoniox v6 + GPT-6.1 Sol + Flash v2.5Level with 10 othersRoark score77 / 100Task completion96%Median response3.7 sCost per minute$0.11
- Best in insuranceUniversal-3.5 Pro + GPT-4o + Turbo v2.5Level with 20 othersRoark score76 / 100Task completion100%Median response3.2 sCost per minute$0.10
The read
- 496 of 890 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 1.2 s to 6.2 s on the same agent and the same caller, a spread of 5.0 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 + AssemblyAI TTS-1 at 1.2 s, ranks 832 of 890 on task completion; the most complete is Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD at 99%.
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 all 6 measures compared here.
- Speech-to-speech costs 3.7 times as much per completed task: $0.24 for speech-to-speech against $0.07 for cascades.
| Measure | Cascade | Speech-to-speech |
|---|---|---|
| Task completion | 92% (leads) | 85% |
| Tool use | 87% (leads) | 78% |
| Time to first word | 0.6 s (leads) | 1.1 s |
| Response time | 2.1 s (leads) | 2.1 s |
| Barge-in handling | 100% (leads) | 96% |
| Cost per task | $0.07 (leads) | $0.24 |
The three strongest of each, averaged. Cascades: Deepgram Flux + OpenAI GPT-6.1 Terra + AssemblyAI TTS-1; Deepgram Flux + Meta Muse Ember 1.0 + AssemblyAI TTS-1; Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Terra + AssemblyAI TTS-1. 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.
- Pick Soniox v6: it leads on semantic word error rate (0.2%). If speed matters more, Deepgram Flux is the quickest, at 0.38 s.
- Deepgram Flux delivers its transcript in 0.38 s, OpenAI Whisper-1 in 1.93 s: 1.54 s added to every turn of the call.
- Soniox v6 is the most accurate: it changes the meaning of 0.2% of the caller's words, against 2.1% for Speechmatics Linden-1 (own VAD).
- In 574 of 1,161 cascades the transcriber is the slowest step of the turn, whichever model runs it.
Roark score, best first
| # | |||||
|---|---|---|---|---|---|
| 1 | Soniox v6Soniox | 100 / 100. Semantic word error rate 0.2%, 71.4 of 71 points; Time to final transcript 0.85 s, 28.6 of 29 points(among the best) | 0.2%(among the best) | 0.85 s(among the best) | $0.008(among the best) |
| 2 | Universal-3.6 ProAssemblyAI | 91 / 100. Semantic word error rate 0.8%, 62.9 of 71 points; Time to final transcript 0.90 s, 28.6 of 29 points(among the best) | 0.8%(among the best) | 0.90 s | $0.029 |
| 3 | Nova-3Deepgram | 83 / 100. Semantic word error rate 1.1%, 54.3 of 71 points; Time to final transcript 0.88 s, 28.6 of 29 points(among the best) | 1.1%(among the best) | 0.88 s | $0.031 |
| 4 | Universal-3.5 ProAssemblyAI | 82 / 100. Semantic word error rate 1.1%, 53.3 of 71 points; Time to final transcript 0.90 s, 28.6 of 29 points | 1.1%(among the best) | 0.90 s | $0.030 |
| 5 | Enhanced (realtime)Speechmatics | 72 / 100. Semantic word error rate 1.5%, 43.9 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points | 1.5% | 0.98 s | $0.054 |
| 6 | FluxDeepgram | 70 / 100. Semantic word error rate 1.5%, 41.9 of 71 points; Time to final transcript 0.38 s, 28.6 of 29 points | 1.5% | 0.38 s(among the best) | $0.031 |
| 7 | Nova-2Deepgram | 68 / 100. Semantic word error rate 1.6%, 39.7 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points | 1.6% | 0.89 s | $0.023 |
| 8 | Linden-1Speechmatics | 68 / 100. Semantic word error rate 1.6%, 39.7 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points | 1.6% | 0.98 s | $0.020 |
| 9 | Scribe v3 LiveElevenLabs | 67 / 100. Semantic word error rate 1.7%, 38.0 of 71 points; Time to final transcript 0.88 s, 28.6 of 29 points | 1.7% | 0.88 s | $0.015(among the best) |
| 10 | Standard (realtime)Speechmatics | 64 / 100. Semantic word error rate 1.8%, 35.1 of 71 points; Time to final transcript 0.96 s, 28.6 of 29 points | 1.8% | 0.96 s | $0.031 |
| 11 | Linden-1 (own VAD)Speechmatics | 56 / 100. Semantic word error rate 2.1%, 27.1 of 71 points; Time to final transcript 0.46 s, 28.6 of 29 points | 2.1% | 0.46 s(among the best) | $0.020 |
| 12 | Whisper-1OpenAI | 54 / 100. Semantic word error rate 1.5%, 43.0 of 71 points; Time to final transcript 1.93 s, 10.9 of 29 points | 1.5% | 1.93 s | $0.025 |
| 13 | GPT TranscribeOpenAI | 50 / 100. Semantic word error rate 1.9%, 30.6 of 71 points; Time to final transcript 1.47 s, 19.5 of 29 points | 1.9% | 1.47 s | $0.018(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.
- OpenAI GPT-6.1 Terra and OpenAI GPT-6.1 Sol are level: neither leads by more than the margin of error. Of the two, OpenAI GPT-6.1 Terra costs least, at $0.013 a call. Avoid OpenAI GPT-5.1: last on tool use (42%) and instruction following (4.1 / 5).
- Anthropic Claude Haiku 4.5 starts answering in 0.36 s, Google Gemini 3.8 Flash in 1.50 s: 1.15 s added to every turn of the call.
- OpenAI GPT-6.1 Terra uses its tools most reliably: it handles its tools without a mistake on 86% of calls, against 42% for OpenAI GPT-5.1.
- In 339 of 1,161 cascades the language model is the slowest step of the turn, whichever model runs it.
Roark score, best first
Not ranked here for missing data: Groq GPT-OSS 120B (no task completion or tool use or instruction following or time to first token).
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6.1 TerraOpenAI | 64 / 100. Task completion 91%, 19.2 of 36 points; Tool use 86%, 19.6 of 27 points; Instruction following 4.3 / 5, 11.5 of 18 points; Time to first token 0.83 s, 14.2 of 18 points(among the best) | 91%(among the best) | 4.3 / 5(among the best) | 86%(among the best) | 0.83 s | 67% | $0.013 |
| 2 | GPT-6.1 SolOpenAI | 63 / 100. Task completion 92%, 22.2 of 36 points; Tool use 82%, 17.4 of 27 points; Instruction following 4.3 / 5, 11.7 of 18 points; Time to first token 1.00 s, 12.2 of 18 points(among the best) | 92%(among the best) | 4.3 / 5(among the best) | 82%(among the best) | 1.00 s | 72% | $0.019 |
| 3 | Claude Sonnet 5.5Anthropic | 57 / 100. Task completion 91%, 20.2 of 36 points; Tool use 75%, 13.5 of 27 points; Instruction following 4.2 / 5, 11.0 of 18 points; Time to first token 0.94 s, 12.8 of 18 points(among the best) | 91%(among the best) | 4.2 / 5 | 75%(among the best) | 0.94 s | – | $0.115 |
| 4 | Muse Ember 1.0Meta | 57 / 100. Task completion 90%, 18.4 of 36 points; Tool use 66%, 8.9 of 27 points; Instruction following 4.3 / 5, 11.8 of 18 points; Time to first token 0.56 s, 17.5 of 18 points(among the best) | 90% | 4.3 / 5(among the best) | 66% | 0.56 s | 85%(among the best) | $0.005(among the best) |
| 5 | Claude Haiku 5.5Anthropic | 56 / 100. Task completion 90%, 17.5 of 36 points; Tool use 68%, 10.0 of 27 points; Instruction following 4.3 / 5, 12.2 of 18 points; Time to first token 0.63 s, 16.5 of 18 points | 90% | 4.3 / 5(among the best) | 68% | 0.63 s | – | $0.008(among the best) |
| 6 | Gemini 3.8 FlashGoogle | 49 / 100. Task completion 92%, 21.5 of 36 points; Tool use 69%, 10.2 of 27 points; Instruction following 4.3 / 5, 11.5 of 18 points; Time to first token 1.50 s, 6.0 of 18 points | 92%(among the best) | 4.3 / 5(among the best) | 69% | 1.50 s | – | $0.015 |
| 7 | GPT-4.1OpenAI | 48 / 100. Task completion 90%, 17.3 of 36 points; Tool use 52%, 1.1 of 27 points; Instruction following 4.2 / 5, 11.1 of 18 points; Time to first token 0.52 s, 18.0 of 18 points | 90% | 4.2 / 5 | 52% | 0.52 s | 82%(among the best) | $0.016 |
| 8 | Claude Haiku 4.5Anthropic | 45 / 100. Task completion 88%, 14.4 of 36 points; Tool use 51%, 0.8 of 27 points; Instruction following 4.3 / 5, 11.4 of 18 points; Time to first token 0.36 s, 18.2 of 18 points | 88% | 4.3 / 5(among the best) | 51% | 0.36 s(among the best) | – | $0.053 |
| 9 | GPT-4o miniOpenAI | 43 / 100. Task completion 86%, 10.3 of 36 points; Tool use 56%, 3.1 of 27 points; Instruction following 4.2 / 5, 11.1 of 18 points; Time to first token 0.50 s, 18.2 of 18 points | 86% | 4.2 / 5 | 56% | 0.50 s(among the best) | 82%(among the best) | $0.001(among the best) |
| 10 | GPT-4oOpenAI | 42 / 100. Task completion 86%, 11.2 of 36 points; Tool use 53%, 1.8 of 27 points; Instruction following 4.2 / 5, 11.2 of 18 points; Time to first token 0.45 s, 18.2 of 18 points | 86% | 4.2 / 5 | 53% | 0.45 s(among the best) | – | $0.022 |
| 11 | GPT-5.1OpenAI | 41 / 100. Task completion 87%, 13.1 of 36 points; Tool use 42%, 0.0 of 27 points; Instruction following 4.1 / 5, 10.4 of 18 points; Time to first token 0.59 s, 17.1 of 18 points | 87% | 4.1 / 5 | 42% | 0.59 s | 74% | $0.026 |
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.
- Deepgram Flux TTS, AssemblyAI TTS-1, Cartesia Sonic-3.6 and Cartesia Sonic-3.5 are level: none leads by more than the margin of error. Of them, AssemblyAI TTS-1 costs least, at $0.054 a call. Avoid OpenAI TTS-1 HD: last on readback accuracy (81%), word error rate (7.6%) and time to first audio byte (2.09 s).
- AssemblyAI TTS-1 starts speaking in 0.04 s, OpenAI TTS-1 HD in 2.09 s: 2.04 s added to every turn of the call.
- AssemblyAI TTS-1 is also the most accurate: it reads codes, amounts and dates back correctly 90% of the time, against 81% for OpenAI TTS-1 HD.
- Rime Coda sounds the most human: 3.5 / 5, against 3.2 / 5 for ElevenLabs Turbo v2.5.
- In 119 of 1,161 cascades the speech engine is the slowest step of the turn, most often with OpenAI TTS-1 (65 of them).
Roark score, best first
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | Flux TTSDeepgram | 83 / 100. Readback accuracy 89%, 27.4 of 38 points; Word error rate 4.8%, 17.9 of 25 points; Time to first audio byte 0.13 s, 25.0 of 25 points; Voice consistency 100%, 12.2 of 13 points(among the best) | 4.8%(among the best) | 89%(among the best) | 3.2 / 5 | 100%(among the best) | 0.13 s | $0.119 |
| 2 | TTS-1AssemblyAI | 82 / 100. Readback accuracy 90%, 28.0 of 38 points; Word error rate 5.3%, 16.8 of 25 points; Time to first audio byte 0.04 s, 25.0 of 25 points; Voice consistency 100%, 12.3 of 13 points(among the best) | 5.3% | 90%(among the best) | 3.3 / 5 | 100%(among the best) | 0.04 s(among the best) | $0.054(among the best) |
| 3 | Sonic-3.6Cartesia | 82 / 100. Readback accuracy 89%, 27.2 of 38 points; Word error rate 5.1%, 17.3 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 100%, 12.2 of 13 points(among the best) | 5.1% | 89%(among the best) | 3.5 / 5(among the best) | 100%(among the best) | 0.12 s(among the best) | $0.160 |
| 4 | Sonic-3.5Cartesia | 82 / 100. Readback accuracy 88%, 26.5 of 38 points; Word error rate 5%, 17.6 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 100%, 12.5 of 13 points(among the best) | 5% | 88% | 3.4 / 5(among the best) | 100%(among the best) | 0.12 s(among the best) | $0.157 |
| 5 | v4 TurboElevenLabs | 82 / 100. Readback accuracy 88%, 26.6 of 38 points; Word error rate 4.7%, 18.2 of 25 points; Time to first audio byte 0.11 s, 25.0 of 25 points; Voice consistency 99%, 11.7 of 13 points(among the best) | 4.7%(among the best) | 88% | 3.4 / 5(among the best) | 99% | 0.11 s(among the best) | $0.455 |
| 6 | Sonic-3Cartesia | 78 / 100. Readback accuracy 87%, 25.2 of 38 points; Word error rate 5.7%, 15.8 of 25 points; Time to first audio byte 0.16 s, 25.0 of 25 points; Voice consistency 100%, 12.2 of 13 points | 5.7% | 87% | 3.2 / 5 | 100%(among the best) | 0.16 s | $0.153 |
| 7 | Turbo v2.5ElevenLabs | 75 / 100. Readback accuracy 81%, 20.1 of 38 points; Word error rate 4.7%, 18.2 of 25 points; Time to first audio byte 0.15 s, 25.0 of 25 points; Voice consistency 99%, 11.7 of 13 points | 4.7%(among the best) | 81% | 3.2 / 5 | 99% | 0.15 s | $0.439 |
| 8 | Flash v2.5ElevenLabs | 74 / 100. Readback accuracy 81%, 19.9 of 38 points; Word error rate 5%, 17.5 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 99%, 11.9 of 13 points | 5% | 81% | 3.3 / 5 | 99% | 0.12 s(among the best) | $0.408 |
| 9 | CodaRime | 73 / 100. Readback accuracy 84%, 22.5 of 38 points; Word error rate 6.8%, 13.1 of 25 points; Time to first audio byte 0.16 s, 25.0 of 25 points; Voice consistency 99%, 12.1 of 13 points | 6.8% | 84% | 3.5 / 5(among the best) | 99% | 0.16 s | $0.111 |
| 10 | TTS-1OpenAI | 57 / 100. Readback accuracy 83%, 21.1 of 38 points; Word error rate 5.5%, 16.2 of 25 points; Time to first audio byte 1.12 s, 7.3 of 25 points; Voice consistency 100%, 12.5 of 13 points | 5.5% | 83% | 3.4 / 5(among the best) | 100%(among the best) | 1.12 s | $0.032(among the best) |
| 11 | TTS-1 HDOpenAI | 43 / 100. Readback accuracy 81%, 19.5 of 38 points; Word error rate 7.6%, 10.9 of 25 points; Time to first audio byte 2.09 s, 0.0 of 25 points; Voice consistency 100%, 12.5 of 13 points | 7.6% | 81% | 3.4 / 5(among the best) | 100%(among the best) | 2.09 s | $0.054(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%.
- Phonic 1 answers in 1.5 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) | 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 |
| 2= (tied) | GPT Live 1 (Sol)OpenAI | 66 / 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 | 1.4 s | 77% | 3.1 / 5 | 100%(among the best) | $0.24 |
| 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 | 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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) | Phonic 1Phonic | 60 / 100±5.4. Task completion 86%, 6.4 of 23 points; Response time 1.5 s, 18.2 of 18 points; Instruction following 4.4 / 5, 9.2 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.2 of 14 points; Tool use 59%, 2.4 of 14 points; Time to first word 2.1 s, 2.9 of 5 points; Readback accuracy 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points | 86%(among the best) | 4.4 / 5(among the best) | 59% | 1.5 s(among the best) | 2.1 s | – | 3.2 / 5 | 100%(among the best) | $0.28 |
| 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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) | 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points | 78% | 4.3 / 5 | 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) |
| 8= (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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 |
| 9= (tied) | Realtime v1 MaxElevenLabs | 48 / 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 |
| 10= (tied) | Ultravox v0.7Ultravox | 49 / 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 |
| 11= (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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 |
| 12= (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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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) |
| 13= (tied) | Realtime v1 MiniElevenLabs | 46 / 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 |
| 14= (tied) | GPT Realtime 2.1 miniOpenAI | 45 / 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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) |
| 15 | 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), 10.2 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 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.3% (field median, not measured), 3.1 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 score; hover a rank for the worst place it could hold. 36 stacks are level with the leader: their calls cannot tell them apart. Among them, 13 OpenAI GPT-6.1 Sol, 8 Meta Muse Ember 1.0, 7 OpenAI GPT-6.1 Terra, 4 Anthropic Claude Haiku 5.5 and 4 Anthropic Claude Sonnet 5.5; 19 Soniox, 14 AssemblyAI and 3 Deepgram; 14 Cartesia, 12 ElevenLabs, 7 AssemblyAI, 2 Rime and 1 Deepgram. 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: Soniox v6 + OpenAI GPT-6.1 Sol + Cartesia Sonic-3 (no response time or readback accuracy or voice consistency); 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.
905
stacks
20
calls per stack
18,950
calls scored
Every model, in every combination
13 transcribers, 11 language models and 11 voices are run in every combination with each other, beside 15 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, 15 November 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
#292of 903 stacks
54 / 100
Leader Soniox v6 + OpenAI GPT-6.1 Terra + Cartesia Sonic-3.5, 75 / 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.
#1005 of 1127 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#178 of 1127 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#85 of 1127 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 658 on the board · best 100%
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 1127 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#1114 of 1127 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 1127 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.
#313 of 810 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.
#795 of 1111 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.
#988 of 1111 on the board · best 0.3%
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.
#747 of 1116 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 1114 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.
#1 of 1116 on the board · best 1.22 s
Time to first word
How long the caller waits before the agent first speaks after pickup.
#172 of 1127 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#1 of 1127 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 82% | 1.27 s | — |
| Home services | 88% | 1.31 s | — |
| Insurance | 86% | 1.17 s | — |
| Customer support | 79% | 1.28 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 89% | 1.18 s | — |
| Spanish-accented English, city street | 84% | 1.27 s | — |
| Indian English, busy café | 88% | 1.39 s | — |
| Southern US, flustered, crying baby | 75% | 1.26 s | — |
| Fast and interrupting, construction outside | 83% | 1.12 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, Alex. Um, sorry. I got a baby crying in the background, so I'm a little flustered. My internet's been down for about two hours now.
CUSTOMERAnd I work from home, so I'm kind of stressing. There's a road crew digging up the street outside, and I'm wondering if that's got anything to do with it.
CUSTOMERI already rebooted the gateway twice and checked every cable, but the internet lights blinking orange. Can you help me out?
AGENTHey, no problem at all—I totally understand. Let's get this sorted for you. The road work could definitely be a factor, so I'll check for any outages in your area right away. Can I grab your account number or the phone number on your account so I can look you up?
CUSTOMERYeah, sure. Um, I think the account number is BW883017.
CUSTOMEROh, sorry. Last digit is one, is that enough or do you need my phone number too?
AGENTBW883017 is perfect, thanks. Let me pull up your account and check for any outages in your area.
AGENTGood news—there's no outage in your area, so it's not the road crew. Since you've already rebooted and checked the cables, let me run a line test to see what's happening with the connection from our network to your gateway.
AGENTOkay, so the signal to your gateway is good, but the gateway
CUSTOMERI.
AGENTPerfect! Your gateway just came back online. Give it about two minutes for your devices to reconnect, and you should be good to go. The orange blinking light should turn solid green once everything syncs up. You're all set—your internet should be back. Let me know if you need anything else!
CUSTOMEROkay.
CUSTOMERThe light just went solid white now.
AGENTGreat!
CUSTOMERHow long does it usually take for everything to reconnect? And since I lost two hours of work.
CUSTOMERCan I get a credit for the downtime?
CUSTOMERSorry to be a bother.
CUSTOMERI just really need to know.
AGENTNo bother at all—you're entitled to it. Devices usually reconnect within a couple minutes, so you should be fully back up shortly. And absolutely, let me apply a credit for those two hours of downtime.
AGENTDone. I've applied a $10 credit to your account BW883017 for the two hours of downtime. It'll show up on your next bill. You're all set!
CUSTOMERThank you. But I lost two hours of work.
CUSTOMERCould you maybe make it more than that?
CUSTOMERI just want to make sure it's fair, if that's possible.
AGENTI hear you, and I understand the frustration. The $10 credit is what the system allows me to apply for a two-hour outage—that's the standard for downtime credits. I don't have the ability to adjust it beyond that, but if you'd like to discuss it further, you're welcome to reach out to our billing department and they can review your account and situation. They may be able to help you out more. Is there anything else I can help with on the technical side?
CUSTOMERThat's
CUSTOMERall. I.
AGENTThat's understandable. Hope your internet's back up and running smoothly now. Take care!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERYeah. Hi.
CUSTOMERI need to reschedule my dermatology appointment next Wednesday morning.
AGENTI'd be happy to help you reschedule your dermatology appointment. To get started, I need to verify your identity. Could you please provide
CUSTOMERI. Just got scheduled for a work shift.
CUSTOMERYep. I already know how it works.
CUSTOMERI just need something after 3 p.m.. Can you check what's available?
AGENTI understand you need an afternoon slot after 3 p.m. To check availability and reschedule your appointment, I'll need to verify you first.
CUSTOMERRight, right.
CUSTOMERMy name is Nate Brooks.
CUSTOMERDate of birth? March 17th, 1948. Sorry, no. 1984.
CUSTOMERMarch 17th, 1984.
AGENTThanks, Nate. Let me verify that information. Your name is Nate Brooks and your date of birth is March 17th,
CUSTOMERGot
CUSTOMERit.
AGENTGreat!
CUSTOMERYep.
CUSTOMERYou got
AGENTPerfect. I found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 a.m. Now let me check what's available after 3 p.m. with Dr. Okafor.
CUSTOMERit.
AGENTI found one slot that works for you: Thursday at 4:10 p.m. with Dr. Okafor. That's after 3 p.m. as you requested. Would you like me to reschedule your appointment to that time?
CUSTOMERYeah. Thursday at 4:10 p.m..
AGENTPerfect. Let me reschedule your appointment to Thursday at 4:10 p.m. with Dr. Okafor.
CUSTOMERWorks. Go ahead and move it to that slot.
AGENTAll set! Your dermatology appointment has been rescheduled. Here are your details: Confirmation Code: RVB-3M8P2 - Provider: Dr. Okafor - Day: Thursday - Time: 4:10 p.m. - Location:
CUSTOMERRight.
AGENTYou're all set! Your appointment is confirmed for Thursday at 4:10 p.m. with Dr. Okafor. Your confirmation code is RVB-3M8P2. Please arrive 15 minutes early with your photo ID and insurance card. Is there anything else I can help you with?
CUSTOMERYeah. Quick
AGENTSure, what do you need?
CUSTOMERquestion. Is there any fee. For changing the appointment?
CUSTOMERIs there a fee for rescheduling?
AGENTLet me check the clinic's change policy for you.
AGENTGood news—there's no fee for rescheduling. Changes made more than 24 hours before the appointment are free. Since you made this change well in advance of your appointment, you're all set with no charge. Anything
CUSTOMERGot it.
AGENTGreat!
CUSTOMEROkay. Next.
AGENTWhat
CUSTOMERWhere should I. Park when I come
AGENTGood question. Free
CUSTOMERin?
CUSTOMERJust.
CUSTOMERYeah. Where do.
CUSTOMERPark.
AGENTYou have free patient parking in Lot C. The entrance is on River Road. Is there anything else I can help you with?
CUSTOMERGot it. That's
AGENTPerfect. You're
CUSTOMERfine. One more. Does.
CUSTOMERDoctor.
AGENTGo ahead, what's your question?
CUSTOMERDoes Doctor Okafor take Aetna insurance?
AGENTI don't have access to insurance provider information. I'd recommend calling the clinic directly
CUSTOMERRight.
AGENTIs there anything else
CUSTOMERAll right.
AGENTGreat!
CUSTOMERNo that's
AGENTPerfect. You're all set, Nate. Your dermatology appointment is confirmed for Thursday
CUSTOMEReverything. Thanks for your help. Goodbye.
CUSTOMERGot it.
AGENTYou're welcome!
AGENTThanks for calling Riverbend Health Clinic. Have a great day!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, Alex.
AGENTHi there!
CUSTOMERSorry. I'm.
AGENTNo problem, take your time. What's going on?
CUSTOMERThanks. I appreciate it.
AGENTYou're
CUSTOMERSo I got a.
AGENTGo ahead, I'm listening.
CUSTOMERSorry.
AGENTIt's okay, no rush. What's happening?
CUSTOMERAll right. Thank you. I appreciate your patience.
AGENTOf course.
CUSTOMERSo I.
AGENTI'm here whenever you're ready.
CUSTOMERSorry. I'm just. There's a lot happening here right now.
CUSTOMERSo I've got a pipe under my kitchen sink that just burst. And there's water spreading all across the floor toward a power strip.
CUSTOMERI haven't shut the water off yet.
CUSTOMERCan you help me with what I should do?
AGENTYes, absolutely—I can help. This is urgent. Here's what to do right now: First priority: shut off the water. Do you know where your main water shut-off valve is? It's usually in the basement, crawl space, or outside near the foundation. Turn it clockwise until it stops. If you can't find it quickly, look under the kitchen sink itself—there may be shut-off valves there for just that line. Second: the power strip. Keep away from it and don't touch it while it's wet. If you can safely reach the outlet it's plugged into without getting near the water, unplug it now.
CUSTOMERI.
AGENTTake your time. Are you able to shut off the water?
CUSTOMERYeah. Okay. I'm doing that right now. Just a second. All right.
AGENTGood.
CUSTOMERI think I got
AGENTYou're doing great. Did you get the water shut off?
CUSTOMERit.
CUSTOMERYeah, I think so.
AGENTExcellent.
CUSTOMERPlease tell me that's the right one.
CUSTOMERThe water stopped.
AGENTPerfect—that's
CUSTOMERAll
AGENTThat's the right one. The water has stopped, so you did it. Good work. Now, is the power strip safe? Are you away from the wet area?
CUSTOMERright.
CUSTOMERYeah, I'm staying clear
AGENTGreat. You've handled the immediate danger. Now let me get you scheduled for a repair. Can I get your phone number or street address so I can look up your account?
CUSTOMERof it. I didn't. Try to touch it or anything.
CUSTOMEROh, sure. My address is 1480 Larkspur Avenue, and my phone number is (503) 555-0139.
CUSTOMERNo, sorry. 0193.
AGENTGot
CUSTOMERIs that all
AGENTLet me look that up for you.
CUSTOMERright?
AGENTPerfect. I have you as a Copperline Care member at 1480 Larkspur Avenue, Unit 4B. Is that correct?
CUSTOMERUm, actually.
AGENTWhat
CUSTOMERSorry. I'm in
AGENTIt's okay, what is it?
CUSTOMERunit.
CUSTOMERThree.
AGENTGot it—you're in Unit 3, not 4B. I'll make sure that's correct on the service request. So 1480 Larkspur Avenue, Unit 3. Is that right?
CUSTOMERSorry. No, I'm in unit four D, not three. And not four
AGENTNo problem.
CUSTOMERB. Is that going to be
CUSTOMERa problem?
AGENTNo problem. Unit 4D—I've got that. So the correct address is 1480 Larkspur Avenue,
CUSTOMERI.
AGENTUnit 4D. That's what I'll put on the service request. No problem at all. Now, this is an emergency—a burst pipe with water spreading. Let me check what we have available and what the fee will be.
AGENTGood news—we have an emergency slot available today from 2:00 PM to 4:00 PM. Since you're a Copperline Care member, the emergency callout fee is $99. Does that work for you?
CUSTOMERUm. $99.
AGENTYes,
CUSTOMERSorry. Is
AGENTIt's okay. What's your question?
CUSTOMERthat the.
CUSTOMERI just want to make sure that's the full cost for the visit. Right. There won't be any extra charges just for
AGENTThat $99
CUSTOMERcoming out. And. Uh, can.
AGENTGood question. The $99 is the emergency callout fee—that gets the technician here today. Any parts or additional work beyond the visit itself
CUSTOMERI.
AGENTwould be quoted separately. But the $99 covers the emergency dispatch and diagnosis. Does that work for you?
CUSTOMERYeah, I think that's
AGENTGreat. Let me
CUSTOMERokay. Um.
CUSTOMERIs there.
AGENTGreat. Let me open the service request and get you booked for that 2:00 to 4:00 PM window today. Perfect. I've
AGENTopened a service request. Your ticket number is CPL-58210. Now let me book you for that 2:00 PM to 4:00 PM window today.
AGENTExcellent. You're all set. Here's what you need to know: Service Details: - Address: 1480 Larkspur Avenue, Unit 4D - Ticket Number: CPL-58210 - Arrival Window: Today, 2:00 PM to 4:00 PM - Technician: Dana - Emergency Fee: $99 (Copperline Care member rate) - Callback Number: (503) 555-0193 Dana will text you 30 minutes before arrival. Is there a gate code or any access instructions we should know about for Unit 4D?
CUSTOMERYeah. Sorry. There is
AGENTGo ahead.
CUSTOMERthe gate codes. Pound two seven.
CUSTOMERSure. So the gate code is pound 2719.
AGENTGot it.
CUSTOMERWell, Dana
AGENTPerfect. The gate code is #2719. I'll add that to your ticket. Dana will text you 30 minutes before she arrives today between 2:00 and 4:00 PM. Keep the water shut off until she gets there, and stay away from that wet power strip area. You did everything right. We'll see you soon.
CUSTOMERknow to use.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I'm at home right now.
CUSTOMERSorry. My baby's crying in the background, but I'm safe.
AGENTNo
CUSTOMERIs that okay?
AGENTYes, that's absolutely
CUSTOMEROh.
AGENTYes, that's absolutely okay—don't worry about the baby. I'm glad you're safe at home. I'm here to help you file a claim for your accident. Let me get some information from you. First, can you give me your policy number so I can pull up your account?
CUSTOMERThank you.
CUSTOMERThat's a relief.
CUSTOMERI was worried I might be making things harder.
CUSTOMERFor my policy number is NG4471903.
AGENTThank
CUSTOMEROh wait, sorry, last one is.
AGENTNo problem,
CUSTOMERSorry.
AGENTTake your time—no rush at all. What's the correct last digit of your policy number?
CUSTOMERSorry. I just want to make sure it's NG4471902. Is that coming up right on your end?
AGENTLet me verify that for you. I'll need your last name as well to pull up the policy.
CUSTOMERSure thing, it's Carter.
AGENTThank you.
CUSTOMERSorry if. I'm being a.
AGENTYou're doing great—no apologies needed. I've got your policy verified. You have a 2021 Honda CR-V, and your policy includes collision, rental reimbursement, and roadside towing coverage. Now let me get the details of what happened. When did the accident occur?
CUSTOMERThank you. That's a relief.
CUSTOMERI keep worrying, I'm messing something up.
AGENTYou're not messing
CUSTOMERUh, it happened about.
AGENTTake your time. When did it happen—do you remember the date and time?
CUSTOMERI appreciate you. Saying that.
AGENTYou're welcome.
CUSTOMERIt was just
AGENTI'm listening—whenever you're ready.
CUSTOMERabout.
CUSTOMEROkay. Sorry. I'm just trying. To get it all straight. It was about 20 minutes ago. I was stopped at a red light at Southeast fifth Avenue and Alder Street when another car hit me from behind. Nobody's hurt but the back bumper's crushed and the rear wheels rubbing.
CUSTOMERI can't drive it.
AGENTOkay, I'm so glad nobody's hurt. Let me make sure I have this right: the accident happened about 20 minutes ago at Southeast Fifth Avenue and Alder Street.
CUSTOMERI.
AGENTYou were stopped at a red light when another car hit you from behind. Your back bumper is crushed and the rear wheels are rubbing, so the car isn't safe to drive. Is that correct?
CUSTOMERYes, that's exactly right. I'm just worried about what happens next.
AGENTWe'll
CUSTOMERCan you help me with that?
AGENTAbsolutely, I can help you. First, let me get a few more details about the other car and driver. Do you have the other driver's name, their insurance company, and their license plate number?
CUSTOMERYeah. I've got all that.
AGENTGreat.
CUSTOMERThe other. Driver's name is Kevin Lund. He's insured with Pacific Shore, and the plate number is 7KXR214. That's X, like X-ray.
CUSTOMERIs that enough info?
AGENTPerfect, thank you. Did the police come to the scene, or do you have a police report number?
CUSTOMERNo.
AGENTOkay,
CUSTOMERSorry. The police. Didn't come out. So I don't have a report number.
AGENTThat's
CUSTOMERIs that going to be a problem for the claim?
AGENTNo, that's not a problem at all. We can still move forward with your claim. Let me open this up for you now.
AGENTYour claim is now open. Here's what you need to know: Your claim number is NGM-904417. Your assigned adjuster is Priya Shah, and she'll contact you within one business day. Now, since your car isn't safe to drive, let me arrange a tow for you. Where is the vehicle right now?
CUSTOMERThank you.
AGENTYou're
CUSTOMERThat's a relief.
AGENTI'm
CUSTOMERUh.
CUSTOMERSorry. I'm still here. My car's. At my house.
AGENTGot
CUSTOMERI just managed to get it home from the accident.
CUSTOMERBut I can't drive it any further.
AGENTThat
CUSTOMERWhere will the tow truck take it to?
AGENTThat's
CUSTOMERAnd, um, how much am I going to have to pay for all this?
AGENTGood questions. Let me arrange the tow first, and then I can answer your coverage questions. I'll need a callback number for the tow truck driver to reach you. What number should they call?
CUSTOMEROh, sure. Please have him call me at. (563) 227-0830. Is that okay for the tow folks?
AGENTPerfect, that works great.
AGENTNow let me arrange that tow for you.
AGENTGreat news. A tow truck from Eastside Towing is on the way to your house. They'll arrive in about 45 minutes, and they'll take your car to our partner repair shop at 9th and Morrison. The driver will call you at (563) 227-0830. As for your coverage: your collision deductible is $500. You also have towing
CUSTOMEROh $500. That's my deductible.
AGENTcoverage
AGENTYes,
CUSTOMERBut he hit me, so I should not have to pay that. Right. Is there any way around
AGENTI understand your frustration—that's
CUSTOMERit? And, um.
CUSTOMERDo I
AGENTI hear you. Here's how it works: your $500 deductible applies to your collision coverage. Now, if the other driver's insurance (Pacific Shore) is found to be at fault—which it sounds like they are, since they hit you from behind—their insurance should ultimately cover the damage and your deductible. But that's handled through the claims process between the insurers. Your adjuster, Priya Shah, will work on that with Pacific Shore's insurance. You also have rental reimbursement coverage of $40 per day for up to 30 days, starting from today when the claim opened. And your towing is covered up to 25 miles, which should get you to the repair shop. Do you have other questions?
CUSTOMERget a.
CUSTOMERThat's really helpful.
CUSTOMERThank
AGENTYou're welcome. Let me read back everything to make sure we have it all straight: Your policy number is NG4471902. Your other driver's license plate is 7KXR214. Your claim number is NGM-904417. Your adjuster is Priya Shah and she'll contact you within one business day. Eastside Towing will be at your house in about 45 minutes and will take your car to our partner repair shop at 9th and Morrison. They'll call you at (563) 227-0830. Is everything correct?
CUSTOMERyou. Uh, will my premium.
CUSTOMERYes. That's all
AGENTGood. One more thing—will my premium go up because of this accident?
CUSTOMERright. Thank you for double checking.
CUSTOMERThat's what I'm real worried about. Honestly.
CUSTOMERIs this going to raise my premium. Even though I. Wasn't at
AGENTThat's a really fair question. I don't have information about how this will affect your premium—that's something your adjuster Priya Shah can discuss with you when she calls within one business day. But since you weren't at fault, that will be part of the conversation. Is there anything else I can help you with right now?
CUSTOMERfault?
CUSTOMERNo. That covers
AGENTOkay, you're all set.
CUSTOMERit. Thank you so much
AGENTYou're very welcome.
AGENTYou did great today. The tow truck will be there soon, Priya will be in touch within one business day, and we'll take it from here. Take care of yourself and your baby.