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.
#322 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.
Not scored by this sweep.
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.
#1 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.
#1 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.
#1044 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.
#875 of 1111 on the board · best 0.3%
Text-to-Speech
Readback accuracy
Share of the codes, amounts, dates and phone numbers the agent wrote that its voice read out correctly. One wrong digit is a miss.
#432 of 934 on the board · best 100%
Word error rate
The share of the words the agent wrote that its voice dropped or changed, read back from Roark’s transcription of the recording; the same transcriber hears every voice.
#344 of 999 on the board · best 0.8%
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.
#1026 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.
#401 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.
#535 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 | 90% | 3.21 s | — |
| Home services | 95% | 3.27 s | — |
| Insurance | 87% | 3.16 s | — |
| Customer support | 95% | 3.17 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 90% | 3.16 s | — |
| Spanish-accented English, city street | 91% | 3.32 s | — |
| Indian English, busy café | 91% | 3.57 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, sorry. Everything's kind of hectic over here. My baby's fussing and I'm just trying to get this sorted. My internet's been down for about two hours now, and I work from home, so I'm getting real anxious. There's a road crew out front digging up the street, and I already rebooted the gateway twice and checked all the cables, but the internet light's just blinking orange. Could you help me out? And do you know if that road work's causing the outage?
AGENTI'm sorry you're dealing with this on top of everything else. I'll get it sorted. I need to verify your account first. Can you give me the account number, or the phone number on the account?
CUSTOMERYeah, sure, I hope this is right. My account number is B W eight eight three zero one seven—oh, sorry, last digit is one. My phone number is nine zero seven, four one six, four two nine one. Is that enough? Please tell me that's the right info. I just want to get this fixed.
AGENTI'll look up the account with both of those details.
AGENTThanks, I've found your account. Account number BW-883011... let me confirm the number I'm reading back: your account is BW8830171. Now I'll check whether there's a known outage in your area.
AGENTThere's no known outage in your area, so the road crew probably isn't the cause at the network level. Next I'll run a line test from our side to your gateway.
AGENTThe
CUSTOMERAll right, that's fine. Just please, can you double-check everything? I really need this working. And just so you know, I already rebooted the gateway twice and checked all the cables. The internet light's still blinking orange. I hope the test helps.
AGENTThanks for your patience. Here's what I've confirmed on my end: - Account: BW8830171 (Brightwave 500, gateway BX7) - No area outage or maintenance is reported, so the road work isn't showing up as a network problem. - The line test showed good signal to your gateway, but the gateway wasn't registered. - I sent a remote reset, and the gateway now reports as registered and online. Devices can take about two minutes to reconnect, so give it a little time. Your light may still show orange at first, then should turn solid. Could you check your devices in about two minutes and tell me if you're back online? If it's still down after that, I can run the line test again or schedule a technician.
CUSTOMERWait, hang on. The light just went solid white. I think it's working now, thank goodness. How long till my laptop and phone get back on? Is it just a couple minutes, or should I do anything else? I really need to get back to work. And since I lost two hours, can I get a credit for the downtime? Sorry, I just want to make sure I'm covered.
AGENTGreat news that the light is solid white. Your laptop and phone should reconnect within a couple of minutes on their own. If one doesn't, toggle Wi-Fi off and back on, or reconnect to the network. You don't need to do anything else. On the credit: I can apply a service credit for the downtime. Should I go ahead and add it to account BW8830171 for the two hours without service?
CUSTOMERYes, please, that'd be great. Sorry, I just, can you make sure it's for this account, BW883011? Honestly, I lost two hours of work. Is there any way you can make it more than just the two hours? I'd really appreciate it.
AGENTYes, I'll apply it to account BW-883011, which is the same account as BW8830171. I can only apply a credit for the documented downtime, which is the two hours you reported, so I can't make it larger than that. I'll apply the credit now.
AGENTA $10.00 service credit has been applied to account BW8830171 (BW-883011) for the two hours of downtime. It will appear on your next bill. Your gateway is back online, so you should be able to get back to work shortly. If your devices don't reconnect in a few minutes, let me know and we can run another test.
CUSTOMEROkay, thank you. I really do appreciate it. I'll keep an eye on things, and if it happens again, I'll call back. Have a good day.
AGENTYou're welcome, and I'm glad we got you back online. Good luck with work, and I hope your baby settles down soon. Have a good day!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi, yes, my name is Lucia Ramirez. I have a dermatology appointment next Wednesday morning, but I just got scheduled for a work shift at that time. I need to move the appointment please. I can only come after 3 p.m.
AGENTI can help with that, Lucia. First I need to verify your identity. Could you please confirm your date of birth?
CUSTOMERYes, it's March 17, 1948. Sorry, no, 1984. March 17, 1984.
AGENTThank you, Lucia, you're verified. Let me pull up your appointments.
AGENTI found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 a.m. at Main Campus, Building B. What day and time would you like to move it to? You mentioned after 3 p.m., so I can check Dr. Okafor's openings from Wednesday afternoon onward. Is there a specific day you'd prefer?
CUSTOMERYeah, so I can't do Tuesday after all because I have to pick up my daughter. Do you have anything Friday after 3 p.m.? If not, Thursday could work too.
AGENTI'll check Dr. Okafor's availability starting from next Wednesday.
AGENTI checked Dr. Okafor's openings, and here's what fits your constraints: - Thursday at 4:10 p.m. works, since it's after 3 p.m. - Friday has an opening at 11:30 a.m., but that's before 3 p.m., so it doesn't work for you. - Tuesday at 3:45 p.m. is available, but you said you can't do Tuesday. Would you like me to move your appointment to Thursday at 4:10 p.m.?
CUSTOMERYes, Thursday at 4:10 p.m. works for me. Please move it to that time. Before you finish, is there any fee for changing the appointment?
AGENTYour appointment is moved. Here are the details: - Provider: Dr. Okafor (dermatology) - New day and time: Thursday at 4:10 p.m. - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2. - Arrival:
CUSTOMEROkay.
CUSTOMERRight, where should I park when I arrive?
AGENTFree patient parking is in Lot C, with the entrance on River Road. Also, I should correct my last message: I cut off the arrival instructions and didn't answer your fee question. Please arrive 15 minutes early with your photo ID and insurance card. Changes made more than 24 hours before the appointment are free, so as long as you're not changing it again within 24 hours of Thursday, there's no fee.
CUSTOMERUh-huh, got it. And does Dr. Okafor accept Aetna insurance?
AGENTI'm sorry, I don't have information about which insurance plans Dr. Okafor accepts. I can only help with scheduling, clinic hours, parking, and the change and cancellation policy. Please call the clinic directly or check with your insurance provider to confirm coverage. Is there anything else I can help you with today?
CUSTOMERNo, that's all. Thank you for your help and goodbye.
AGENTYou're welcome, Lucia. Your dermatology appointment with Dr. Okafor is confirmed for Thursday at 4:10 p.m. at Main Campus, Building B, confirmation code RVB-3M8P2. Goodbye, and take care.
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi, I've got a pipe under my kitchen sink that just burst, and there's water spreading across the floor toward a power strip. I haven't shut the water off yet. Can you send someone out right away?
AGENTThis is an emergency, so let's act fast. First, please do these two things right now: 1. Shut off the water. Look under the kitchen sink for the two small valves on the supply lines (one hot, one cold) and turn them clockwise until they stop. If you can't turn them, or they don't stop the flow, shut off the main water valve for the house. 2. Keep away from the power strip and any outlets near the water. Don't touch them or walk through standing water toward them. If the power strip is already wet, switch off the breaker that feeds that area, but only if you can reach the panel without stepping in water. Let me know once the water is off, and tell me whether anyone is hurt or in immediate danger. In the meantime, I'll pull up your account so we can get a technician out to you. What phone number is on your account, or what's the service address?
CUSTOMERThe service address is 1480 Larkspur Avenue, and the phone number is 503-555-0139, no 0193. The water is now off, and no one is hurt or in any immediate danger.
AGENTThank you, I'm glad the water is off and no one is hurt. I'll look up your account using the corrected number.
AGENTI found your account. The service address is 1480 Larkspur Avenue, unit 4B. Before I open the ticket, do you have a gate code or any access instructions for the building?
CUSTOMERYes, I moved to unit 4D last month, not 4B. The gate code is pound two seven one nine.
AGENTThanks for the correction. I'll use unit 4D, and the gate code is #2719. I'll check the fees and availability for an emergency visit now.
CUSTOMERRight. Can you tell me how much the visit will cost before I agree to it? And is there any way someone can come before 2 p.m.?
AGENTI'll check availability and the fees that apply to your account now.
AGENTHere's what I have: - Earliest emergency window: today, 2:00 PM to 4:00 PM. That's the earliest the system offers, so I can't get anyone in before 2 p.m. - Fee for your account: you're a Copperline Care member, so the emergency callout fee is $99. The standard callout is $149 for non-members, and $79 is the standard visit fee. Payment is by card or check on completion. Would you like me to open an emergency ticket and book the 2:00 to 4:00 PM window at the $99 emergency fee? Please confirm yes or no.
CUSTOMERYes, go ahead and open the emergency ticket for the 2 to 4 p.m. window at the $99 fee. Who will be coming, and how will I know they're on the way? Also, can you give me the ticket number?
AGENTYour emergency visit is booked. - Ticket number: CPL-58210 - Visit window: today, 2:00 PM to 4:00 PM - Technician: Dana - Fee: $99 (Copperline Care member emergency callout), payable by card or check on completion. - Service address: 1480 Larkspur Avenue, Unit 4D. - Gate code: #2719. - Callback number: 503-555-0139. Dana will text the callback number 30 minutes before arrival, so you'll know they're on the way. Until then, keep the water shut off and stay clear of the wet area and the power strip. If the water spreads or you notice anything unsafe, like sparking or a burning smell, call 911 first and then us. Is there anything else I can help with?
CUSTOMERNo, that covers everything. Thanks for your help, Alex. Goodbye.
AGENTYou're welcome. Dana will be in touch before arrival. Goodbye.
Insurance
AGENTNorthgate Mutual
CUSTOMERHey, sorry, could you tell me what you mean by Northgate? Are you asking about a location, or is there something specific you need help with?
AGENTNo, not a location. Northgate Mutual Insurance is the company I work for, and I'm Alex, the claims intake assistant. I help people report auto accidents and open claims. Before anything else, I need to ask: is everyone safe right now? Is anyone hurt or in danger? If so, please call 911 first. If you're safe and need to report an accident, I can help. I'll start by verifying your policy. Do you have your policy number handy, and your last name?
CUSTOMERYeah, everybody's okay. Nobody's hurt, thank goodness. Sorry, I'm a little flustered. I've got a baby crying here. My policy number is NG4471903. Oh, wait, sorry. The last one is two. Carter, that's C-A-R-T-E-R. Is that all right?
AGENTThanks, I'm glad everyone is okay. Take your time. I've noted the policy number as NG4471902, with the last name Carter. Let me verify that now.
AGENTThank you, your policy is verified. It covers a 2021 Honda CR-V with collision, rental reimbursement, and roadside towing. Now, when and where did the accident happen?
CUSTOMERYeah, so it happened about 20 minutes ago. We stopped at a red light at Southeast Fifth Avenue and Alder Street. Are you able to find that okay?
AGENTYes, I have that: Southeast Fifth Avenue and Alder Street, about 20 minutes ago. Can you tell me what happened? For example, did the other car hit you from behind, or was there another impact?
CUSTOMERYeah, um, the other car hit me from behind. I was just sitting at the light, and he ran right into my back bumper. Sorry, it's pretty bad. The bumper's crushed and the rear wheel is rubbing, so I can't drive it. Is that enough detail?
AGENTYes, that's helpful, and I'm sorry you're dealing with this. Since the rear wheel is rubbing and the car isn't safe to drive, I'll arrange a tow. I'll also need the other driver's name, insurer, and license plate, and whether police attended. First, can you confirm the location where the car is now, and a callback phone number for the tow driver?
CUSTOMEROh, yeah, so the car is still right here at Southeast Fifth Avenue and Alder Street, same spot as the accident. My phone number is 907-416-6664. Is that okay for the tow? And police did not come out.
AGENTYes, that works. I'll dispatch the tow now.
AGENTThe tow is dispatched. Eastside Towing is on the way, with an estimated arrival of about 45 minutes. They'll take your car to the Northgate partner repair shop at 9th and Morrison. I've noted that police did not attend. Now I need the other driver's details: his name, his insurance company, and his license plate number.
CUSTOMEROkay, the other driver is Kevin Lund. His insurance is Pacific Shore. The license plate is 7KX, like X-ray, R214. Is that all you need?
AGENTI have Kevin Lund, insurer Pacific Shore, and license plate 7KX-R214. Let me read that back to make sure I have it right: the plate is 7-K-X-R-2-1-4. Is that correct? Once you confirm, I'll open the claim. Is there anything else you can tell me about the accident, such as any damage to the other car or anything you noticed about how it happened?
CUSTOMERYeah, that's right. 7K X like X-ray R 2 1 4. Um, I didn't really see much damage on his car. He just got out, looked at it, and said he was sorry. He hit me pretty hard, but I couldn't really tell about his bumper. I was just focused on my car and making sure the baby was okay. Is that enough?
AGENTYes, that's enough, and it's completely understandable that you were focused on your baby. I'll open the claim now.
AGENTYour claim is open. Here are the details I'm reading back: - Policy number: NG4471902 - Other driver's license plate: 7KX-R214 - Claim number: NGM-904417. - Adjuster: Priya Shah, who will contact you within one business day. Tow is on the way from Eastside Towing, arriving in about 45 minutes. Please stay somewhere safe with your baby while you wait. Would you like me to check your coverage for the rental reimbursement and towing details, so you know what's available while your car is in the shop?
CUSTOMEROh, yes, please, if you could. I'm worried about the cost. Do I have to pay anything out of pocket, like a deductible? And since he hit me, I shouldn't have to pay that, right? Also, will I get a rental car while mine's being fixed? And is my premium going to go up from this? Sorry for all the questions. I just want to make sure I understand everything.
AGENTOf course, these are good questions. I'll look up your coverage now.
AGENTHere's what your policy shows: - Collision deductible: $500. This is what you'd normally pay toward repairs under the collision coverage. I can't tell you whether it will apply to this claim or whether it can be recovered from the other driver's insurer. That will be up to your adjuster, Priya Shah, once she reviews the claim. Since the other driver hit you, it's a good question to raise with her. - Rental reimbursement: $40 per day for up to 30 days, starting from the day the claim was opened. That's a reimbursement, so you'd arrange and pay for the rental first, then be reimbursed up to that limit. - Towing: covered up to 25 miles. The tow to the partner shop at 9th and Morrison is the one dispatched today. Please check with your adjuster whether any distance beyond 25 miles would be covered. I can't tell you whether your premium will go up. That depends on underwriting decisions, so please ask your adjuster or your agent about that. Your adjuster, Priya Shah, will contact you within one business day to go over next steps, including the deductible question and the rental. Is there anything else I can help you with right now?
CUSTOMERWell, I think that's everything. Thank you for explaining all that. I really appreciate it. And could you just repeat the claim number one more time? I want to make sure I have it right before I go.
AGENTYour claim number is NGM-904417. Your adjuster is Priya Shah, and she'll contact you within one business day. Take care of yourself and your baby.