Roark Live Bench · Suite v1.3 · Sweep of 20 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 overallAssemblyAI-STT-3.7 Realtime-Agent + GPT-6.2 Sol + Flash v2.5Level with 37 othersRoark score79 / 100Task completion91%Median response3.1 sCost per minute$0.11
- Best valueSoniox v6 + Muse Ember 1.0 + TTS-1Level with 12 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 5 othersRoark score66 / 100Task completion85%Median response2.3 sCost per minute$0.061
- Best in customer supportGrok Voice 3.0Level with 24 othersRoark score86 / 100Task completion95%Median response1.7 sCost per minute$0.083
- Best in healthcareAssemblyAI-STT-3.7 Realtime-Agent + Muse Ember 1.0 + Sonic-3.5Level with 30 othersRoark score80 / 100Task completion88%Median response2.1 sCost per minute$0.041
- Best in home servicesAssemblyAI-STT-3.7 Realtime-Agent + GPT-6.2 Sol + Sonic-3.5Level with 10 othersRoark score83 / 100Task completion96%Median response3.7 sCost per minute$0.051
- Best in insuranceUniversal-3.5 Pro + GPT-4o + Turbo v2.5Level with 28 othersRoark score76 / 100Task completion100%Median response3.2 sCost per minute$0.10
The read
- 505 of 916 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 855 of 916 on task completion; the most complete is Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD at 99%.
- The language model matters most: swapping it moves task completion by 9 points, against 7 for the transcriber and 5 for the speech engine.
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.
- Soniox v6 and AssemblyAI-STT-3.7 Realtime-Agent are level: neither leads by more than the margin of error. Of the two, Soniox v6 costs least, at $0.008 a call.
- 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% for Speechmatics Linden-1 (own VAD).
- In 587 of 1,218 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 | AssemblyAI-STT-3.7 Realtime-AgentAssemblyAI | 97 / 100. Semantic word error rate 0.6%, 68.1 of 71 points; Time to final transcript 0.86 s, 28.6 of 29 points(among the best) | 0.6%(among the best) | 0.86 s | $0.030 |
| 3 | Universal-3.6 ProAssemblyAI | 92 / 100. Semantic word error rate 0.8%, 63.7 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 |
| 4 | Nova-3Deepgram | 84 / 100. Semantic word error rate 1.1%, 55.4 of 71 points; Time to final transcript 0.88 s, 28.6 of 29 points | 1.1% | 0.88 s | $0.031 |
| 5 | Universal-3.5 ProAssemblyAI | 82 / 100. Semantic word error rate 1.1%, 53.9 of 71 points; Time to final transcript 0.90 s, 28.6 of 29 points | 1.1% | 0.90 s | $0.029 |
| 6 | Enhanced (realtime)Speechmatics | 73 / 100. Semantic word error rate 1.4%, 44.4 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points | 1.4% | 0.98 s | $0.054 |
| 7 | FluxDeepgram | 70 / 100. Semantic word error rate 1.6%, 41.4 of 71 points; Time to final transcript 0.38 s, 28.6 of 29 points | 1.6% | 0.38 s(among the best) | $0.031 |
| 8 | Nova-2Deepgram | 69 / 100. Semantic word error rate 1.6%, 40.3 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points | 1.6% | 0.89 s | $0.023 |
| 9 | Linden-1Speechmatics | 69 / 100. Semantic word error rate 1.6%, 40.2 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points | 1.6% | 0.98 s | $0.020 |
| 10 | Scribe v3 LiveElevenLabs | 67 / 100. Semantic word error rate 1.7%, 38.4 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) |
| 11 | Standard (realtime)Speechmatics | 64 / 100. Semantic word error rate 1.8%, 35.6 of 71 points; Time to final transcript 0.96 s, 28.6 of 29 points | 1.8% | 0.96 s | $0.030 |
| 12 | Linden-1 (own VAD)Speechmatics | 57 / 100. Semantic word error rate 2%, 28.2 of 71 points; Time to final transcript 0.46 s, 28.6 of 29 points | 2% | 0.46 s(among the best) | $0.020 |
| 13 | Whisper-1OpenAI | 55 / 100. Semantic word error rate 1.5%, 43.6 of 71 points; Time to final transcript 1.93 s, 10.9 of 29 points | 1.5% | 1.93 s | $0.025 |
| 14 | GPT TranscribeOpenAI | 51 / 100. Semantic word error rate 1.9%, 31.0 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-6.2 Sol, OpenAI GPT-6.1 Terra and OpenAI GPT-6.1 Sol are level: none leads by more than the margin of error. Of them, OpenAI GPT-6.1 Terra costs least, at $0.013 a call. Avoid Google Gemini 4 Neon: last on task completion (81%), instruction following (3.8 / 5) and time to first token (2.67 s).
- Anthropic Claude Haiku 4.5 starts answering in 0.36 s, Google Gemini 4 Neon in 2.67 s: 2.32 s added to every turn of the call.
- OpenAI GPT-6.2 Sol uses its tools most reliably: it handles its tools without a mistake on 86% of calls, against 42% for OpenAI GPT-5.1.
- In 378 of 1,218 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-6.2 SolOpenAI | 66 / 100. Task completion 91%, 20.3 of 36 points; Tool use 86%, 19.9 of 27 points; Instruction following 4.3 / 5, 11.8 of 18 points; Time to first token 0.87 s, 13.7 of 18 points(among the best) | 91%(among the best) | 4.3 / 5(among the best) | 86%(among the best) | 0.87 s | 67% | $0.025 |
| 2 | GPT-6.1 TerraOpenAI | 65 / 100. Task completion 90%, 19.0 of 36 points; Tool use 86%, 19.8 of 27 points; Instruction following 4.3 / 5, 11.6 of 18 points; Time to first token 0.83 s, 14.2 of 18 points(among the best) | 90% | 4.3 / 5(among the best) | 86%(among the best) | 0.83 s | 67% | $0.013 |
| 3 | GPT-6.1 SolOpenAI | 63 / 100. Task completion 92%, 22.0 of 36 points; Tool use 82%, 17.5 of 27 points; Instruction following 4.3 / 5, 11.8 of 18 points; Time to first token 1.00 s, 12.1 of 18 points(among the best) | 92%(among the best) | 4.3 / 5(among the best) | 82%(among the best) | 1.00 s | 72% | $0.018 |
| 4 | Claude Sonnet 5.5Anthropic | 57 / 100. Task completion 91%, 19.9 of 36 points; Tool use 75%, 13.6 of 27 points; Instruction following 4.2 / 5, 11.0 of 18 points; Time to first token 0.93 s, 12.9 of 18 points | 91%(among the best) | 4.2 / 5 | 75% | 0.93 s | – | $0.114 |
| 5 | Muse Ember 1.0Meta | 57 / 100. Task completion 90%, 18.4 of 36 points; Tool use 67%, 9.2 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 | 90% | 4.3 / 5(among the best) | 67% | 0.56 s | 85%(among the best) | $0.005(among the best) |
| 6 | Claude Haiku 5.5Anthropic | 56 / 100. Task completion 90%, 17.3 of 36 points; Tool use 69%, 10.2 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) | 69% | 0.63 s | – | $0.007(among the best) |
| 7 | Gemini 3.8 FlashGoogle | 49 / 100. Task completion 92%, 21.2 of 36 points; Tool use 69%, 10.4 of 27 points; Instruction following 4.3 / 5, 11.5 of 18 points; Time to first token 1.53 s, 5.7 of 18 points | 92%(among the best) | 4.3 / 5(among the best) | 69% | 1.53 s | – | $0.015 |
| 8 | GPT-4.1OpenAI | 47 / 100. Task completion 89%, 17.1 of 36 points; Tool use 52%, 1.2 of 27 points; Instruction following 4.2 / 5, 11.2 of 18 points; Time to first token 0.52 s, 18.0 of 18 points | 89% | 4.2 / 5 | 52% | 0.52 s | 82%(among the best) | $0.016 |
| 9 | Claude Haiku 4.5Anthropic | 45 / 100. Task completion 88%, 14.3 of 36 points; Tool use 52%, 0.9 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) | 52% | 0.36 s(among the best) | – | $0.052 |
| 10 | Gemini 4 HydrogenGoogle | 43 / 100. Task completion 91%, 20.9 of 36 points; Tool use 70%, 11.0 of 27 points; Instruction following 4.0 / 5, 9.4 of 18 points; Time to first token 1.88 s, 1.4 of 18 points | 91%(among the best) | 4.0 / 5 | 70% | 1.88 s | – | $0.049 |
| 11 | GPT-4o miniOpenAI | 43 / 100. Task completion 86%, 10.1 of 36 points; Tool use 56%, 3.3 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) |
| 12 | GPT-4oOpenAI | 42 / 100. Task completion 86%, 11.0 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) | – | $0.021 |
| 13 | GPT-5.1OpenAI | 40 / 100. Task completion 87%, 12.9 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 |
| 14 | Gemini 4 NeonGoogle | 20 / 100. Task completion 81%, 1.2 of 36 points; Tool use 70%, 10.7 of 27 points; Instruction following 3.8 / 5, 7.7 of 18 points; Time to first token 2.67 s, 0.0 of 18 points | 81% | 3.8 / 5 | 70% | 2.67 s | – | $0.078 |
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.
- 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 $0.052 a call. Avoid OpenAI TTS-1 HD: last on readback accuracy (81%), word error rate (7.4%) 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 1,218 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 | TTS-1AssemblyAI | 84 / 100. Readback accuracy 90%, 28.5 of 38 points; Word error rate 4.9%, 17.8 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) | 4.9% | 90%(among the best) | 3.3 / 5 | 100%(among the best) | 0.04 s(among the best) | $0.052(among the best) |
| 2 | Flux TTSDeepgram | 83 / 100. Readback accuracy 90%, 27.7 of 38 points; Word error rate 4.7%, 18.3 of 25 points; Time to first audio byte 0.13 s, 25.0 of 25 points; Voice consistency 100%, 12.3 of 13 points(among the best) | 4.7% | 90%(among the best) | 3.2 / 5 | 100%(among the best) | 0.13 s | $0.116 |
| 3 | Sonic-3.6Cartesia | 83 / 100. Readback accuracy 90%, 27.7 of 38 points; Word error rate 4.8%, 18.0 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 100%, 12.3 of 13 points(among the best) | 4.8% | 90%(among the best) | 3.4 / 5(among the best) | 100%(among the best) | 0.12 s(among the best) | $0.156 |
| 4 | Sonic-3.5Cartesia | 83 / 100. Readback accuracy 89%, 27.0 of 38 points; Word error rate 4.6%, 18.4 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) | 4.6%(among the best) | 89% | 3.3 / 5 | 100%(among the best) | 0.12 s(among the best) | $0.153 |
| 5 | v4 TurboElevenLabs | 83 / 100. Readback accuracy 89%, 27.1 of 38 points; Word error rate 4.4%, 18.9 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) | 4.4%(among the best) | 89% | 3.4 / 5(among the best) | 99% | 0.11 s(among the best) | $0.451 |
| 6 | Sonic-3Cartesia | 79 / 100. Readback accuracy 87%, 25.6 of 38 points; Word error rate 5.4%, 16.6 of 25 points; Time to first audio byte 0.16 s, 25.0 of 25 points; Voice consistency 100%, 12.3 of 13 points | 5.4% | 87% | 3.2 / 5 | 100%(among the best) | 0.16 s | $0.149 |
| 7 | Turbo v2.5ElevenLabs | 76 / 100. Readback accuracy 82%, 20.6 of 38 points; Word error rate 4.4%, 18.9 of 25 points; Time to first audio byte 0.15 s, 25.0 of 25 points; Voice consistency 99%, 11.7 of 13 points | 4.4%(among the best) | 82% | 3.2 / 5 | 99% | 0.15 s | $0.435 |
| 8 | Flash v2.5ElevenLabs | 76 / 100. Readback accuracy 82%, 20.6 of 38 points; Word error rate 4.7%, 18.2 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 99%, 12.0 of 13 points | 4.7% | 82% | 3.3 / 5 | 99% | 0.12 s(among the best) | $0.399 |
| 9 | CodaRime | 74 / 100. Readback accuracy 85%, 23.1 of 38 points; Word error rate 6.5%, 13.8 of 25 points; Time to first audio byte 0.16 s, 25.0 of 25 points; Voice consistency 99%, 12.1 of 13 points | 6.5% | 85% | 3.5 / 5(among the best) | 99% | 0.16 s | $0.107 |
| 10 | TTS-1OpenAI | 58 / 100. Readback accuracy 83%, 21.7 of 38 points; Word error rate 5.2%, 16.9 of 25 points; Time to first audio byte 1.12 s, 7.3 of 25 points; Voice consistency 100%, 12.5 of 13 points | 5.2% | 83% | 3.4 / 5(among the best) | 100%(among the best) | 1.12 s | $0.028(among the best) |
| 11 | TTS-1 HDOpenAI | 44 / 100. Readback accuracy 81%, 20.0 of 38 points; Word error rate 7.4%, 11.6 of 25 points; Time to first audio byte 2.09 s, 0.0 of 25 points; Voice consistency 100%, 12.5 of 13 points | 7.4% | 81% | 3.4 / 5(among the best) | 100%(among the best) | 2.09 s | $0.049(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 | 67 / 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), 10.3 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 5.2% (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), 10.3 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 5.2% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best) | 85% | 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), 10.3 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 5.2% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best) | 85% | 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), 10.3 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 5.2% (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) | GPT-Live 1.1 (Luna)OpenAI | 64 / 100±3.9. Task completion 86%, 6.4 of 23 points; Response time 2.3 s, 17.0 of 18 points; Instruction following 4.2 / 5, 7.8 of 14 points; Semantic word error rate 1.1% (field median, not measured), 10.3 of 14 points; Tool use 81%, 8.5 of 14 points; Time to first word 1.9 s, 3.1 of 5 points; Readback accuracy 86% (field median, not measured), 3.0 of 5 points; Word error rate 5.2% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points | 86%(among the best) | 4.2 / 5 | 81% | 2.3 s | 1.9 s | 75% | 3.2 / 5 | 100%(among the best) | $0.22 |
| 6= (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), 10.3 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 5.2% (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 |
| 7= (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), 10.3 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 5.2% (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 |
| 8= (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), 10.3 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 5.2% (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) |
| 9= (tied) | GPT Realtime 2OpenAI | 49 / 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), 10.3 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 5.2% (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 |
| 10= (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), 10.3 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 5.2% (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 |
| 11= (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), 10.3 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 5.2% (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 |
| 12= (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), 10.3 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 5.2% (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 |
| 13= (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), 10.3 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 5.2% (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) |
| 14= (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), 10.3 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 5.2% (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 |
| 15= (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), 10.3 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 5.2% (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) |
| 16 | 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), 10.3 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 5.2% (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. 38 stacks are level with the leader: their calls cannot tell them apart. Among them, 10 OpenAI GPT-6.2 Sol, 9 Meta Muse Ember 1.0, 7 OpenAI GPT-6.1 Sol, 5 OpenAI GPT-6.1 Terra, 3 Anthropic Claude Haiku 5.5, 2 Google Gemini 4 Hydrogen, 1 Anthropic Claude Sonnet 5.5 and 1 Google Gemini 3.8 Flash; 18 Soniox, 16 AssemblyAI and 4 Deepgram; 14 ElevenLabs, 12 Cartesia, 6 AssemblyAI, 4 Deepgram and 2 Rime. 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: AssemblyAI Universal-3.6 Pro + Google Gemini 4 Neon + AssemblyAI TTS-1 (no response time or readback accuracy or voice consistency); 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.
932
stacks
20
calls per stack
19,550
calls scored
Every model, in every combination
14 transcribers, 14 language models and 11 voices are run in every combination with each other, beside 16 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, 20 November 2026. Highlighted turns are the ones that affected a score. Every stack's report links to its calls.
See how your own agent compares
Roark runs the same kind of calls against your agent, on your scenarios, with the same scoring.
Rank on Roark score
#30of 929 stacks
63 / 100
Leader AssemblyAI-STT-3.7 Realtime-Agent + OpenAI GPT-6.2 Sol + ElevenLabs Flash v2.5, 79 / 100
Where it ranks
Its models
Task completion
Task completion
How much of the caller’s task the agent completed: the share of the scenario’s checks a judge model found met in the transcript, averaged over calls. Before v1.3, the share of calls judged 4 or better out of 5.
#860 of 1184 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#192 of 1184 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#94 of 1184 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 698 on the board · best 100%
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 1184 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#1040 of 1184 on the board · best 0.0%
Agent self-cutoffs
Times the agent cut its own sentence off mid-word.
#1 of 1184 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.
#315 of 825 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.
#772 of 1167 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.
#968 of 1167 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.
#744 of 1169 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 1165 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.
#29 of 1169 on the board · best 1.22 s
Time to first word
How long the caller waits before the agent first speaks after pickup.
#67 of 1184 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#79 of 1184 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 86% | 1.54 s | — |
| Home services | 86% | 1.92 s | — |
| Insurance | 87% | 1.55 s | — |
| Customer support | 91% | 1.92 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 94% | 1.76 s | — |
| Spanish-accented English, city street | 92% | 1.71 s | — |
| Indian English, busy café | 94% | 1.65 s | — |
| Southern US, flustered, crying baby | 81% | 1.83 s | — |
| Fast and interrupting, construction outside | 77% | 1.65 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, Alex, I need this fixed quick. My internet's been down for two hours now. I work from home, and there's a road crew digging up the street right outside. I already rebooted the gateway twice. Checked every cable. Still nothing. The internet lights blinking. Orange is the road crew. The problem or what?
AGENTI understand, let's
CUSTOMERLa.
AGENTI'm sorry, I cut
CUSTOMERYep.
AGENTI need your account first. Can you give me the account number, or the phone number on the account?
CUSTOMERYeah. Account number is BW883017. Sorry, the last digit is one. Or you can use the phone number I'm calling from, that's (907) 416-6703.
AGENTThanks. I've got the account, BW-883011, on the Brightwave 500 plan. Let me check for an outage at your address.
AGENTNo
CUSTOMERRight, that's the one.
CUSTOMERSo can you check if the road crew is causing this?
CUSTOMERI really need my internet backup.
AGENTI can't tell from here whether the crew cut a line. What I can see is that there's no known outage in your area, so this may be a problem on the line between your address and our network.
CUSTOMERRight.
AGENTI can't see the road crew's
CUSTOMEROkay.
CUSTOMERYeah. Got it. Already checked outside. But can you just get my connection back up?
CUSTOMERLike I said, I already rebooted the gateway twice and checked every cable. The internet lights still blinking orange.
CUSTOMERWhat's next?
AGENTSignal from the network to your gateway is good, but the gateway isn't registering.
CUSTOMERRight.
AGENTLine test shows a good signal to your gateway, but it isn't registering. I'm sending a remote reset now. Your gateway
AGENTis back online and registered. Devices can
CUSTOMERYep. Got
AGENTGood. The gateway
CUSTOMERit. I already rebooted it twice. So what else can
CUSTOMERyou do?
AGENTYour gateway, on
CUSTOMERAll right.
CUSTOMERYeah. The light just went solid white. Now, how long until my. Device is actually reconnect?
AGENTSolid white means the gateway is online. Your devices can take about two minutes to reconnect. If they're still offline after that, let me know and I'll check further. Also, I sent the remote reset twice
CUSTOMEROkay. Got
AGENTBefore you
CUSTOMERit. I lost two hours of work.
CUSTOMERCan you give me a.
CUSTOMERYeah. Need that credit for the downtime.
CUSTOMERCan you process it now?
AGENTI can apply that. Downtime credit for a two-hour outage on account BW-883011.
AGENTA $10.00 service credit has been applied to account BW-883011. It will appear on your next bill. Your gateway is online and solid white. Give your devices
CUSTOMERYeah.
CUSTOMERWait. I lost two. Hours of work. Can you make it more than
AGENTI can't change the credit amount. The downtime credit on your account is $10.00, and that's what's applied. I can't promise any larger credit from here. Your gateway is online, so your devices should reconnect within about two minutes. If they don't, tell me and I'll check further, including a technician visit if needed.
CUSTOMERthat?
CUSTOMERAll right, that works.
CUSTOMERThanks for handling it. Goodbye.
AGENTYou're welcome. To confirm: account BW-883011, gateway online, and a $10.00 credit on your next bill. Good luck with the work.
CUSTOMERYep. That's right.
CUSTOMERI'm all set. Goodbye.
AGENTGoodbye.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHey. Uh.
CUSTOMERHi, Alex.
AGENTHi
CUSTOMERSorry. There's a baby.
AGENTNo problem at all, take
CUSTOMERSorry.
CUSTOMERThank you.
AGENTNo problem at all, take your time. When you're ready, tell me what you need, and I'll need your full name and date of birth to verify your identity.
CUSTOMERI really appreciate it.
CUSTOMERSorry.
CUSTOMERIt's just a bit hectic here. Uh, my name's Wade Carter.
CUSTOMERI need to move my dermatology appointment. That's set for next Wednesday morning.
CUSTOMERBecause I just got scheduled for a work shift, then.
CUSTOMERUm, my date of birth is March 17th, 1948.
CUSTOMERSorry. No. 1984.
CUSTOMERMarch 17th, 1984.
CUSTOMERIs that okay?
AGENTThanks, Wade. Let me verify your details.
AGENTThanks, you're verified, Wade. Let me pull up your upcoming appointments.
AGENTI found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM, Main Campus, Building B. What day and time would you like to move it to? Also, let me know if you have any other constraints, like specific days or times that don't work.
CUSTOMERThanks for checking that. Sorry. I can only do after 3 p.m.. Just cause of work and childcare.
CUSTOMERIs there anything open after three?
AGENTDr. Okafor has these openings after 3 p.m.: - Tuesday at 3:45 PM
- Thursday at 410 PM
Which one works better for you?
CUSTOMERUm. Sorry.
AGENTNo
CUSTOMERActually don't work. After all.
AGENTNo problem, Wade.
CUSTOMERRight.
AGENTJust to confirm where things stand: your dermatology appointment with Dr. Okafor is still set for next Wednesday at 9:15 AM, and nothing has been changed. Would you like me to look at other options, or is there anything else I can help with?
CUSTOMERYeah. Sorry. I definitely need to move it. Uh. What about Friday?
CUSTOMERAre there any Friday options after 3 p.m. with Doctor Okafor?
AGENTThe only Friday opening Dr. Okafor has is at 11:30 AM, which is before 3 p.m., so it doesn't fit your constraint. Would you like me to check a different date range or another provider?
CUSTOMEROkay. Sorry.
CUSTOMERI really need after three.
AGENTUnderstood,
CUSTOMERThursday at 14.
AGENTThursday at 2 PM isn't one of
CUSTOMERLa.
AGENTSorry, I didn't catch that. Do you mean
CUSTOMERLa.
AGENTI'm not sure what you mean by "La." Are you asking about the Thursday 4:10 PM slot with Dr. Okafor? If so, would you like me to move your appointment there?
CUSTOMERYes.
CUSTOMERSorry.
CUSTOMERThat's what I meant.
CUSTOMERThursday at 4:10 p.m. with Doctor Okafor. Could you move my appointment to that slot, please? Is that okay?
AGENTJust to confirm before I make the change: you want to move your dermatology appointment with Dr. Okafor (currently next Wednesday at 9:15 AM) to Thursday at 4:10 PM. Shall I go ahead?
CUSTOMERYes.
CUSTOMERSorry. That's exactly right.
CUSTOMERPlease go ahead and change it to Thursday at 4:10 p.m..
CUSTOMERIs there any issue with that?
AGENTYour appointment is moved. Here are the details: - Provider: Dr. Okafor,
CUSTOMERI.
AGENTYour appointment is confirmed. - Provider: Dr. Okafor (Dermatology) - New time: Thursday at 4:10 PM - Location: Main Campus, Building B
- Confirmation codeRVB-3M8P2
- ArrivalPlease arrive 15 minutes early with your photo ID and insurance card.
Was there something you wanted to ask about? I'm happy to help.
CUSTOMERYeah. Sorry. I do have a couple questions. Uh, is. There. Any fee for changing the appointment. Like this?
AGENTChanges made more than 24 hours before the appointment are free. Changes made later than that carry a $40 fee. Since your appointment is next Wednesday, this change was made in time and there's no fee. What's your other question?
CUSTOMEROkay. Thank you. That helps.
CUSTOMERUm, where. Should I park when I come in for the appointment?
CUSTOMERI just want. To make sure I'm not going to get lost or ticketed.
AGENTFree patient parking is in Lot C, with the entrance on River Road. That should keep you from getting a ticket.
CUSTOMERAll right. That's good to know. Thank you. Uh, last thing. Does Doctor Okafor accept Aetna insurance. Sorry if that's a dumb question.
CUSTOMERI just want to make
AGENTIt's not a dumb question. I don't have information about which insurance plans Dr. Okafor accepts, and I can't confirm that from here. I'd recommend calling the clinic directly or checking with your insurance provider before your Thursday appointment. Is there anything else I can help you with?
CUSTOMERsure.
CUSTOMERNo. That covers it. Thank you. Could you just repeat the confirmation code for me once
AGENTYour
CUSTOMERmore. I want to make sure I've. Got it
CUSTOMERright.
AGENTYour confirmation code is RVB-3M8P2.
CUSTOMEROkay. Thank you. Uh. Just to be sure. That's RVB3M8.
CUSTOMERP two, right? Is that correct?
AGENTAlmost. The code is R-V-B, dash, 3-M-8-P-2. So it's RVB-3M8P2, with a dash after RVB.
CUSTOMEROkay. Got it. Thank
AGENTYou're welcome, Wade.
CUSTOMERyou. So. R.v.b
CUSTOMERde.
AGENTYes, that's right: R-V-B-3-M-8-P-2, with a dash after RVB. Is there anything else I can help you with, Wade?
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey.
AGENTHi
CUSTOMERSorry. I've got a baby crying here, and I'm a little frazzled.
CUSTOMERI need someone quick. A pipe under my kitchen sink just burst and the water spreading across the floor toward a power strip. Can you send someone out?
CUSTOMERI haven't shut the water off yet.
AGENTLet's deal with the water first. Please do these now: 1. Unplug anything near the sink, especially that power strip. Don't touch it with wet hands.
CUSTOMERI.
AGENTOkay, take
CUSTOMEROwe.
CUSTOMERAll right.
CUSTOMERI unplugged it.
CUSTOMERWhat do I do next?
AGENTGood.
CUSTOMERSorry.
CUSTOMERI just want to make sure I'm not missing anything.
AGENTYou're doing fine. Next, shut off the water. Look under the sink for the small valve on the pipe feeding the leak and turn it clockwise until it stops. If you can't find it or it won't turn, go to your main shutoff, usually near the water meter or where the main line enters the house, and turn it clockwise. Once the water is off, tell me when it's done and I'll get your details and send someone out right away.
CUSTOMEROkay. Um. Hang on. Let me check under the sink. All right. Yeah.
CUSTOMERI found the valve, and I'm turning it.
CUSTOMEROkay.
CUSTOMERIt stopped.
CUSTOMERThe water's not running anymore.
CUSTOMERSorry.
CUSTOMERIs that good?
CUSTOMERCan you send someone out now?
AGENTYes, that's good. You did it right. Stay clear of the power strip and any puddles until the floor is dry. Now I'll pull up your account. What's the phone number on your account?
CUSTOMERSure. I think it's.
CUSTOMER503.
CUSTOMER5550139.
CUSTOMERNo! Sorry.
CUSTOMER0193.
CUSTOMERIs that all right? Just want to make sure you got the right one.
AGENTNo problem at all. I have 503-555-0193. Let me look you up.
AGENTI found your account. The service address on file is 1480 Larkspur Avenue, unit 4B. Is that where the leak is?
CUSTOMERUm. Not quite. Sorry.
CUSTOMERI actually moved to unit 4D last month. It's still 1480 Larkspur Avenue, but it's 4D now. Is that going to be a problem?
AGENTNo problem at all. I'll update the unit to 4D for this visit. So the address is 1480 Larkspur Avenue, unit 4D. Is there a gate code or any access instructions I should note?
CUSTOMERYeah. There's a gate. The code is. Pound 2719. Is that enough or do y'all need anything else.
AGENTThat's enough. I'll note the gate code as #2719. Let me check the fees and availability for an emergency visit.
AGENTSince you're a Copperline Care member, the emergency callout fee is $99. The earliest window is today, 2:00 to 4:00 PM. The next option is tomorrow, 8:00 to 10:00 AM, but that's a standard visit at $79. Would you like the emergency visit today at $99? Please confirm, and I'll open the ticket.
CUSTOMERSorry.
CUSTOMERI just want to check.
CUSTOMERIs there any way someone could come before two?
CUSTOMERI've got the baby here. And all this water. If not, I guess I'll take the earliest window. But I just want to make sure.
AGENTI understand. The tools only show the 2:00 to 4:00 PM emergency window today, so that's the earliest I can book. I'm sorry I can't offer sooner. Until the technician arrives, keep the water off, stay away from the wet floor and the power strip, and if the water reaches any outlets or appliances, leave that area and call me back. Do you want me to book today's 2:00 to 4:00 PM emergency visit at $99? Please confirm.
CUSTOMERI guess that's the best I can do.
CUSTOMERPlease go ahead and. Book the 2:00 to 4:00 PM window.
CUSTOMERSorry. I just want to make sure.
CUSTOMERWho's coming out and how will I know they're on the way?
CUSTOMERCould you give me the ticket? Number two.
CUSTOMERI just want to be sure everything's set.
AGENTYou're booked. Here's your confirmation: - Ticket number: CPL-58210 - Visit:
CUSTOMERI.
CUSTOMERAll right. Thank you. That's CPL5821.
CUSTOMERI appreciate it, and I'll keep an eye out.
CUSTOMERThanks for all your help.
CUSTOMERGoodbye.
AGENTThe ticket number is CPL-58210,
AGENTnot CPL5821. Please double-check that when you talk to the technician. Your visit is booked for today, 2:00 to 4:00 PM, with technician Dana. You'll get a text at 503-555-0193 about 30 minutes before arrival. The address is 1480 Larkspur Avenue, Unit 4D, gate code #2719. The emergency fee is $99 as a Copperline Care member, payable by card or check when the work is done. Keep the water off, stay away from the wet floor and power strip, and call us back if the water reaches any outlets. Take care of your little one, and I hope the rest of your day gets easier.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I'm at home right now.
CUSTOMERI got the baby here, so it's a little loud, but I'm not hurt or anything. Sorry.
CUSTOMERIs that okay?
AGENTThat's completely okay, and no need to apologize. I'm glad you and your baby are safe at home. To get started, I'll need your auto policy number. If you can, please also give me the policyholder's last name.
CUSTOMERThank you.
AGENTYou're welcome. Whenever you're ready, please share your policy number and the policyholder's last name, and we'll get your claim started.
CUSTOMERI. Appreciate that. Uh.
CUSTOMEROkay. Um, my policy number is NG4471903.
CUSTOMERWait, sorry. Last one is two, so it's n g.
CUSTOMER4471902. Your last name is Carter?
CUSTOMERIs that all right?
AGENTThanks for clarifying. I have the policy number as NG-4471902. I'm sorry, I think you may have been asking me a question there. Is your last name Carter? If so, I'll verify the policy now.
CUSTOMERYes.
CUSTOMERThat's right. Carter.
CUSTOMERSorry if I was confusing.
CUSTOMERI just wanted to make sure you got the right info.
CUSTOMERIs that okay?
AGENTYes, that's completely okay, and you weren't confusing at all. Your policy is verified: a 2021 Honda CR-V with collision, rental reimbursement, and roadside towing coverage. Now, can you tell me when and where the accident happened?
CUSTOMERThank you.
CUSTOMERThat's a relief.
AGENTYou're
CUSTOMERThe accident happened about 20.
AGENTwelcome,
AGENTThanks. When
CUSTOMEROh.
AGENTNo problem. I just need to know a couple of things about the accident. What time did it happen, and where did it take place? For example, the street names or nearest intersection would help.
CUSTOMERRight. Sorry, I'm a little flustered.
CUSTOMERIt happened about 20 minutes ago.
CUSTOMERI was stopped at a red light at Southeast fifth Avenue and Alder Street.
CUSTOMERIs that enough?
AGENTYes, that's helpful, and there's no need to apologize. So the accident happened about 20 minutes ago at Southeast Fifth Avenue and Alder Street, while you were stopped at a red light. Next, can you tell me what happened? For example, was your car hit from behind, from the side, or something else?
CUSTOMERYeah. Thank you for checking.
CUSTOMERMy car was hit from behind, right at the back bumper. I was just sitting at the light, and the other car ran into me. Is that what you needed?
AGENTYes, that's exactly what I needed. Your car was rear-ended while stopped at the red light. Next, I need the other driver's information: their name, their insurance company, and their license plate number. If you don't have all of it, tell me what you do have.
CUSTOMEROkay. Um, I've got that here.
AGENTGreat.
CUSTOMERThe other driver's name is Kevin Lund.
CUSTOMERHe's insured with Pacific Shore.
CUSTOMERThe license plate is seven K.
CUSTOMERX, like X-ray.
CUSTOMERR.
CUSTOMER214.
CUSTOMERIs that everything you
AGENTLet me read that back to make sure I have it right. The other driver is Kevin Lund, insured with Pacific Shore, and the license plate is 7KX-R214. Is that correct? Also, I still need to know whether the police attended the scene, and if so, whether there's a report number. And is anyone injured, including you or your baby, or anyone in the other car?
CUSTOMERneed?
CUSTOMERYeah, that's all correct. And, um, no. The police didn't come, so there's no report number.
CUSTOMERNobody's hurt. Not me. Not the baby. And I don't think anybody in the other car was either. Is that all
AGENTYes, that's all I need for now. I'm opening your claim.
CUSTOMERright?
AGENTYour claim is open. Your claim number is NGM-904417, and Priya Shah has been assigned as your adjuster. She'll contact you within one business day. Let me read back the key details: policy number NG4471902, and the other driver's license plate 7KX-R214. Is your car drivable right now, or does it need to be towed from the scene? If it needs a tow, tell me where it is and the best callback number.
CUSTOMERThank
AGENTYou're
CUSTOMERyou. That
CUSTOMERhelps. No. I
AGENTYou're welcome. Before
CUSTOMERcan't.
AGENTIt sounds like you may have been cut off there. Just to confirm where things stand: your claim number is NGM-904417, and Priya Shah will contact you within one business day. Can you tell me whether your car is drivable, or whether you need a tow? If you need one, I'll also need the callback number you'd like the driver to use.
CUSTOMERSorry. I got distracted.
CUSTOMERMy car. Definitely needs. A
AGENTNo need to apologize.
CUSTOMERtow. The back bumpers
CUSTOMERcrushed.
AGENTNo need to apologize. I understand, and I'll arrange a tow. Your car is at Southeast Fifth Avenue and Alder Street. What's the best callback number for the tow driver?
CUSTOMERThank
AGENTI'm sorry, I didn't catch
CUSTOMERyou. I. Appreciate it.
CUSTOMERThe best.
AGENTYou're welcome. I still need a callback number before I can dispatch the tow. What's the best phone number for the driver to reach you at?
CUSTOMEROh, sorry.
AGENTNo problem at all.
CUSTOMERYes. Please have them call me
CUSTOMERat one.
AGENTI'm happy to have them call you, but I need the actual phone number to pass along. What's the best number to reach you at?
CUSTOMERSorry. I'm just a little frazzled.
CUSTOMERIt's (802) 727-9076. Will that work for the tow
AGENTYes, that works. I'm dispatching the tow now.
CUSTOMERdriver?
AGENTThe tow is dispatched. Eastside Towing will call you at (802) 727-9076, and they should arrive in about 45 minutes. Your car will be taken to the Northgate partner repair shop at 9th and Morrison. To recap:
- Claim numberNGM-904417
- Policy numberNG4471902
- Other driver's license plate7KX-R214
- AdjusterPriya Shah, who will contact you within one business day
Is there anything else I can help you with right now?
CUSTOMERThank you. That's a relief. Uh, I. Just. Want
AGENTYou're welcome. It
CUSTOMERto check. How much am I supposed. To
CUSTOMERpay for?
AGENTI can look up your coverage details for you. Would you like me to check your collision deductible and your rental and towing coverage now?
AGENTHere's what your policy
CUSTOMERYes,
AGENTHere's what your policy shows: - Collision deductible: $500. This is what you would typically pay toward the repair of your car. - Rental reimbursement: $40 per day for up to 30 days, starting from the day the claim was opened. - Towing: Covered up to 25 miles. The tow to the Northgate partner shop should fall within that, and your adjuster can confirm the details.
Your adjuster, Priya Shah, can go over the final repair costs and what you'd owe with you.
CUSTOMERplease.
CUSTOMERWait. But he hit. Me, so. I should not have to pay that deductible,
AGENTI understand why you'd expect that, and it's a fair question. I can't make a determination on fault or on whether the deductible applies in your case. Those decisions are made by your adjuster, Priya Shah, once she reviews the claim. When she contacts you, ask her specifically about the deductible and whether it can be recovered from the other driver's insurer, Pacific Shore. Your claim number, NGM-904417, will help her find your file. Is there anything else I can help you with right now?
CUSTOMERright?
CUSTOMERSorry. A couple
AGENTNo need to apologize. Take your time. What else would you like to ask?
CUSTOMERmore things. Will I get a rental car?
CUSTOMEROkay.
AGENTYour policy includes rental reimbursement of up to $40 per day for up to 30 days, starting from the day the claim was opened. That's reimbursement, so you'd arrange the rental yourself and be reimbursed up to that amount. I can't confirm whether a rental car will be provided directly,
CUSTOMERThank you. So, will I. Get a.
AGENTso check with Priya Shah when she contacts you.