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
#16of 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.
#532 of 1184 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#119 of 1184 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#94 of 1184 on the board · best 5.0 / 5
Turn-taking
Barge-in handling
When the caller interrupts, how often the agent made the right call: yielding to a real correction, and holding the floor through a filler.
#1 of 698 on the board · best 100%
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 1184 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#736 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.
#861 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.
#571 of 1167 on the board · best 0.3%
Text-to-Speech
Readback accuracy
Share of the codes, amounts, dates and phone numbers the agent wrote that its voice read out correctly. One wrong digit is a miss.
#425 of 974 on the board · best 100%
Word error rate
The share of the words the agent wrote that its voice dropped or changed, read back from Roark’s transcription of the recording; the same transcriber hears every voice.
#89 of 1043 on the board · best 0.8%
Voice
Human-likeness
How human the agent's voice sounds, scored by an audio model on intonation, rhythm and expressiveness. 5 = hard to tell from a person.
#1139 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.
#288 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.
#659 of 1184 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#253 of 1184 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 88% | 2.97 s | — |
| Home services | 95% | 2.92 s | — |
| Insurance | 88% | 2.69 s | — |
| Customer support | 90% | 2.96 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 91% | 2.99 s | — |
| Spanish-accented English, city street | 96% | 2.73 s | — |
| Indian English, busy café | 90% | 2.93 s | — |
| Southern US, flustered, crying baby | 92% | 2.74 s | — |
| Fast and interrupting, construction outside | 82% | 2.87 s | 100% |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHi. Uh, yeah, I'm calling because my internet has been down for about two hours. I work from home, so, um, it's a problem. There's a road crew digging up the street right outside my building. Could that be the cause? I already rebooted the gateway twice. Checked every cable. But the internet light is still blinking orange. Can you help me figure out what's going on?
AGENTI can help with that. First, I need to verify your account. Can you give me your account number or the phone number on the account?
CUSTOMERSure. My account number is BW883017. Oh, sorry. Last digit is one, and my phone number is plus 15074152146. Does that work for you?
AGENTThe account lookup returned account ID BW-883011, which ends in 1, as you said. Let me check for an outage at your address.
AGENTThere's
CUSTOMEROkay. Go ahead. I just. Want to know if the road crew outside is causing this, because it's been two hours and I need to get back online.
AGENTUnderstood. The line test shows a good signal from the network to your gateway, so the line itself looks fine. The gateway is not registering, which is why the light is orange. There's no known outage in your area, so I can't confirm the road crew is the cause. A cut fiber nearby could still cause this, but our system doesn't show one. I'm sending the remote reset now.
AGENTThe remote reset worked. Your gateway is registered and online. Devices can take about two minutes to reconnect, so give it a moment, then check your connection. Your account is BW-883011. If your connection doesn't come back after a couple of minutes, or drops again, call us back and we can schedule a technician.
CUSTOMEROkay. The internet light just went solid right now. How long until my devices reconnect fully? And since I lost two hours of work, can you add a credit for the downtime to my account?
AGENTYour devices should reconnect fully within about two minutes of the reset. If any are still offline after that, toggle Wi-Fi on them or restart them. For the credit, I can apply a service credit for the downtime. I'll apply it to account BW-883011 now.
AGENTA $10.00 service credit has been applied to account BW-883011. It will appear on your next bill.
CUSTOMERMM. I lost two hours of work. Can you make it more than that?
AGENTI can't increase the credit. The $10.00 credit is what I'm able to apply for this downtime. Since your service is back, there's nothing more I can do to change that amount. If you want to dispute the amount, you can ask our billing team to review it. Is there anything else I can check on your connection now?
CUSTOMERNo, that's all. I needed. Thanks for your help. Goodbye.
Healthcare
AGENTRiverbend
CUSTOMERHey, there. Uh, I'm calling Riverbend Health clinic. I need to reschedule my dermatology appointment next Wednesday morning. I just found out I have to work that shift now. Sorry. I got a baby crying in the background, and my lunch break is almost over. Can y'all help me move it to something after 3 p.m.? My name's Wade Carter.
AGENTHi Wade, no problem at all. I can help you move that. First I need to verify your identity. Could you please give me your date of birth?
CUSTOMERYeah, sure. Uh, it's March 17th, 1948. Oh, wait. Sorry. No. 1984. March 17th, 1984. Sorry about that. My mind's just all over the place right now. Is that okay?
AGENTNo problem, Wade. I have your date of birth as March 17, 1984. Let me verify your details.
AGENTThanks, Wade, you're verified. Let me pull up your upcoming appointments.
AGENTI found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 a.m. at Main Campus, Building B. Let me check Dr. Okafor's openings after 3 p.m.
AGENTHere are Dr. Okafor's openings after 3 p.m.: - Tuesday at 3:45 p.m. - Thursday at 4:10 p.m. Do either of those work for you?
CUSTOMEROh, um. Tuesday's actually don't work after all, cause I got to pick up my daughter. Sorry. I should have mentioned that. What about Friday? Is there anything open, then? Or maybe Thursday at 4:10 p.m..
AGENTFriday's only opening is at 11:30 a.m., which is before 3 p.m., so it doesn't fit your requirement. That leaves Thursday at 4:10 p.m. Would you like me to move your appointment to Thursday at 4:10 p.m.?
CUSTOMERYeah. Sorry. Let's go with Thursday at 4:10 p.m.. I'm just worried about missing work, so that should be okay. Is that all right? Can you confirm that for me?
AGENTYour appointment is rescheduled, Wade. - New time: Thursday at 4:10 p.m., with Dr. Okafor - 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?
CUSTOMERUh, yeah. Sorry. Just a couple quick things. Is there a fee for changing the appointment?
AGENTLet me check the clinic's change policy for you.
AGENTChanges made more than 24 hours before your appointment are free. Since your appointment is next Wednesday, you're well within that window, so there's no fee for this change. What's your other question?
CUSTOMERThat's a relief. Thanks. Uh, where should I park when I get there? I always worry about that. You know?
AGENTFree patient parking is in Lot C, with the entrance on River Road.
CUSTOMEROkay. Thank you. That helps a lot. And, um, does Doctor Okafor accept Aetna insurance. I just want to make sure I'm covered.
AGENTI'm sorry, Wade, I don't have information about which insurance plans Dr. Okafor accepts. I'd recommend calling the clinic's billing or front desk team, or checking with Aetna directly, to confirm your coverage before Thursday.
CUSTOMERAll right. I'll do that. Thanks for checking anyway. So just to double check my appointments Thursday at 4:10 p.m.. Main campus, building B, confirmation code RVB3M8P2, that's all correct, right?
AGENTAlmost. The confirmation code is RVB-3M8P2, with a hyphen after the RVB. Everything else is correct: Thursday at 4:10 p.m., with Dr. Okafor, at Main Campus, Building B. Remember to arrive 15 minutes early with your photo ID and insurance card.
CUSTOMERThank you so much. For your help. Sorry again for all the questions. I really appreciate it. Have a good day.
AGENTYou're welcome, Wade. No need to apologize, and good luck with your shift. Have a good day!
Home services
AGENTCopperline Home Services,
CUSTOMERHey. Uh, sorry. I need some help real quick. A pipe under my kitchen sink just burst. Water spreading all over the floor. And it's heading toward a power strip. I've got a baby crying in the background, so I'm kind of flustered. Can you help me get someone out here to fix it?
AGENTYes, I'm going to help you right now. Stay calm, and do these things first: 1. Shut off the water. Look under the kitchen sink for the two small valves on the supply lines (one for hot, one for cold). Turn them clockwise until they stop. If you can't find them or they won't turn, shut off the main water supply to the house. 2. Keep away from the power strip and outlets near the water. Don't touch anything plugged in that's sitting in water. If you can safely unplug the strip without stepping in water, do it. If not, leave it alone and stay out of the wet area. 3. Move the baby to a dry room if you can. Let me know once the water is off, and tell me if anyone is hurt or if you see sparks, buzzing, or a burning smell. While you do that, what's the service address including the unit number, and what's the best callback number?
CUSTOMEROkay. Sorry. Uh. Hang on. I'm turning the valves now. Yeah. Okay. The water stopped. Nobody's hurt, and I don't see sparks or smell anything burning. The baby's fine. Just scared. The address is 1480 Larkspur Avenue, and the unit is 4D, not 4D. I just moved last month. And for the callback, it's (503) 555-0139. No, sorry. 0193. Is that all right?
AGENTThanks, that's good work. The water is off, and I'm glad everyone is safe. Let me confirm what I have: 1480 Larkspur Avenue, Unit 4D, and callback number (503) 555-0193. Let me look up your account now.
AGENTI found your account, but the unit on file is 4B, and you've told me it's 4D. Since you recently moved, I'll go with 4D. Do you have a gate code or any access instructions for the building?
CUSTOMEROh. Uh yeah it's pound 2719 for the gate. Sorry. I know the unit changed, please make sure it's for 4D. Is that going to be a problem?
AGENTNo problem at all. I'll use Unit 4D, and I'll note the gate code is #2719. Before I open the request, I'm checking
CUSTOMERSorry. Thank you for making sure. Uh, can I ask how much is the visit going to cost? I just want to know before we get started.
AGENTOf course. I'll check the availability and fees for an emergency visit now.
AGENTYour ticket is CPL-58210. Since you're a Copperline Care member, the emergency callout fee for your visit is $99. The earliest window is today, 2:00 to 4:00 PM. The next option is tomorrow, 8:00 to 10:00 AM, but that's a standard visit at $79. Do you want the today 2:00 to 4:00 PM emergency window at $99?
CUSTOMEROkay. Thank you for checking. Is there any way someone could come before two? I just I'm worried with the baby. And all this water. If that's the earliest, then yes. I'll take the 2:00 to 4 p.m.. Emergency window for $99. Could you tell me who's coming and how? I'll know when they're on the way? And, uh, could you repeat the ticket number one more time just so I don't mess it up?
AGENTI understand the worry. The 2:00
CUSTOMEROh. Sorry. I just want to make sure. So 2:00 is the soonest. Please tell me. That's right. And who's coming out? And how will I know they're on their way? Could you say the ticket number again so I can double check?
AGENTYes, 2:00 PM is the earliest window the system offers today. Your visit is booked for today, 2:00 to 4:00 PM. The technician is Dana. Dana will text your callback number, (503) 555-0193, about 30 minutes before arriving, so you'll know they're on the way. Your ticket number is CPL-58210.
CUSTOMERAll right. That helps a lot. Thank you. So Dana will text me before coming. And the ticket number is CPL 58,000. Could you finish it for me just to be sure I have it right? Sorry, I just want to make sure nothing gets mixed up.
AGENTYour ticket number is CPL-58210. That's C-P-L, then 5-8-2-1-0. Dana will text (503) 555-0193 about 30 minutes before arriving. In the meantime, keep the baby away from the wet floor, stay clear of the power strip, and leave the water valves off. If you see sparks, smell burning, or the water spreads toward any outlets, get everyone out of the room and call 911 right away.
CUSTOMERWith. Okay. Thank you. That's CPL58210. I really appreciate your help, and I'll keep the baby safe and watch the water. Thanks again. Goodbye.
AGENTYou're welcome. Your ticket is CPL-58210, and Dana will text you before arriving. Take care of yourself and the baby. Goodbye.
Insurance
AGENTNorthgate Mutual
CUSTOMERHi. Sorry. I need some help. I'm Wade Carter. My car just got hit about 20 minutes ago, and I'm pretty flustered right now. My baby's crying and I can't drive the car. I'm insured with y'all. Northgate mutual. Can. You help me start a claim?
AGENTclaims,
AGENTHi Wade, I'm Alex, and I'm here to help. Take a breath, you're doing fine. First, is everyone safe right now? That includes you, your baby, and anyone else involved. Is anyone hurt or in danger? If anyone is injured or you're near traffic that could hit you, please call 911 before anything else. Once everyone is safe, I'll need your policy
CUSTOMERI appreciate you asking. Thank you. Yeah. Everyone's okay. No one's hurt. Just shaken up. My baby's crying, but he's all right. We're up on the sidewalk, so we're safe from traffic. It's just the cars that got banged up. What do you need from me first?
AGENTI'm glad everyone is okay, and thank you for getting to the sidewalk. To start, I need your policy number. If you don't have it handy, your last name will also help me look it up.
CUSTOMERYeah, I've got it here. I think it's NG4471903. Wait. Sorry. Last one is 2NG4471902. Is that okay?
AGENTThanks, Wade. You gave two numbers, so I want to be sure I use the right one. The latest one you gave is 2NG4471902. Let me verify that policy now, along with your last name.
AGENTThank you, Wade. Your policy is verified. It covers a 2021 Honda CR-V, with collision, rental reimbursement, and roadside towing. Next, can you tell me when and where the accident happened? Then tell me what happened in your own words.
CUSTOMERYeah sure. It was about 20 minutes ago at the intersection of Southeast fifth Avenue and Alder Street. I was stopped at a red light, and another car just ran right into the back of me. My bumper's crushed and the rear wheel is rubbing. I can't drive it. Nobody's hurt. Like I said, the police didn't come out. I'm standing next to the car still. Is that enough detail or do you need more?
AGENTThat's helpful, thank you. I still need the other driver's name, their insurance company, and their license plate number. If you didn't get those, tell me what you have and we can work from there. Also, since the rear wheel is rubbing and you can't drive the car safely, I can arrange a tow. Where is the car located right now, and what's a good callback number for the tow driver?
CUSTOMERYeah, I got all that. Just let me grab the info. The other driver's name is Kevin Lund. He's insured with Pacific Shore, and his plate is 7KXR214X, like X-ray. My car's right here at southeast, fifth and Alder, like I said. And my phone number for the tow is (443) 746-9570. Is that all you need for the tow truck? Where's the car going to be taken?
AGENTThanks, Wade. I have the other driver as Kevin Lund, insured with Pacific Shore, plate 7KXR214X, and your callback number is (443) 746-9570. I'll dispatch the tow to Southeast Fifth Avenue and Alder Street now.
AGENTWade,
CUSTOMEROh. All right, thank you.
CUSTOMERSorry. What else do you need?
AGENTNo need to apologize, Wade. You're doing great. Here's where things stand: - Claim number: NGM-904417 - Adjuster: Priya Shah, who will contact you within one business day. - Tow: Eastside Towing is dispatched to your location at Southeast Fifth Avenue and Alder Street. They should arrive in about 45 minutes and will call you at (443) 746-9570. The car will be taken to the Northgate partner repair shop at 9th and Morrison. - Other driver: Kevin Lund, Pacific
CUSTOMEROkay. Thank you so much for the update. I really appreciate you breaking it all down for me. Just can you tell me how much am I supposed to pay for all this? Is there a deductible? Since he hit me? I shouldn't have to pay that, right? Also, do I get a rental car? And is my premium going to go up because of this? Sorry for all the questions. I just want to be sure.
AGENTThose are good questions, and I'll check your actual coverage rather than guess.
AGENTHere's what your policy shows: - Deductible: Your collision deductible is $500. That's the amount you'd normally pay toward repairs on your own car. Whether it's ultimately charged to you depends on how the claim is handled, including recovery from the other driver's insurer, which Priya Shah can explain. - Rental: Your policy includes rental reimbursement of $40 per day for up to 30 days, starting from the day the claim was
CUSTOMERAll right. So just to be clear, I might have to pay $500 at first, but since he hit me, there's a chance I won't actually have to pay that. Right. I really want to make sure I'm not stuck with the bill when it wasn't my fault. And for the rental, that's $40 a day up to 30 days, starting now. Is that right? Also, is there any way to know if my premium is going to go up because of this? Sorry. I just worry about these things.
AGENTYes, you have it right. You may need to pay the $500 deductible up front, but because the other driver hit you, there's a chance it can be recovered from his insurer, Pacific Shore. I can't promise that outcome. Priya Shah will look into fault and recovery and can tell you where things stand. On the rental, yes: $40 a day for up to 30 days, starting from the day the claim was opened, which is today.
CUSTOMERThank you. That helps a lot. So is there any way to know if my premiums are going to go up? That's just got me worried. Could you repeat the claim number for me, please? I want to make sure I got it right.
AGENTYour claim number is NGM-904417. About your premium: I don't have any information on how this claim will affect your rates, and I can't estimate it. Your agent or Priya Shah can explain how claims affect your policy. Since this was a rear-end collision where the other driver hit you, it's worth asking them directly about that. Is there anything else I can help you with right now?
CUSTOMERThat's everything I needed. I think. Thank you for being patient. Sorry I was so flustered. I really appreciate your help. Goodbye.
AGENTYou're welcome, Wade. You did everything