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.
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.
#613 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.
#1101 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.
#851 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.
#1007 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.
#954 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.
#507 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.
#242 of 1127 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#386 of 1127 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 88% | 3.59 s | — |
| Home services | 85% | 3.14 s | — |
| Insurance | 89% | 3.18 s | — |
| Customer support | 96% | 3.65 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 98% | 3.06 s | — |
| Spanish-accented English, city street | 94% | 3.57 s | — |
| Indian English, busy café | 87% | 3.89 s | — |
| Fast and interrupting, construction outside | 79% | 3.50 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey. I'm sorry I'm a little flustered here.
CUSTOMERI've got a baby crying in the background, so I might talk fast. My internet's been out for about two hours now and I work from home, so it's been real stressful. There's a road crew digging up the street outside, and I wondered if that might be the cause. I've already rebooted my gateway twice and checked every cable.
CUSTOMERThe internet lights blinking orange.
CUSTOMERCan you help me figure out what's going on?
AGENTAbsolutely—I’ll keep this quick. You’ve already rebooted twice and checked the cables, so we won’t repeat those steps. The roadwork could be related, but I’ll check for a confirmed outage first. What’s your account number or the phone number on the account?
CUSTOMEROkay.
CUSTOMERThanks. I appreciate you moving fast.
CUSTOMERMy account number is BW88301. Seven.
CUSTOMEROh, sorry. Last digit is one.
CUSTOMERIs that coming up right on your end?
AGENTI have BW883011, with the final digit corrected to one. I’ll check that now.
CUSTOMERYeah, that. Should be it.
CUSTOMERSorry. Is that going to be a problem? I just want to make sure nothing gets lost.
AGENTNo problem—the corrected account number, BW883011, matched. There’s no known area outage reported. I’ll test your line now; you don’t need to repeat anything.
CUSTOMERAll right. Thank you for checking. Can you tell if that road crew could be causing this? Or do you see anything else on your end?
CUSTOMERI'm just trying to figure out what's going on, because it's been two hours, and I really need to get back online for work.
AGENTThe test shows a good signal reaching your gateway, but the gateway isn’t registered on our network. That doesn’t confirm the road crew caused this. The recommended next step is a remote reset from my end, which is different from the reboots you’ve already done. I’ll send that now.
CUSTOMERAll. Right. Go ahead and. Do the remote reset.
CUSTOMERIs there anything I need to do while you're sending that? And, uh, could you let me know what happens after?
CUSTOMERI'm just really anxious to get back online.
AGENTThe remote reset has finished, and your gateway is now registered and online. You don’t need to reboot or unplug anything—give your devices about two minutes to reconnect, then try opening a website. If you still can’t connect after that, let me know and we’ll continue from here.
CUSTOMEROkay. Ah. I see the internet. Light just went solid white now.
CUSTOMERDoes that mean it's working again?
CUSTOMERHow long should I wait before everything reconnects?
CUSTOMERI just want to make sure I don't mess anything up.
CUSTOMERAlso, since I lost two hours of work. Can I get a credit for the downtime?
AGENTYes—the solid white light, along with our check showing the gateway online, indicates service is restored.
CUSTOMERI.
AGENTGive your devices about two minutes from the reset to reconnect, then try a website. You don’t need to unplug or change anything. I also applied a $10.00 downtime credit to account BW883011. It will appear on your next bill.
CUSTOMEROkay. I appreciate you doing that, but,
CUSTOMERum. I lost two hours of work. Is
CUSTOMERthere.
CUSTOMERA.
CUSTOMERSorry. You cut off there.
CUSTOMERWhat were you about to say?
CUSTOMERCan you make the credit? More than $10?
CUSTOMERI really need some help. Since this cost me a couple hours.
AGENTSorry we got cut off.
CUSTOMERNo worries. I got it
CUSTOMERnow. Is there any way you could. Bump
CUSTOMERup the.
AGENTI understand—two hours offline when you need to work is stressful. The $10 credit is confirmed for your next bill. I don’t have a way to choose a higher amount here, and I can’t promise additional compensation. You can request a further billing review through Brightwave customer service.
CUSTOMERAll right, I'll do that if I need
AGENTUnderstood.
CUSTOMERto. Thanks for your help today. I appreciate you
CUSTOMERgetting me.
AGENTYou’re welcome. I’m glad we got your gateway back online. Take care, and I hope the rest of your workday goes more smoothly.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey, there. Um, sorry. I got a baby crying in the background, so I might sound a little flustered.
CUSTOMERI need to reschedule my dermatology appointment. That's supposed to be next Wednesday morning. I just found out I got a work shift then, and I can only do after 3 p.m. now.
CUSTOMERCan y'all help me move it?
CUSTOMERMy name's Wade Carter.
AGENTOf course, Wade Carter—we can help. I’ll keep in mind that you need a time after 3 p.m. What’s your date of birth so I can verify your record?
CUSTOMERYeah, it's March 17th, 1948.
CUSTOMERSorry. No, I said that wrong. It's actually March 17th, 1984.
CUSTOMERIs that all right?
CUSTOMERHello?
CUSTOMEROh. Thank goodness.
CUSTOMERI was.
CUSTOMERSo sorry. Was there more you needed?
CUSTOMERI just want to make sure everything's all right.
CUSTOMERDid you need anything else from me?
AGENTYes, I’m here—everything’s all right. I verified you as Wade Carter, born March 17, 1984. Your dermatology appointment is with Dr. Okafor next Wednesday at 9:15 a.m. I can offer Tuesday at 3:45 p.m. or Thursday at 4:10 p.m. Which works better for you?
CUSTOMEROh. Thanks for checking.
CUSTOMERSorry. Tuesday's actually don't work for me, after all, because I have to pick up my daughter. It's Friday. An option, maybe.
CUSTOMERIf not, I guess Thursday at 4:10 p.m. would work.
AGENTThe only Friday opening is before 3 p.m., so it won’t fit your schedule. Shall I move your appointment with Dr. Okafor to Thursday at 4:10 p.m.?
CUSTOMERYeah. That should be okay. Sorry. Is that going to be a problem?
CUSTOMERThursday at 4:10 p.m. with Doctor Okafor. Please tell me that's all right.
CUSTOMERCould you confirm if there's any fee for changing the appointment to.
AGENTThursday at 4:10 p.m. with Dr. Okafor is an available option. Changes are free if made more than 24 hours before your original appointment; otherwise, there’s a $40 fee. I haven’t moved it yet. Would you like me to go ahead under that policy?
CUSTOMERYes. Please go ahead and move it.
CUSTOMERThat should be fine. And I appreciate you checking on the
CUSTOMERfee.
CUSTOMEROkay.
AGENTYou’re all set, Wade. Your dermatology appointment with Dr. Okafor has been moved to Thursday at 4:10 p.m. Your confirmation code is RVB-3M8P2 — R, V, B, dash, 3, M, 8, P, 2. Please arrive 15 minutes early with your photo ID and insurance card.
CUSTOMERAll right. Sorry to keep asking, but just to double check.
CUSTOMERWhere should I park when I get there?
CUSTOMERAnd, um.
CUSTOMERDoes Doctor Okafor accept Aetna insurance?
CUSTOMERI just want to make sure I'm set.
AGENTNo need to apologize. Parking is free in Lot C, with the entrance on River Road. Your appointment is at Main Campus, Building B. I can’t verify whether Dr. Okafor accepts your specific Aetna plan here. Please check with the clinic’s billing team or Aetna to confirm that Dr. Okafor is in-network for your plan.
CUSTOMERThank you. I really appreciate you helping me out and answering all my questions. Bye.
AGENTYou’re very welcome, Wade. Take care, and goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey.
CUSTOMERUh, sorry. I'm a little flustered right now.
CUSTOMERI've got a pipe under my kitchen sink that just busted and water spreading across the floor.
CUSTOMERIt's getting real close to a power strip.
CUSTOMERAnd my baby's crying in the other room, so I need somebody out here as soon as possible. Can you help?
AGENTYes, I can help. First, get your baby and yourself somewhere dry, away from the kitchen. Don’t touch the power strip, its plug, or any water near it. If you can reach the water main shutoff without stepping into water or going near electrical equipment, turn it off. Otherwise, stay clear. Is anyone hurt, and has the water reached the power strip yet?
CUSTOMERThank you.
CUSTOMERI appreciate it. Um.
CUSTOMERNobody's hurt. Just shaken up.
CUSTOMERThe water's real close, but hasn't gotten to the power strip yet.
CUSTOMERI'll grab the baby and step out of the kitchen, like you said. I haven't shut the water off yet. Can you tell me real quick where the shut off might be?
CUSTOMERI'm not sure where to look, and I want to do it safely.
AGENTKeep your baby somewhere dry and safe first. Don’t try to move or unplug the power strip. The main water shutoff is often near the water meter, where the water pipe enters the house—sometimes in a basement, garage, utility closet, or outside near the foundation. Only approach it by a dry, safe route. Turn a round handle clockwise, or turn a lever a quarter-turn so it’s across the pipe. Don’t force it. There may also be valves under the sink, but don’t reach under there if water or nearby electricity makes it unsafe. If you can’t safely reach a shutoff, leave the kitchen. What’s your service address, including any unit number, and your best callback number?
CUSTOMEROkay. Thank you.
CUSTOMERThat helps a lot.
CUSTOMERI.
CUSTOMERAt 1480 Larkspur Avenue, unit four D.
CUSTOMERI actually just moved from four B to four D last month, so.
CUSTOMERPlease use four D.
CUSTOMERMy call back number is (503) 555-0139.
CUSTOMERNo.
CUSTOMERSorry. 0193. Is that all right? Hello?
AGENTI’m here. I’ve opened emergency ticket CPL-58210 for 1480 Larkspur Avenue, unit 4D, with callback 503-555-0193—using your corrections, not the old unit on file. The earliest arrival is today, 2–4 PM.
CUSTOMERI.
CUSTOMERAll right. Um, just to check.
CUSTOMERCan anybody come before 2 p.m.?
CUSTOMERThis is really urgent.
CUSTOMERI'm worried about the water spreading.
CUSTOMERIf not, I'll take the earliest emergency window. But I wanted to ask.
CUSTOMERAnd, uh, is that $99? The total? I'll pay for this visit. Or could it be more?
AGENTI understand. Today, 2–4 p.m. is the earliest emergency window available; I don’t have an earlier opening. Your Copperline Care emergency callout fee is $99—not a confirmed total for repairs. Repairs could cost more; I don’t yet have a repair estimate. Do you agree to the $99 callout fee so I can book that window? Is there a gate code or any access instruction? And have you safely stopped the water?
CUSTOMERI.
CUSTOMERYes, I.
AGENTTake your time. Were you saying yes to the $99 emergency callout fee and today’s 2–4 p.m. window? Repairs may cost extra.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes.
CUSTOMERI am safe.
CUSTOMERI am just standing next to my car by the side of the street.
AGENTIs anyone injured? If anyone is hurt or in danger, please call 911 first. If it’s safe to do so, stay away from traffic while we talk.
CUSTOMERNo. Nobody's hurt. I ran away from the traffic right now.
AGENTThank you for moving away from traffic. What’s your policy number and the policyholder’s last name?
CUSTOMERAh, yes. My policy number is n a quattro. Cuatro 719503.
CUSTOMERNo, sorry. Last one is two, and the last name is Ramirez.
AGENTThank you, Mr. or Ms. Ramirez. I have the last six digits as 719502, with your correction. Could you repeat the letters and numbers before those digits, one at a time?
CUSTOMERSure. Let me repeat.
CUSTOMERIt's n cuatro cuatro siete uno nueve dos.
CUSTOMERN like November.
CUSTOMERJ. Like golf.
CUSTOMERFour. Four. Seven. One nine. Zero. Two.
AGENTI heard N as in November, then “J like golf,” then four, four. Golf usually means G—did you mean G or J? And what digits come after those two fours?
CUSTOMEROh, sorry, I meant. G. Like golf, not J.
CUSTOMERSo after the two fours, it's.
CUSTOMEROne.
CUSTOMER902. So the whole number is.
CUSTOMERN g.
CUSTOMERFour. Four
AGENTLet me check: is the full policy number N G 4 4 1 9 0 2, under Ramirez?
CUSTOMERseven. 1902.
CUSTOMERUm, actually, after the two. Fours
AGENTAfter the two fours, is it seven, one, nine, zero, two—making the full policy number N G 4 4 7 1 9 0 2?
CUSTOMERit's. 1902. So.
CUSTOMERYes that's exactly right.
CUSTOMERCuatro cuatro 1902.
AGENTI’m hearing two different versions, so I want to get this right. Is there a seven after the two fours, or does it go straight to one, nine, zero, two?
CUSTOMERYes there is a seven after the two fours. It goes. N cuatro cuatro siete 190 dos.
AGENTYour policy is verified under Ramirez: N G 4 4 7 1 9 0 2, for a 2021 Honda CR-V. When and where did the accident happen, and what happened?
CUSTOMERUh yeah. So about 20 minutes. Ago, another car hit the back of my car while I was stopped at the red light. It happened at Southeast fifth Avenue and Alder Street. The back bumper is crushed and the rear wheel is rubbing so I can drive it.
AGENTWith the rear wheel rubbing, please don’t drive it—it may not be safe. I can arrange a tow. What city and state are you in, and what phone number can the tow driver call? Also, did you mean you can’t drive it?
CUSTOMERYes. I cannot drive it. The wheel
CUSTOMERwraps. I am in Portland, Oregon. The phone number
CUSTOMERfor.
AGENTThank you. I have your location as Southeast Fifth Avenue and Alder Street in Portland, Oregon. Please finish your callback phone number, and tell me which corner or side of the street your car is on so the tow driver can find it.
CUSTOMERAh yes, my phone number is 912.
CUSTOMER5610164. I am on the southeast corner of the intersection, right by the traffic light.
AGENTEastside Towing has been dispatched, with an estimated arrival in 45 minutes. The destination is Northgate’s partner repair shop at 9th and Morrison. Stay safely away from traffic while you wait. Do you have the other driver’s name, insurer, and license plate? Also, did police attend?
CUSTOMERYes, I have the other drivers information. His name is Kevin Lund.
CUSTOMERInsured with Pacific Shore. The license plate is seven.
CUSTOMERK x, like X-ray.
CUSTOMERR.
CUSTOMER214. And the police did not come.
AGENTI have the other driver as Kevin Lund, insured with Pacific Shore, with license plate 7 K X R 2 1 4. Police did not attend. Your claim is open. Your claim number is NGM-904417—N G M, nine zero four four one seven. Your assigned adjuster is Priya Shah, who will contact you within one business day. Is the other driver’s plate correct?
CUSTOMERYes. That's correct. The plate is.
CUSTOMERK
AGENTDid you mean the plate starts with K, without the seven, or is it still 7 K X R 2 1 4?
CUSTOMERx. Like X-ray r 214.
CUSTOMERIt starts with seven, then k.
CUSTOMERX like X-ray.
CUSTOMERR.
CUSTOMER214. So 7KX.
CUSTOMERR.
CUSTOMER214.
AGENTThank you—confirmed: 7 K X R 2 1 4. That matches the plate recorded on your claim, NGM-904417. Please stay safely away from traffic while you wait for Eastside Towing. Is there anything else you need help with?
CUSTOMERYes, I wanted to
AGENTOf course.
CUSTOMERask. How much do I have to pay for this? Is there
CUSTOMERa.
CUSTOMERSorry, could you repeat that? I did not catch what. You said.
AGENTOf course. Your policy shows: - Collision deductible: $500. This is your share of a covered collision repair. - Towing: Covered up to 25 miles. - Rental car: Up to $40 per day for up to 30 days, starting the day your claim is opened. The $500 deductible is not necessarily your total out-of-pocket cost. Your adjuster can explain how it applies to this accident.
CUSTOMERBut he hit me, so I should not have to pay that right. And will I. Get a rental car for this?
AGENTI understand—it’s frustrating when someone hits you. Your policy has a $500 collision deductible, but I can’t promise it will be waived or recovered from the other driver’s insurer. Priya, your adjuster, can explain how it applies to your claim. You do have rental coverage up to $40 a day for up to 30 days, starting today, when your claim was opened. Costs above those limits could be yours. I haven’t reserved a rental; your adjuster can help explain the arrangements.
CUSTOMERWill my premiums go up because of this accident? And where. Exactly will my car be taken after the tow?
AGENTI can’t tell from the information available whether this accident will affect your premium. Your adjuster or policy service team can help with that question. Your car is scheduled to go to Northgate’s partner repair shop at 9th and Morrison. I don’t have the shop’s name or exact street address, so please confirm those with the tow driver before they leave with your car.