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.
#410 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.
#616 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.
#633 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.
#486 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.
#775 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.
#568 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.
#10 of 1127 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#572 of 1127 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 87% | 3.60 s | — |
| Home services | 100% | 3.55 s | — |
| Insurance | 87% | 3.24 s | — |
| Customer support | 91% | 3.25 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 3.64 s | — |
| Spanish-accented English, city street | 77% | 3.43 s | — |
| Indian English, busy café | 98% | 3.54 s | — |
| Fast and interrupting, construction outside | 94% | 3.45 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, Alex. Uh, sorry. I'm a little flustered here. My internet's been down for about two hours now, and I work from home, so it's kind of urgent. There's a road crew digging up the street outside, so I don't know if that's related. The Gateway's internet light is blinking orange. I already rebooted it twice and checked all the cables just in case, but nothing changed. Can you check if there's an outage or something, please?
CUSTOMERHello?
AGENTI’m here—sorry for the delay.
CUSTOMEROh, no worries. I just... Uh, sorry. I get anxious when things go wrong. So, could you check if that road crew is causing the outage? And, uh, do you need my account number? I just wanna make sure we can get this fixed.
CUSTOMEROh. Hello?
AGENTI’m here, and I’m sorry for the delay. Yes—please send your account number, or the phone number on the account, so I can check for an area outage. I’ve noted that you already rebooted twice and checked the cables; we won’t repeat those steps.
CUSTOMERThank you. I appreciate that. Uh, my account number is BW883017. Oh, wait. Sorry. Last digit is one. So, BW883011. The phone number on the account should be 540-441-9967. Is that enough to pull it up? And, uh, could you let me know if that road work outside is related?
AGENTYes, that’s enough. I’ll use the corrected account number, BW883011, and check for a reported outage. I can only confirm whether the road work is related if that’s in the outage report.
CUSTOMERAll right. Thank you. Sorry. I-I just wanna make sure, are you seeing anything on your end? I really need to get back online for work, and, um, the baby's crying, so I'm a little scattered. Can you tell if it's something in the area or just my line?
AGENTThere’s no known area outage or maintenance reported, so I can’t confirm a connection to the road work. I’ll test your line now to narrow down the problem.
CUSTOMEROkay.
CUSTOMERSorry, I-
CUSTOMERSorry, I'm not sure what you mean. Could you repeat that? I just wanna make sure I'm following everything right. Is there something else I need to do?
CUSTOMERHello?
AGENTI’m here. You don’t need to do anything right now. The signal to your gateway is good, but it isn’t connecting to our network. The test recommends a remote reset from my end—that’s the next step, rather than asking you to reboot it again.
AGENTThe remote reset
CUSTOMERAll right. Okay. Go ahead with the remote reset, please. Sorry. I just wanna make sure. Will this take long? I'm really nervous about losing any more time. Can you tell me when it's done and what I should look for on the gateway?
AGENTThe remote reset is already complete, and your gateway is now registered and online. Your devices may take about two minutes to reconnect. Look for the blinking orange internet light to stop, then try opening a webpage. If it stays orange or you still can’t get online, let me know.
CUSTOMEROh, thank you. The light just went solid white, so I guess that means it's back. How long until my devices pick up the connection? Should I try reconnecting now or wait? And, um, since I lost two hours of work- Can I get a credit for the downtime on my account? Sorry if that's a bother. I just wanna make sure it's handled
AGENTYou can try now—open a webpage to confirm you’re connected. Devices may take up to two minutes after the reset to reconnect automatically. If yours hasn’t, try reconnecting to Wi-Fi. I’ve also applied a $10.00 downtime credit to account BW883011. It will appear on your next bill. No bother at all.
CUSTOMERAll right. Thanks for that. Sorry, but I lost two hours of work. Could you make it more than 10 dollars? I just wanna make sure the credit reflects what happened.
AGENTI’ve applied an additional $10.00 credit, bringing the total to $20.00 on account BW883011. Both credits will appear on your next bill.
CUSTOMERThat's really helpful. Thank you so much. I think everything's sorted now, so goodbye.
CUSTOMERHello?
AGENTI’m here—glad everything’s sorted. Thanks for choosing Brightwave, and goodbye!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey, I need to reschedule my dermatology appointment next Wednesday morning. I just got assigned a work shift then. Is there any way to move it to a time after 3:00 p.m.? I'm Nate Brooks.
AGENTI can help with that. Could you confirm your full name and date of birth so I can look up your appointment?
CUSTOMEROkay. Yeah, it's Nate Brooks. March 17th, 1948. Sorry, no, 1984. March 17th, 1984.
AGENTThank you, Nate Brooks—March 17, 1984.
CUSTOMERMm-hmm.
CUSTOMERRight. That's correct. So I can only do after 3:00 p.m. What do you have open?
AGENTDr. Okafor has Tuesday at 3:45 p.m.
CUSTOMERMm-hmm. Yeah, actually, Tuesdays don't work after all. I have to pick up my daughter. What about Friday?
AGENTFriday’s only opening with Dr. Okafor is at 11:30 a.m., so it doesn’t fit your after-3:00 p.m. requirement. Would Thursday at 4:10 p.m. work?
CUSTOMERYeah, Thursday at 4:10 p.m. works. Go ahead and book that. Quick question, do you charge a fee for rescheduling?
AGENTChanges made more than 24 hours before the appointment are free; later changes carry a $40 fee. I’ll move your appointment with Dr. Okafor to Thursday at 4:10 p.m.
CUSTOMERAll right, that's fine. Where should I park when I come in?
AGENTParking is free in Lot C, with the entrance on River Road. Your appointment with Dr. Okafor is now Thursday at 4:10 p.m. at Main Campus, Building B. Your confirmation code is RVB-3M8P2.
CUSTOMERMm-hmm. Got it. One last thing. Does Dr. Okafor accept Aetna insurance?
AGENTI don’t have access to insurance participation details, so I can’t confirm whether Dr. Okafor accepts Aetna.
CUSTOMERUh-huh.
CUSTOMEROkay. I'll check on that myself. Thanks for your help. Goodbye.
AGENTYou’re welcome, Nate.
AGENTPlease arrive 15 minutes early with your photo ID and insurance card. Goodbye!
Home services
AGENTCopperline Home Services,
CUSTOMERHi. Uh, uh
CUSTOMERHey, sor-
CUSTOMERHi. Sorry. I'm here. I-I need help real quick. I've got a pipe under my kitchen sink that just burst, and water's spreading all over the floor, heading toward a power strip. Can y'all send someone out? I haven't shut the water off yet.
AGENTYes—we can help. Stay out of the water and don’t touch the power strip, its plug, or nearby
CUSTOMEROkay. Yeah. I'm not gonna touch anything. Promise. Uh, should I try to shut the water off right now?
AGENToutlets.
AGENTYes—if you can reach the water shutoff without stepping in water or going near the power strip, turn it off now. If the valves under the sink aren’t safe to reach, use the main water shutoff instead. Don’t enter the wet area to reach either one. Is anyone hurt, and can you safely reach a shutoff from
CUSTOMERNobody's hurt. Thank goodness. I think I can get to the main shutoff without stepping in the water. Hang on. I'm doing that now. Okay. It's stopped. The water's off. So, uh, what happens next? Can y'all get somebody out here soon? I'm worried about the cost. How much is this gonna run before I agree to anything?
AGENTGood—the water is off. Keep clear of the wet floor and power strip; shutting off the water doesn’t remove the electrical hazard. The earliest emergency arrival window is today, 2–4 PM. The emergency callout fee is $149, or $99 for Copperline Care members. That’s the callout fee, not a total repair quote. I won’t book until you agree to the applicable fee. What’s your service address, including any unit number, or the phone number on your account so I can check your customer details?
CUSTOMERYeah, I understand. Sorry. Uh, my address is 1480 Larkspur Avenue, and I just moved to unit 4D last month. Not 4B. Please make sure it's 4D. My phone number is, uh, 503-555-0139. No, 0193. That's 503-555-0193. Can anybody come before 2:00? I've got a baby here and I'm real anxious about this.
AGENTI understand, especially with a baby there. Please keep both of you away from the wet area and power strip. The earliest window offered is today, 2–4 PM; I don’t have an earlier arrival available. You’re a Copperline Care member, so your emergency callout fee is $99, not including repairs. I’ll use unit 4D, not the outdated 4B, and callback 503-555-0193. Do you agree to the $99 callout fee and the 2–4 PM window? Is there a gate code or any access instruction?
CUSTOMERYeah. Okay. I'll take that window and the $99 fee if that's all you can do. The gate code is #2719. Who's coming out and how will I know they're on the way? Can I get the ticket number, please?
CUSTOMERHello?
AGENTI’m here—you’re booked. Dana will arrive today between 2 and 4 PM and text you 30 minutes before arrival. Here’s your confirmation: - Address: 1480 Larkspur Avenue, unit 4D, not 4B - Gate code: #2719 - Callback: 503-555-0193 - Ticket: CPL-58210 - Emergency callout fee: $99, not including repairs Leave the water off, and keep you and your baby away from the wet floor and
CUSTOMERAll right. That's everything, right? CPL58210. Got it. Thank you. I really appreciate it. Goodbye.
Insurance
AGENTNorthgate
CUSTOMERHey. Uh, I'm sorry. Could you repeat that? I'm a little flustered right now. Did you mean Northgate Insurance? I'm calling about an accident, so I just wanna make sure I'm talking to the right place.
AGENTYes, you’ve reached Northgate Mutual Insurance. I’m Alex, the claims intake assistant. You’re in the right place to report an accident. Are you somewhere safe, and is anyone injured? If anyone is hurt or in danger, please call 911 first.
CUSTOMERYeah. I think we're okay. Nobody's hurt, thank goodness. I'm just, uh, I'm standing next to my car, but the baby's crying inside and I'm a little stressed. My car got hit. The back bumper's crushed and I can't drive it because the rear wheel- ... could you help me figure out what to do next?
AGENTI can help you step by step. Don’t try to drive with that rear-wheel damage. Are you
CUSTOMERSorry, are you asking if I'm still at the scene? Yeah, I'm just standing next to the car, not driving anywhere. I can't move it, honestly. What do I need to do first?
AGENTFirst, are you and the baby safely away from moving traffic? If either of you is in danger, call 911 now. If you’re safe, please give me your policy number and the policyholder’s last name so I can verify the policy. We can then work on the claim and getting a tow.
CUSTOMERYeah, we're safe. We're up on the sidewalk, so that's okay. Um, my policy number is NG4471903. No, sorry. Last one is two. Carter is the last name. Is Right info
CUSTOMERHello?
CUSTOMERAre you still there?
AGENTYes, I’m still here. Thank you, Carter. I have your corrected policy number as NG4471902—ending in two. I’ll verify that now.
AGENTYour policy
CUSTOMEROkay.
CUSTOMERSorry. Was there more you needed from me right now, or do you need anything else to pull up the policy?
AGENTYour policy is verified—you don’t need to give me anything else to pull it up. Since the car can’t be driven safely, I can arrange a tow. What’s your exact location—street, nearest intersection, and city—and what phone number can the tow driver reach you on?
CUSTOMERUh, sure. I'm at Southeast Fifth Avenue and Alder Street, right in Portland. My phone number is 802-521-8062. Is that enough for the tow truck to find me?
AGENTYes—that’s enough to dispatch the tow. Eastside Towing is on the way, with an estimated arrival in 45 minutes. The listed destination is the Northgate partner repair shop at 9th and Morrison. They have your callback number if they need help finding you. For the claim, when did the accident happen, and can you tell me how your car was hit?
CUSTOMEROh, thank you. Um, I really appreciate that. The accident happened about 20 minutes ago. I was stopped at a red ... and another car just hit me from behind. The back bumper's crushed and the rear wheel's rubbing, so I can't drive it. Sorry if I'm repeating myself. Just wanna make sure that's clear. Do you need anything else about what happened?
CUSTOMERHello?
AGENTI’m here. You’ve been clear, and there’s no need to apologize. You were stopped at a red light about 20 minutes ago when another car hit you from behind. The rear bumper is crushed, and the rear wheel is rubbing, making the car unsafe to drive. Do you have the other driver’s name, insurance company, and license plate? Also, did police attend? It’s okay if you don’t have all those details.
CUSTOMERThanks for being patient, and, uh, sorry again if I sound frazzled. The other driver's name is Kevin Lund. He's insured with Pacific Shore. The license plate is 7K-X, like X-ray, R214. The police did not come out since nobody was hurt. Is that all right?
CUSTOMERHello?
AGENTI’m here. Yes—we can open the claim and note that police did not attend. I have Kevin Lund, insured with Pacific Shore, and the plate as 7K-XR214, with X as in X-ray. I’ll include those details along with the damage you described.
AGENTYour claim is open. Your claim number is NGM-904417—that’s NGM, nine-zero-four-four-one-seven. Your assigned adjuster is Priya Shah, who will contact you within one business day. Eastside Towing has also been dispatched. You don’t need to apologize—you’ve given me the information needed to open the claim. Please keep yourself and the baby safely away from traffic while you wait.
CUSTOMERThank you. I really appreciate it. Sorry, just a couple things. Do I have to pay anything out of pocket for this, like a deductible? And, uh, do I get a rental car while my car's being fixed? Also, is my premium going to go up because of this? Just want to make sure I understand everything.
CUSTOMERHello?
CUSTOMERAre you still there?
AGENTYes, I’m still here. Let me check your deductible, rental coverage, and towing coverage so I can give you accurate information.
AGENTYes. Here’s what your policy shows: - Deductible: Your collision deductible is $500. Your adjuster will need to confirm how it applies to this claim and whether it could be recovered from the other driver’s insurer. - Rental: You have rental reimbursement of up to $40 per day for up to 30 days, starting the day the claim is opened. Costs above those limits would be yours. - Towing: Your coverage includes up to 25 miles of towing. I can’t confirm whether your premium will go up—the coverage check doesn’t provide that information. Your adjuster, Priya Shah, can help direct that question to the right team.
CUSTOMEROkay, but, um, sorry, he hit me, so I shouldn't have to pay that deductible, right? Or does that come out of my pocket no matter what? And just to double-check, I can get a rental car starting today up to forty dollars a day for thirty days. Is that right? Sorry, I just want to make sure I understand. No.
AGENTYou don’t need to apologize. The $500 is your collision deductible, but I can’t confirm that it will—or won’t—come out of your pocket for this accident. Being hit from behind doesn’t let me promise it will be waived. Priya will need
AGENTto confirm how it applies and whether any deductible you pay can be recovered from the other driver’s insurer. And yes: your rental reimbursement starts today, the day we opened the claim, at up to $40 per day for up to 30 days. That’s reimbursement coverage—not a rental reservation. Before booking, confirm the arrangements with Priya so you know how payment will work.