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
#47of 929 stacks
61 / 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.
#898 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.
#599 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.
#1153 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.
#918 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.
#1097 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.
#738 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.
#78 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.
#256 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 | 91% | 2.17 s | — |
| Home services | 79% | 2.09 s | — |
| Insurance | 90% | 2.00 s | — |
| Customer support | 89% | 2.32 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 90% | 2.02 s | — |
| Spanish-accented English, city street | 92% | 2.48 s | — |
| Indian English, busy café | 96% | 2.18 s | — |
| Southern US, flustered, crying baby | 84% | 2.10 s | — |
| Fast and interrupting, construction outside | 73% | 1.99 s | 94% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi, Alex. Sorry.
CUSTOMERI'm a little flustered here.
CUSTOMERI got a baby crying in the background, and my internet's been down for about two hours now. I work from home, so this is a real problem.
CUSTOMERThere's a road crew digging up the street outside, and I'm worried they might have hit something.
CUSTOMERI already rebooted the gateway twice and checked every cable.
CUSTOMERBut the internet lights blinking orange.
CUSTOMERCan you help me figure out what's going on?
AGENTNo need to apologize, I'll get right on it. Can you give me your account number or the phone number on the account so I can pull it up?
CUSTOMEROh. Sure.
CUSTOMERMy account number is BW88301. Seven.
CUSTOMERSorry, the last digit is one. Is that okay?
CUSTOMEROr if you need my phone number, it's (907) 416-6728.
CUSTOMERIs that what you need?
AGENTThe caller gave BW88301 and then said "Seven" and then "the last digit is one", so the account number is BW88301 (ending in one). I'll look that up.
AGENTThe account looks up
CUSTOMERYeah.
AGENTI found your account. Next I'll check whether there's an outage at your address. No known
AGENToutage is reported for your
CUSTOMERI.
CUSTOMEROkay. Uh, are you sure?
CUSTOMERCause, like I said, there's a road crew digging up the street right now.
CUSTOMERIs it possible they messed something up that ain't been reported yet?
CUSTOMERI just want to make sure nothing's getting missed.
AGENTThe remote reset worked. Your gateway now shows as registered and online. It can take about two minutes for your devices to reconnect, so give it a moment and the light should turn solid. Your account number is BW88301, in case you need it later. Can you check whether you're back online?
CUSTOMERAll right. Uh, hang on just a sec.
CUSTOMEROkay. The light just went solid white.
CUSTOMERDoes that mean it's all set?
CUSTOMERAbout how long till my laptop and phone actually get back online?
CUSTOMERJust want to be sure I'm not doing anything wrong.
AGENTYes, a solid white light means the gateway is connected and working. You're not doing anything wrong. Your laptop and phone should reconnect on their own within
CUSTOMERAll right, that's a relief.
CUSTOMERThank you.
CUSTOMERUm.
CUSTOMERSince I lost about two hours of work while it was down. Can I get a credit for the downtime?
AGENTTwo hours of
CUSTOMERSorry.
CUSTOMERCould
AGENTNo need to apologize.
CUSTOMERyou. Yeah.
AGENTYes, I can do that. Applying the credit now. I've applied
AGENTa $10.00 service credit to account BW88301 for the two hours of downtime. It will show up on your next bill. Your laptop and phone should reconnect on their own within a couple of minutes. If either one doesn't, turn its Wi-Fi off and back on. If the light goes orange again, contact us and we can send a technician. Is there anything else I can help with?
CUSTOMERSorry. I know I'm being a pain,
AGENTYou're not being a pain at
CUSTOMERbut. Two hours of work lost is. A lot for
CUSTOMERme.
AGENTYou're not being a pain.
CUSTOMERAll right.
CUSTOMEROkay.
CUSTOMERThat's good to hear.
CUSTOMERI think that's everything I needed.
CUSTOMERThank you for your help, Alex.
CUSTOMERGoodbye.
AGENTI need to correct something. When I applied your credit, my system
AGENTran it twice, and each run returned a $10.00 confirmation. You may have been credited $20.00 instead of the $10.00 I told you about. I can't see or reverse that from here, so please check your next bill. If you see two credits, call us and we'll fix it. Your account number is BW88301, the gateway is online, and the credit is for the two hours of downtime. I'm sorry about the lost work, and I hope the rest of your day goes better. Goodbye!
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi.
CUSTOMERSorry. I've got a baby crying here. So sorry if I sound a little frazzled.
CUSTOMERUm, I need to reschedule my dermatology appointment. I've got next Wednesday morning. I just found out I got to work that shift now.
CUSTOMERCan you help me move it to a later time?
CUSTOMERI can only come after 3 p.m..
AGENTNo need to apologize, I'm happy to help. First I need to verify you. Could
CUSTOMERI.
AGENTNo worries,
CUSTOMERAll right.
AGENTTake your time.
CUSTOMERThanks.
CUSTOMEROh, I'm.
AGENTNo
CUSTOMEROh.
CUSTOMERI'm.
AGENTWhenever you're ready,
CUSTOMERSorry. Um.
AGENTNo rush at all.
CUSTOMERSorry.
AGENTNo need to be sorry at all. When you have a moment, I just need your full name and date of birth to pull up your appointment. We can go at whatever pace works for you.
CUSTOMERAll right. Thanks, I. My name's Wade Carter.
CUSTOMERMy date of birth is March 17th, 1948.
CUSTOMEROh, shoot. Sorry. No, that's not right. It's 1984.
CUSTOMERMarch 17th, 1984.
CUSTOMERIs that gonna work?
AGENTThanks, Wade. I'll use the corrected date: March 17th, 1984. Let me look you up.
CUSTOMEROkay. Thank you.
CUSTOMERJust,
AGENTTake your time, Wade.
CUSTOMERuh. Please let me know if you need anything else from me.
CUSTOMERI.
AGENTThanks, Wade, you're verified, Wade Carter, born March 17th, 1984. I found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at Main Campus, Building B. Here are Dr. Okafor's openings after 3 PM: - Tuesday at 3:45 PM - Thursday at 4:10 PM Do you want either of those? One note: the Tuesday opening may fall before your original Wednesday date, so please make sure it works for you.
CUSTOMERThanks for checking.
CUSTOMERUh. Actually, Tuesdays won't work for me, after all.
CUSTOMERI pick up my daughter. Then. Is there anything on Friday?
CUSTOMEROr. If not, is Thursday at 4:10 p.m. still available?
CUSTOMERSorry.
CUSTOMERI just want to be sure I don't mess this
AGENTYou're not messing anything up, Wade. Friday's only opening with Dr. Okafor is at 11:30 AM, which is before your 3 PM cutoff, so that one won't work. Thursday at 4:10 PM is still open. Would you like me to move your appointment from next Wednesday at 9:15 AM to Thursday at 4:10 PM?
CUSTOMERup.
CUSTOMERYeah, that sounds good.
CUSTOMERPlease move it to Thursday at 4:10 p.m..
CUSTOMERIs that all
CUSTOMERright? I just want to make sure nothing gets lost or messed
CUSTOMERup.
AGENTNothing got lost, Wade. Your appointment is moved. Here are the details: - Provider: Dr. Okafor, dermatology - New time: Thursday at 4:10 PM - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2 Please arrive 15 minutes early with your photo ID and insurance card. Is there anything else I can help you with today?
CUSTOMERYeah. Sorry.
CUSTOMERJust a couple. More quick questions. Um. Is there any kind of fee for changing my appointment like this?
AGENTGood question. Let me check the change policy.
AGENTChanges made more than 24 hours before the appointment are free. Later changes carry a $40 fee. Since your original appointment was next Wednesday and you moved it ahead of time, you shouldn't be affected by the fee. If you ever need to change the new Thursday appointment, just make sure to do it more than 24 hours beforehand. You mentioned a couple more questions. What else would you like to know?
CUSTOMEROkay. Thanks. That's a.
CUSTOMERUh. Next thing, where should I park when I come for the appointment?
CUSTOMERI always get turned around at the main campus.
AGENTThe clinic offers free patient parking in Lot C, with the entrance on River Road. I don't have more detailed directions than that, so I can't say how Lot C connects to Building B. When you arrive, signs or the front desk should be able to point you the rest of the way. Is there anything else I can help with?
CUSTOMERThat helps. Thank you. Last thing. Do you know. If Doctor Okafor takes. Aetna insurance?
AGENTTake
CUSTOMERI just want to double check
CUSTOMERbefore.
CUSTOMERSorry I
AGENTNo apology
CUSTOMERjust.
CUSTOMERSorry.
AGENTYou're doing great, Wade. I don't have any information on which insurance plans Dr. Okafor accepts, so I can't confirm whether Aetna is covered. The best way to be sure is to call your insurance company, or ask the clinic's front desk, before Thursday. Bring your insurance card to the appointment either way, since they'll ask for it at check-in. Your appointment is set for Thursday at 4:10 PM, confirmation code RVB-3M8P2. Is there anything else I can help with?
CUSTOMERJust.
CUSTOMERNo.
CUSTOMERThat covers everything I was worried about.
CUSTOMERThank you so much for your help. Really.
CUSTOMERGoodbye.
AGENTYou're very welcome, Wade. Good luck with the little one, and we'll see you Thursday at 4:10 PM. Goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHey. Um.
CUSTOMERSorry if I sound a little flustered.
CUSTOMERMy baby's crying in the background.
CUSTOMERI've got a real emergency.
CUSTOMERA pipe under my kitchen sink just burst and water is spreading across the floor toward a power strip.
CUSTOMERHey, can you send someone out, please?
AGENTNo need to apologize, let's get this handled. First, safety: 1. Stay away from that power strip and the
CUSTOMERI.
AGENTGo ahead,
CUSTOMEROkay.
AGENTI'm here. A few
CUSTOMERSorry.
AGENTYou're all right, no apology needed. Here's what I need you to do right now, one step at a time: 1. Don't touch the power strip or step in the water near it. If you can reach the breaker panel without walking through water, turn off the kitchen breakers. 2. Shut off the water. Look under the sink for the small valves on the pipes and turn them clockwise. If the water is still coming, shut off the main valve, usually where the water line enters the house, near the water heater, or by the meter. 3. Keep the baby out of the kitchen and away from the water. Can you tell me when the water is off? While you do that, what's the best phone number to reach you, or the address of the home?
CUSTOMERAll right. Uh, I'm turning the valves now.
CUSTOMEROkay. I think the water stopped.
CUSTOMERThank you for walking me through that.
CUSTOMERYeah. I'll keep the baby out of the kitchen. My address is 1480 Larkspur Avenue.
CUSTOMERUm, I moved from unit four B to 4D last month.
CUSTOMERSo it's 4D now. My phone number is (503) 555-0139.
CUSTOMER00193. Is that all you need or do you need anything else?
AGENTGlad the water's stopped. Let me pull up your account and check the earliest emergency times.
AGENTThe phone number came through with extra digits, so I'll look you up by address first.
CUSTOMEROh, sorry.
CUSTOMERDid I mess up the number?
CUSTOMERIt should just be (503) 555-0193.
CUSTOMERPlease tell me that's the right one.
CUSTOMERAnd yeah, the address is 1480 Larkspur Avenue, unit 4D. Is that coming up okay on your end?
AGENTYou
CUSTOMEROh.
CUSTOMERUm, yeah. Go ahead.
CUSTOMERSorry. I'm just a little anxious right
AGENTNo problem at all. I found your account, and I'll update it to unit 4D as you said. You're a Copperline Care member, so your emergency callout fee is $99 instead of the standard $149. The earliest emergency window is today, 2:00 PM to 4:00 PM. Do you agree to the $99 fee and that window? Your number is (503) 555-0193. Is there a gate code or any access instructions for the building?
CUSTOMERnow.
CUSTOMERYeah, that's my
AGENTThanks. I'll take that as a yes on the $99 fee and the 2:00 to 4:00 PM window. I still need to know if there's a gate code or any access instructions for the building. I'm opening your request now.
CUSTOMERnumber. 503555.
CUSTOMEROh, right. Sorry. Yeah. There's a gate
CUSTOMERcode.
AGENTYou're booked. Go ahead with the gate code whenever you're ready, and I'll add it to the ticket so Dana can get in. Here's what I have so far: - Address: 1480 Larkspur Avenue, Unit 4D - Callback number: (503) 555-0193 - Ticket number: CPL-58210 - Visit: Today, 2:00 PM to 4:00 PM, with Dana - Fee: $99 emergency callout, Copperline Care rate Dana will text you 30 minutes before arriving. Until then, keep the water off and stay clear of the power strip and the wet floor. What's the gate code?
CUSTOMERIt's pound 2719.
CUSTOMERSorry.
AGENTGot it, the gate code is pound 2719. I don't have a way to add it to the ticket now that
CUSTOMERI hope I. Said it clearly. I'm just a little flustered.
AGENTit's booked, so I'll tell you plainly: it isn't on the ticket yet. When Dana texts you 30 minutes before arriving, please reply with the gate code so they can get in without delay. Here's the final confirmation: - Address: 1480 Larkspur Avenue, Unit 4D - Gate code: #2719 (please send it to Dana by text) - Callback number: (503) 555-0193 - Ticket number: CPL-58210 - Visit: Today, 2:00 PM to 4:00 PM, with Dana - Fee: $99 emergency callout, Copperline Care rate Until Dana arrives, keep the water off, stay away from the power strip and the wet floor, and keep the baby out of the kitchen. If you see sparks or smell burning, leave the home and call 911. Is there anything else I can help with?
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah, I think so.
CUSTOMERI'm at home right now.
CUSTOMERSorry. My baby's crying in the background, so I'm a little flustered.
CUSTOMERNobody's hurt. Thankfully.
CUSTOMERIs it okay if I give you the details now?
AGENTNo need to apologize, and I'm glad everyone is okay. Take your time. A crying baby is no problem. To start, could you give me your policy number and the last name on the policy? Then we'll go through what happened.
CUSTOMEROh, thanks, I appreciate that.
CUSTOMEROkay, so my policy number is N g.
CUSTOMER4471903.
CUSTOMERWait, sorry. Last one is two.
CUSTOMERNG4471.
CUSTOMER902.
CUSTOMERAnd the last name on the policy should be Carter. Is that all right?
AGENTLet me check that corrected number. I'll use NG4471902 with the last name Carter.
AGENTThank you, Ms.
CUSTOMERYes.
AGENTThanks, Ms. Carter. I found your policy. To confirm, the policy number is NG4471902, and it covers a 2021 Honda CR-V. Is that the vehicle that was in the
CUSTOMERI.
AGENTSounds like you may be getting interrupted, which is completely fine. Take a moment if you need one. When you're ready, I'd like to start with these: 1. Was the 2021 Honda CR-V the vehicle involved in the accident? 2. When did it happen, and where? If the baby needs you first, I can wait.
CUSTOMEROh. Thank you. That's real kind. I'm okay to keep going. Just a little frazzled.
CUSTOMERYes. It was the 2021 Honda CRV. The accident happened about 20 minutes ago at the red light at Southeast fifth Avenue and Alder Street. Is that enough, or do you need anything else right now?
AGENTThat's a good start, thank you. I still need a few more things: 1. What happened? Walk me through it in your own words. 2. The other driver: their name, their insurance company, and their license plate, if you were able to get them. 3. Police: did police come to the scene, and if so, do you have a report number? 4. The car: is the CR-V drivable, or is it still at the intersection? Start with whichever is easiest.
CUSTOMERAll right. Um. So.
CUSTOMERI was stopped at the red light.
CUSTOMERJust waiting. And another car ran right into the back of mine.
CUSTOMERThe back bumper was crushed and the rear wheels rubbing, so I can't drive it.
CUSTOMERI'm at home now, but the car's parked outside, not at the intersection.
CUSTOMERThe other driver's name is Kevin Lund. He's insured with Pacific Shore.
CUSTOMERThe license plate is 7KX, like X-ray R 214. No, police came to the scene, so there's no report number. Sorry. I hope that's okay. Is there anything else you need?
AGENTYou're doing fine, Ms. Carter. Before I open the claim, I want to get two things right. The plate: I heard 7KX, then R 214. Is the full plate 7KXR214? Please correct me if I have any of it wrong. On the police, you said police came to the scene but there's no report number. I want to be sure I write that down correctly. Did police attend, and you just don't have a number yet? Since the car can't be driven, I can also arrange a tow to your home. What's the address, and what's the best phone number to reach you?
CUSTOMERSorry, I probably said that. Funny.
CUSTOMERThe plate is exactly right.
CUSTOMERSeven k.
CUSTOMERX like X-ray r 214. And actually, police did not come at all. So there's no report number. The car is already at my home, so I guess I don't need a tow to the house.
CUSTOMERBut I do need to know where it'll go for repairs.
CUSTOMERMy address is.
CUSTOMERSorry. Do you need my full address right now or just the phone number?
CUSTOMERThe best number to reach me is (856) 502-9670.
CUSTOMERIs that okay?
AGENTThat's all fine, Ms. Carter. Police did not attend, so I'll note that. The plate is 7KXR214, and I have your number as (856) 502-9670. I'll open the claim now, and I'll check your coverage at the same time so I can answer your repair and tow questions.
AGENTI'll open the claim now.
CUSTOMEROkay. Thank you. Could.
CUSTOMERYou let me know what happens next?
CUSTOMERI'm just worried about what I have to pay. And if I get a rental car.
CUSTOMERIs my premium going to go up to.
CUSTOMERAnd will you send a tow truck, or do I need to call one myself?
CUSTOMERI'm sorry.
CUSTOMERI'm just nervous about the whole process.
AGENTPlease don't apologize. These are all reasonable questions. Your claim is open, and I'll answer each one. Your claim: The claim number is NGM-904417. Your adjuster is Priya Shah, and she will contact you within one business day. She'll walk you through the repair process, including where the car will go. What you pay: Your policy has a $500 collision deductible. I can't tell you the final cost or how fault will be decided. That's something Priya can go over with you. Rental: Your policy covers a rental at $40 per day for up to 30 days, counted from the day the claim was opened, which is today. Premium: I don't have anything in your policy details about how a claim could affect your premium, so I can't say either way. Priya
CUSTOMERI.
AGENTIt sounds like you may have
CUSTOMERThank you.
AGENTYou're welcome, Ms.
CUSTOMERSorry. Yeah.
AGENTNo apology needed, Ms. Carter. Take your time. Two things are left,
AGENTand the tow was one of your questions. Tow: The car is already at your home, so you don't need a tow to get it there. Your policy covers towing up to 25 miles. When Priya tells you which repair shop the car is going to, I can arrange the tow then if you'd like. Or Priya can set it up with you. Premium: I don't have anything about premium changes in your policy information, so I can't say. Priya is the right person to ask. Recap: - Policy number: NG4471902 - Claim number: NGM-904417 - Other driver's plate: 7KXR214 - Adjuster: Priya Shah, contacting you at (856) 502-9670 within one business day Is there anything else you'd like to ask or correct before we finish?