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
#18of 929 stacks
65 / 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.
#904 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.
#645 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.
#1019 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.
#920 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.
#857 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.
#1027 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.
#125 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.
#797 of 1184 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#168 of 1184 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 92% | 2.40 s | — |
| Home services | 91% | 2.44 s | — |
| Insurance | 73% | 2.26 s | — |
| Customer support | 91% | 2.31 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 91% | 2.27 s | — |
| Spanish-accented English, city street | 83% | 2.39 s | — |
| Indian English, busy café | 92% | 2.46 s | — |
| Southern US, flustered, crying baby | 94% | 2.34 s | — |
| Fast and interrupting, construction outside | 74% | 2.19 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey. Yeah. I'm working from home, and my Internet's been down for two hours now. There's a road crew digging right outside my place. I already rebooted the gateway twice and checked all the cables. Still nothing. The Internet light's blinking orange. Can you check if it's related to the roadwork?
CUSTOMERMy account number is b w eight eight three zero one seven... oh, sorry. Last digit is one.
AGENTThanks. I'll pull up the account with BW8830171 and check for an outage there.
CUSTOMERRight. Go ahead.
CUSTOMERwanna get this fixed as fast as possible.
AGENTI also still need to run that outage check, so I'll do it now.
CUSTOMEROkay.
AGENTHere's where things stand on account BW-883011:
CUSTOMERGot it.
AGENTYour
CUSTOMERYep. That's right. Go ahead.
AGENTMy last two messages got cut off, so here's the full picture for account BW-883011. What I found: - There's no known outage or maintenance in your area, so the roadwork isn't showing up as a cause
CUSTOMERGot it.
CUSTOMERYeah. Got it. So the roadwork isn't listed, but that's what's going on right outside. The Internet light's still blinking orange, and I've already rebooted everything twice and checked the cable, so it's not that. What can you do on your end to get me back up?
AGENTI'm sorry my last few messages got cut off. Here's where things stand on account BW-883011. - Outage: None is listed for your area, but that only means nothing has been reported. It doesn't rule out the crew outside
CUSTOMERRight.
AGENTMy replies keep getting cut off, so I'll keep this short. The remote reset went through, and the system shows your gateway as registered
CUSTOMEROkay.
AGENTI want to get you a clear answer. For account BW-883011, I ran the line test and it showed good signal to your gateway, but the gateway wasn't registered. I
CUSTOMERMhmm.
AGENTI'll keep
CUSTOMERAlright.
AGENTHere's
CUSTOMERGo ahead.
AGENTSorry
CUSTOMERYep. I'm here.
AGENTThanks
CUSTOMERThat's fine. Just wanna get this sorted.
CUSTOMERGo ahead.
AGENTSorry about the cut-off messages. Here's the short version for account BW-883011. What I found: - The line test showed good signal to your gateway, but the gateway wasn't registered. - I sent a remote reset, and the system now shows the gateway as registered and online. It can take about two minutes for devices to reconnect. - There's no known outage or maintenance in
CUSTOMERRight.
AGENTSorry
CUSTOMEROkay. The
CUSTOMERNo problem.
CUSTOMERSo the light on my gateway just went solid white now. How long until my devices should reconnect?
CUSTOMERSince I've been down for two hours, can you credit my account for the downtime?
AGENTA solid white light means the gateway is back online, so the reset worked. Devices usually
CUSTOMERGot it.
CUSTOMERYep. Makes sense. About how long until everything reconnects?
CUSTOMERAnd what about that credit for the two hours I lost?
AGENTYour devices should reconnect within about two minutes of the reset. The solid white light means the gateway is back online. If a laptop or phone doesn't pick it up, toggle its Wi-Fi off and on. The credit is done: a $10.00 service credit went onto account BW-883011 for the two hours of downtime, and it will show on your next bill. I also need to correct something from earlier. I read your account number back as
CUSTOMERGot it.
AGENTThe correction
CUSTOMERI want to --
CUSTOMERI lost two hours of work. Can you make it more than ten dollars?
AGENTI understand, two hours of lost work is frustrating. I can't change the amount, though. The credit tool applies a fixed amount, which
CUSTOMERAlright. If that's all you can do, just wanted to check. Thanks for your help. Goodbye.
AGENTHere's the correction I kept getting cut off on. You gave me BW8830171, but the account the system found, and the one I fixed and credited, is BW-883011. The lookup didn't match what you said, and I should have flagged that right away instead of going ahead. Please check that BW-883011 is your account. If it isn't, contact us so the reset and the $10.00 credit can be sorted out. Your gateway is registered and online, and the $10.00
CUSTOMERGot it.
AGENTThanks for your patience, and sorry again for the cut-off
AGENTmessages. Your gateway is back online, and the $10.00 credit on account BW-883011 will show on your next bill. If the Internet light goes back to orange or the connection drops again, contact us and we'll send a technician. Take care, and good luck catching up on your work.
Healthcare
AGENTRiverbend Health Clinic, this is Alex. How can I help you today?
CUSTOMERHi. Uh, this is Lucia Ramirez.
CUSTOMERhave a dermatology appointment next Wednesday morning, but I need to move it because I just got scheduled for work then. Can you help me reschedule it?
CUSTOMERI can only come after three PM.
AGENTI can help with that, Lucia. First I need to verify your identity. Could you give me your full name and your date of birth?
CUSTOMERSure.
CUSTOMERMy full name is Lucia Ramirez. My date of birth is March seventeen nineteen forty
CUSTOMERSorry. No.
AGENTNo problem, take your time. What is your correct date of birth?
CUSTOMERRight. It's March seventeen nineteen eighty four.
AGENTThank you. Let me verify that.
AGENTThanks, Lucia, you're verified. Let me pull up your appointments.
AGENTI found it: your dermatology appointment with Dr. Okafor, next Wednesday at 9:15 AM at Main Campus, Building B. Let me check what's open after 3 PM.
AGENTHere are Dr. Okafor's openings that are after 3 PM: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. There's nothing open after 3 PM on Wednesday itself. Would either of those work for you?
CUSTOMERActually, Tuesdays don't work after all because I pick up my daughter.
CUSTOMERWhat about Friday?
CUSTOMERIs there anything available then?
AGENTDr. Okafor's only Friday opening is 11:30 AM, which is before your 3 PM cutoff, so I can't offer it. The only slot that fits everything is Thursday at 4:10 PM. Would you like me to move your appointment to Thursday at 4:10 PM, or would you rather I check another provider or later dates?
CUSTOMERThursday at four ten PM works for me. Yes.
CUSTOMERPlease move my appointment to that time. And before we finish, is there a fee for changing the appointment?
AGENTI'll make the change and check the fee policy.
AGENTSince your appointment is next week, this change is more than 24 hours out, so there's no fee. Now I'll move it.
CUSTOMEROkay. That's good to know. And where should I park for the appointment?
AGENTPatient parking is free in Lot C, and the entrance is on River Road. Is there anything else I can help you with today?
CUSTOMERYeah. One more thing. Does doctor Okafor accept Aetna insurance?
AGENTI'm sorry, Lucia, but I don't have information on which insurance plans Dr. Okafor accepts, and I don't want to guess. Please call your Aetna plan or our billing office to confirm coverage before your visit. Also, bring your insurance card on Thursday, since you'll need it at check-in anyway. Is there anything else I can help you with?
CUSTOMERNo. That's all. Would you read back the new appointment time and give me the confirmation code, please?
AGENTYour dermatology appointment with Dr. Okafor is now Thursday at 4:10 PM at Main Campus, Building B. Your confirmation code is RVB-3M8P2. That's R-V-B, 3, M, 8, P, 2. Please arrive 15 minutes early with your photo ID and insurance card. Thanks for calling Riverbend Health Clinic, Lucia, and take care!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERHi. Uh, I need help right away. The pipe under my kitchen sink just burst, and water is spreading across the floor. It's heading toward a power strip. I haven't shut the water off yet. What should I do?
AGENTStay away from that power strip and don't step into the water near it. If you can reach the breaker panel without walking through standing water, switch off the kitchen circuits, or the main breaker if you're not sure which is which. Next, shut off the water. Look for the shutoff valve under the sink and turn it clockwise. If you can't reach it safely or it won't turn, shut off the main water valve. It's usually where the water line enters the house, near the water heater, or by the meter outside. Turn it clockwise until it stops. Is anyone hurt, and were you able to get the water off?
CUSTOMERNo. Nobody's hurt. I just shut off the water, and it stopped now. So can you send someone to fix the pipe?
CUSTOMERAnd how much will the visit cost?
AGENTGood, that was the right move. I'll pull up your account and check what we have available. Can you give me the phone number or street address on the account?
CUSTOMERYeah. Sure. The address is fifteen Ovechanta, Larkspur Avenue, and my phone number is No.
AGENTThe address and
CUSTOMERHello?
AGENTSorry
CUSTOMERYeah. The address
CUSTOMERNo problem.
CUSTOMERThe address is four tenobe Ochenta Larkspur Avenue, and my phone number is
AGENTSorry about the delay. Let me make sure I have this right. Is the address 1480 Larkspur Avenue? And can you give me your phone number again? The line cut out before I caught it.
CUSTOMERYes. That's right.
CUSTOMERfourteen eighty Larkspur Avenue. My phone number is five zero three five five five zero one nine three.
AGENTThanks. I'll check the phone number against the account and see what times are open for an emergency visit.
AGENTI'll also
CUSTOMEROkay. Alright. Mhmm. Go ahead.
AGENTI found your account, and it matches both the address and the phone number. You're a Copperline Care member, so the emergency callout fee for you is $99 instead of the standard $149. The earliest emergency window is today, 2:00 PM to 4:00 PM. Does that work, and are you okay with the $99 fee? I have 1480 Larkspur Avenue, unit 4B on file. Is that still right? Is there a gate code or any access
CUSTOMERIs it possible for anyone to come before two? The water is
CUSTOMERYeah. That's fine. I'm okay with the ninety nine dollars fee. So just let me know if someone can come before two. If not, I'll take the two PM to four PM window.
CUSTOMERwill be coming and how will I know when they're on the way?
AGENTI checked, and 2:00 PM to 4:00 PM today is the earliest emergency window we have, so nothing earlier is open. I don't have a technician name or a way to send arrival alerts, so I can't promise either. I'll put your callback number on the ticket so the team can reach you. Before I book, I need to confirm a few things. Is the address still 1480 Larkspur Avenue, unit 4B? Is there a gate code or any special access instructions? Is 503-555-0193 the best number to reach you?
CUSTOMERActually, I moved last month.
CUSTOMERfrom unit four b to unit four d.
CUSTOMERit's one four eight zero Larkspur Avenue, unit four d now. For the gate, the code is pound two seven one nine. And, yes, five zero three five five five zero one nine three is the best number to reach me.
AGENTThanks, I'll use unit 4D instead of 4B. Opening the ticket now.
CUSTOMEROkay. Could you let me know the ticket number when it's ready?
AGENTYou're booked. Your ticket number is CPL-58210. - Visit: today, 2:00 PM to 4:00 PM, emergency callout at the $99 Copperline Care rate - Address: 1480 Larkspur Avenue, Unit 4D - Gate code: #2719 - Callback number: 503-555-0193 - Technician: Dana. You'll get a text at that number about 30 minutes before arrival. Earlier I said I couldn't promise a technician name or arrival alerts. The booking has now confirmed both, so that's correct. Until Dana arrives, keep the water off and stay clear of the power strip and any wet areas near outlets. If you can, put a bucket under the pipe and mop up the standing water. If anything changes, like sparking, a burning smell, or water coming back, call us right away. Is there anything else I can help with?
CUSTOMERNo. That's everything I needed. Thank you for your help. Goodbye.
AGENTYou're welcome.
AGENTDana will see you this afternoon between 2:00 and 4:00. Stay safe, and goodbye.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYes. I'm safe.
CUSTOMERI'm standing next to my car, but I really need to get this handled quickly. There's construction right outside, and my car got hit about twenty minutes ago at Southeast Fifth Avenue and Alder Street. The back bumper's crushed. The rear wheel rubs, so I can't drive it. Nobody's hurt, but I need to start a claim. Can you help?
AGENTI'm glad you're safe, and yes, I can help with the claim and with getting a tow. To verify your policy, I need your policy number and your last name.
CUSTOMERLet's do this fast.
CUSTOMERPolicy number is n g four four seven one nine zero three. Oh, sorry. Last one is two. Brooks for the last name.
AGENTThe corrected policy number is NG44719032,
CUSTOMERRight.
CUSTOMERYep. n g four four seven one nine zero two.
CUSTOMERRight.
AGENTBoth numbers came back verified, and I can't be sure which one is yours,
CUSTOMERYeah.
CUSTOMERIt's n g four four seven one nine zero two n g four four seven one nine zero two. That's the correct one. Can you pull it up and keep going? I need to move fast here.
AGENTI
AGENTGot it. I'll use NG44719002, ending in zero-zero-two, and I'm sorry for the mix-up earlier. Next I'm checking your coverage and sending a tow, since the rear wheel is rubbing and the car isn't safe to drive. I need two things from you for the tow:
CUSTOMERYeah.
CUSTOMEROkay. Go ahead.
CUSTOMERWhat do you need for the tow?
AGENTI need two things for the tow: 1. Location: I have Southeast Fifth Avenue and Alder Street. Is that exactly where the car is, or is there a nearby landmark or cross street that would help the driver find you, given the construction? 2. Callback number: What's the best phone number for the tow driver to reach you? Your coverage includes towing up to 25 miles, so let
CUSTOMERRight.
AGENTI didn't get your callback number or confirmation of the location. Please tell me: 1. Is the car right at Southeast Fifth Avenue and Alder Street, or is there a landmark or side of the street that will help the driver find you? 2. What phone number should the tow driver
CUSTOMERRight.
AGENTIt sounds
CUSTOMERYeah. Sorry.
AGENTNo need to apologize,
CUSTOMERYeah. Still
AGENTNo problem,
CUSTOMERRight. Let's keep...
CUSTOMEROkay. The car is right at Southeast fifth Avenue in Alder Street, parked on the north side, near the big construction site. The best number for the tow driver to reach me is nine zero seven four one six two eight one zero. What's next?
AGENTThanks, that's what I needed. I'll send the tow now.
CUSTOMERAlright. Where will the car be taken?
CUSTOMERI need a claim number, please.
CUSTOMERAlso, what do I have to pay for this?
AGENTThe tow is dispatched. Eastside Towing is on the way with an estimated arrival of 45 minutes. They'll call you at 907-416-2810
CUSTOMERGot it. That's fine. I need the claim number. And, also, where exactly are they taking the car?
CUSTOMERwhat do I have to pay out of pocket?
AGENTTo answer your questions: Where the car is going: Eastside Towing will take it to our partner repair shop at 9th and Morrison. What you pay: Your policy covers towing
CUSTOMERYeah. I got it. I just need the claim number and the address where the car is going.
CUSTOMERtell me if I have to pay anything.
CUSTOMERYeah. I know how coverage works. Just tell me, do I have a deductible?
CUSTOMERSince he hit me, I shouldn't have to pay that. Right? Also, is my premium going to go up because of this?
AGENTI still need a few details to open the claim, and I'll answer your questions first. Where the car is going: the Northgate partner repair shop at 9th and Morrison.
CUSTOMERUh-huh.
AGENTHere are your answers,
CUSTOMERYeah. Hi.
AGENTHi Mr.
CUSTOMERGo ahead.
CUSTOMERI'm ready.
AGENTHere are your
CUSTOMERYeah. I'm still here.
AGENTHere
CUSTOMERRight. I'm listening.
CUSTOMERyou give me the claim number?
AGENTI can't give you the claim number yet because I haven't opened the claim. I still need a few details from you. Once I have them, I'll open it right away and read you the number. First, your questions: - Where the car is going: the Northgate partner repair shop at 9th and Morrison. - Towing cost: your policy covers towing up to 25 miles. I don't have a charge to quote
CUSTOMERUh-huh.
AGENTYour policy shows a $500 collision deductible. I can't tell you whether you'll end up paying it, because that depends on how the claim is decided. I also can't say whether your premium
CUSTOMEROkay.
AGENTNow the details
CUSTOMERBut he
AGENTGo ahead,
CUSTOMERLook.
AGENTI'm
CUSTOMERRight. But he hit me.
AGENTI understand, and what you're telling me is going into the claim. I can't say who pays the deductible
CUSTOMEROkay.
AGENTLet's get your claim opened.
CUSTOMERYeah.
CUSTOMERAlright. I'm ready.
CUSTOMERwhat do you need from me?
AGENTHere's what I need. Take them in any order: 1. Time of the accident. You said about twenty minutes ago. What time was that, roughly, and what's today's date? 2. What happened. In your own
CUSTOMERGot it.
AGENTLet's start with the first one: what time did the accident happen, and what's today's date? After that, tell me in your own words what happened,
CUSTOMERYeah. About twenty minutes ago. So whatever time that was now, today's date is June thirteenth.
AGENTThanks. I don't have a clock on my end, so I'll note it as about twenty minutes before this call on June 13th.
CUSTOMERYeah.
CUSTOMERRight. So around two twenty five PM,
AGENTGot it, around 2:25 PM on June 13th. Next, tell me in your own words what happened. Then I need the other driver's details: 1. Their name 2. Their insurance company 3. Their license plate 4. Whether police came to the scene, and a report number if you have one.
CUSTOMEROkay. I was stopped at a red light at Southeast fifth and Alder, and another car hit the back of my car. Nobody's hurt, but the back bumper is crushed, and the rear wheel rubs, so I can't drive it. The other driver is Kevin Lund, insured with Pacific Shore. His license plate is seven k x r two one four, x like X-ray. Police did not come, so there's no report number.
AGENTLet me read back what I have so you can correct anything before I open the claim: - Policy number: NG44719002 - Other driver's
CUSTOMERYeah. That's all correct. Go ahead and open the claim.
AGENTYour claim is open. Here are the details to check: - Claim number: NGM-904417 (N-G-M,
CUSTOMERAlright. Just need the claim number.
AGENTYour claim number is NGM-904417. That's N-G-M, nine-zero-four-four-one-seven. Here is the rest
CUSTOMEROkay. I've got the claim number. Thanks. That's all I needed.
CUSTOMERGoodbye.
AGENTTake care, Mr. Brooks. Before you go, here are the key details: - Claim number: NGM-904417
AGENT- Policy number: NG44719002 - Other driver's plate: 7KXR214 (Kevin Lund, Pacific Shore) - Adjuster: Priya Shah, who will contact you within one business day. - Tow: Eastside Towing is about 45 minutes out and will call 907-416-2810. The car is going to the Northgate partner repair shop at 9th and Morrison. Your policy covers towing up to 25 miles. - Rental: $40 per day for up to 30 days, starting from the day the claim was opened. - Deductible: Your collision deductible is $500. I can't say whether you'll end up paying it or whether your premium will change, so please ask Priya Shah about both. One correction: I opened the claim before you confirmed the read-back, and I never read the plate back to you. Please make sure 7KXR214 is right. If it's wrong, tell Priya Shah or call us back and we'll fix it. Goodbye, and I hope the rest of your day goes better.