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
#293of 929 stacks
54 / 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.
#1065 of 1184 on the board · best 99%
Flow adherence
How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.
#192 of 1184 on the board · best 5.0 / 5
Instruction following
How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.
#94 of 1184 on the board · best 5.0 / 5
Turn-taking
Barge-in handling
When the caller interrupts, how often the agent made the right call: yielding to a real correction, and holding the floor through a filler.
#1 of 698 on the board · best 100%
Incorrect interruptions
How often the agent interrupted the caller when it should have kept listening.
#1 of 1184 on the board · best 0%
Overtalk
Share of the conversation where both sides were speaking over each other.
#962 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.
#1 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.
#699 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.
#601 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.
#455 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.
#264 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.
#935 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.
#36 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.
#753 of 1184 on the board · best 0.45 s
Latency spikes
Turns where the response took far longer than the rest of the conversation.
#1 of 1184 on the board · best 0.0 per call
By industry
| Industry | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| Healthcare | 78% | 1.66 s | — |
| Home services | 78% | 1.49 s | — |
| Insurance | 85% | 1.81 s | — |
| Customer support | 93% | 2.10 s | — |
By caller
| Caller | Task completion | Latency P50 | Barge-in handling |
|---|---|---|---|
| US English, quiet line | 92% | 1.88 s | — |
| Spanish-accented English, city street | 90% | 1.64 s | — |
| Indian English, busy café | 90% | 2.28 s | — |
| Southern US, flustered, crying baby | 84% | 2.05 s | — |
| Fast and interrupting, construction outside | 62% | 1.35 s | — |
The calls behind the numbers
Customer support
AGENTBrightwave Internet support, this is Alex. What’s going on with your service?
CUSTOMERHey, Alex. Um, sorry. I'm a little flustered here.
CUSTOMERMy Internet's been down for about two hours now.
CUSTOMERAnd I work
CUSTOMEROh,
AGENTNo problem, take your time. I can help you get this sorted out. Let me pull up your account so we can figure out what's going on. Can you give me your account number or the phone number associated with your account?
CUSTOMERSure. Sorry. Let me grab that for you.
CUSTOMERMy account number is b w eight eight three zero one seven... oh, shoot. Sorry. Last digit is one. Is that enough?
AGENTGot it—account number bw8830171. Let me look that up for you.
AGENTPerfect, I've got your account pulled up. Now let me check if there's an outage in your area.
AGENTOkay, good news—there's no outage in your area. Let me run a line test to see what's happening with your connection.
AGENTAlright, so the signal to your gateway is good, but it's not registered on the network. Let me send a remote reset to your gateway.
AGENTGreat! I've reset your gateway and it's now registered and online. Your devices should be back up within about two minutes. Give it a quick test once they reconnect—you should be good to go.
CUSTOMEROkay. Thanks for resetting it.
CUSTOMERThe Internet light just went solid white, so I think it's coming back. How long does it usually take for everything to reconnect?
CUSTOMERI really need to get back.
AGENTGood sign with that solid white light! Like I mentioned, devices typically take about two minutes to fully reconnect. You should be back online pretty soon. In the meantime, if you want to speed things up a bit, you can reconnect your devices manually—just toggle Wi-Fi off and back on, or reconnect to your network. But give it a couple minutes and you should be all set. Let me know if you're back up and running, or if you hit any issues.
CUSTOMEROkay. Thanks. That helps.
CUSTOMERI'm a little anxious about it.
CUSTOMERSorry.
CUSTOMERI'm not sure what you mean. Could you clarify?
CUSTOMERyou asking about my network or my device?
AGENTNo worries! I was just saying you can manually reconnect your devices to speed things up a bit. So on your phone or laptop—whichever device you're using—you can turn Wi-Fi off and back on, or go into your network settings and reconnect to your home Wi-Fi network. That way you don't have to wait the full two minutes for automatic reconnection. But honestly, it should come back on its own in a minute or two anyway. You're all set—just let it do its thing.
CUSTOMERAlright. Thanks. I appreciate that.
CUSTOMERSo while I've got
AGENTYou're welcome! While you've got me, what else do you need?
CUSTOMERYeah. I wanted to ask about a credit for the downtime. I lost two hours of work today.
CUSTOMERCan you help me out with that?
CUSTOMERSorry if that's a bother.
CUSTOMERSorry.
AGENTNo need to apologize! I've applied a $10.00 service credit to your account for the two hours of downtime. It'll show up on your next bill. You're all set. Anything else I can help with?
CUSTOMERThanks for doing that, but I lost two hours of work. Could you make it more than ten dollars?
CUSTOMERIs that possible?
AGENTI understand—two hours of lost work is frustrating. Unfortunately, the credit I just applied is what the system allows me to issue for that amount of downtime. I don't have the ability to adjust it beyond that $10.00. If you'd like to discuss this further, you could reach out to our billing department directly—they may be able to review your situation and see if there's anything else they can do for you. But the $10.00 credit is what I can process on my end. Is there anything else I can help with today?
CUSTOMERAlright. I get it. Thanks for explaining.
CUSTOMERThat's all I needed.
AGENTYou're welcome! Glad I could get you back online. Your account number is bw8830171, and you've got that $10.00 credit applied. Take care!
Healthcare
CUSTOMEROkay.
AGENTHi! I'm Alex, the scheduling assistant at Riverbend Health Clinic. How can I help you today?
CUSTOMEROkay.
CUSTOMERHey.
AGENTHey there!
CUSTOMERSorry.
AGENTNo problem at all! Take your time. What can I help you with today?
CUSTOMERThanks. I just need to move my dermatology appointment next Wednesday morning.
CUSTOMERScott scheduled for a work shift then, so I can only come after three PM. Can you help me reschedule it?
AGENTI'd be happy to help you reschedule! To get started, I need to verify your account. Could you please provide: 1. Your full name
CUSTOMERYeah. Sure. It's Nate Brooks.
CUSTOMERMarch seventeenth nineteen forty eight. Oh, sorry. No. Nineteen eighty four. March seventeenth nineteen eighty four.
AGENTGot it! Let me verify that for you.
AGENTPerfect! I've verified you, Nate Brooks, date of birth March 17th, 1984.
CUSTOMEROkay. Great. So I just need to move that appointment to any day after three PM. What do you have?
AGENTI'll check Dr. Okafor's availability for slots after 3 PM starting next Wednesday.
AGENTGreat! Here are Dr. Okafor's available slots.
CUSTOMERUh-huh.
CUSTOMERYep.
CUSTOMERUh-huh.
CUSTOMERJust give me the earliest one after three. I really don't have much time.
AGENTPerfect! The earliest slot after 3 PM is Thursday at 4:10 PM.
CUSTOMERRight. Go ahead. What's the soonest one?
AGENTThursday at 4:10 PM is the soonest one after 3 PM. Should I reschedule your appointment to that slot?
CUSTOMERYes.
CUSTOMERThursday at four ten PM works.
CUSTOMERbook it for me. Yep. Thursday at four ten PM is good. Go ahead and move my appointment to that.
AGENTDone!
CUSTOMERAlright. So before we finish, can you tell me if there's any fee for changing the appointment
AGENTLet me check the clinic's change policy for you.
AGENTGood news!
CUSTOMERMhmm.
AGENTAccording to our policy, changes made more than 24 hours before the appointment are free.
CUSTOMERYeah.
AGENTSo you're all set!
CUSTOMEROkay. Thanks.
CUSTOMERwhere should I park when I come in?
AGENTYou can use the free patient parking in Lot C—the entrance is on River Road.
CUSTOMERYeah.
AGENTYou're all set, Nate! Here's your confirmation:
CUSTOMERGot it.
CUSTOMERAlright. One last thing. Does doctor Okafor accept Aetna insurance?
AGENTI don't have information about insurance coverage in my system. I'd recommend calling the clinic directly to confirm that Dr. Okafor accepts your Aetna insurance. Is there anything else I can help you with?
CUSTOMERNo. That's all.
CUSTOMERThanks for your help. Goodbye.
AGENTYou're welcome! Just to confirm your details one more time:
CUSTOMERThanks. I got everything I needed. Goodbye.
AGENTGreat! Take care, Nate. Goodbye!
Home services
AGENTCopperline Home Services, this is Alex. What can I help you with?
CUSTOMERSorry. I'm a little flustered. I got a baby crying right here.
CUSTOMERI need help quick. A pipe under my kitchen sink just burst, and there's water spreading everywhere, heading right toward a power strip. I haven't shut the water off yet. Can y'all send someone out?
AGENTOkay, stay calm—I'm here to help. First things first: shut off your water main right now. Do you know where it is? It's usually in the basement, crawl space, or near the street. Turn the valve clockwise until it stops. This will stop the water immediately. While you're doing that, unplug anything near that power strip or move it away from the water. Keep yourself and your baby away from any standing water near electrical outlets. Once you've shut off the water, I'll get a technician out to you as soon as possible. Let me know when that's done.
CUSTOMEROkay. I'm doing that now.
CUSTOMERHang on. I got it. I think the water stopped. The power strip's out of the way, and we're clear from the outlet. Sorry. Is that enough?
CUSTOMERCan you send somebody out now?
AGENTPerfect—you did exactly right. You're safe now, and that was quick thinking. Let me get you set up with a service request. I need a few details: 1. What's your phone number? 2. What's your street address and unit number (if you have one)?
Once I have that, I'll open an emergency ticket and get you the earliest available technician.
CUSTOMERThank you. I just... I really hope this gets fixed fast.
CUSTOMERMy phone number is
AGENTI'm here to help—we'll get this sorted. Go ahead and give me that phone number whenever you're ready.
CUSTOMERSorry. I'm just a little shaken.
CUSTOMERMy number is five zero three five five five zero one three nine. No. Zero one nine three. Five zero three five five five zero one nine three. My address is fourteen eighty Larkspur Avenue, and I'm in unit four d now. Not four b. I moved last month. Is that all you need?
AGENTYou're doing great. I've got: - Phone: 503-555-0193
- Address1480 Larkspur Avenue, Unit 4D
That's all I need for now. Let me look up your account and open an emergency service request.
AGENTNow let me check if you're in our system:
AGENTGreat news—you're a Copperline Care member, which saves you money on emergency calls. I see your address on file as Unit 4B, but you just told me you moved to Unit 4D last month. I'll update that to 4D. Here's what I can offer you right now: Emergency visit today: 2:00 PM to 4:00 PM
- Emergency callout fee$99 (Copperline Care rate)
That's the soonest we can get someone out. Does that work for you?
CUSTOMERSorry. Is there any way someone could come before two?
CUSTOMERI'm just really worried about the water damage and the baby's here. And how much will the whole visit cost?
CUSTOMERNinety nine dollars. Is that everything?
CUSTOMERor could there be more?
AGENTI understand—you're worried, and that's completely fair. Unfortunately, 2:00 PM to 4:00 PM is the earliest emergency window we have available today. I can't promise anything sooner than that. As for cost: The $99 is the emergency callout fee—that gets the technician here. Once they assess the burst pipe and do the repair, there will be additional charges for parts and labor, which depend on what they find. I don't have those costs upfront, but the technician will give you an estimate before they start any work. The $99 is just the service call itself. Does that window work for you, or would you prefer to wait until tomorrow morning (8:00 AM to 10:00 AM) at the standard rate of $79?
CUSTOMEROkay. I guess I'll take the two PM to four PM window.
CUSTOMERI'm just too nervous to wait.
CUSTOMERSorry if I'm being a bother. Can you tell me who'll be coming and how I'll know when they're on the way?
CUSTOMERAnd, uh, what's the ticket
CUSTOMERSorry.
AGENTYou're not being a bother at all—this is exactly what we're here for. Let me book that 2:00 PM to 4:00 PM window for you right now.
AGENTNow let me book the visit:
AGENTPerfect. You're all set. Here's what you need to know: Your ticket number is CPL-58210. Your technician is Dana. She'll text you at 503-555-0193 about 30 minutes before she arrives, so you'll know exactly when to expect her. To confirm everything: - Address: 1480 Larkspur Avenue, Unit 4D - Callback phone: 503-555-0193
- IssueBurst pipe under kitchen sink
- WindowToday, 2:00 PM to 4:00 PM
- Emergency fee$99 (Copperline Care rate)
The water main is already shut off, so you're safe. Just keep that area clear, and Dana will take it from there. You did everything right. Any questions before we wrap up?
CUSTOMERNo. I think that covers it. Thank you for helping me so quick and for getting Dana out here.
CUSTOMERI really do appreciate
AGENTYou're very welcome. You handled this perfectly—shutting off that water main right away was exactly what needed to happen. Dana will take great care of you and that burst pipe. If you need anything before she arrives, just call us back. Otherwise, look for her text in about an hour or so. Take a deep breath. You've got this. Bye now.
Insurance
AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?
CUSTOMERYeah. I think so. I'm just standing next to my car on the sidewalk. I got the baby with me, but we're alright. Just kinda shaking up. You know?
CUSTOMERSorry. Am I supposed to do anything else right now?
AGENTYou're doing just right. I'm glad you and the baby are safe—that's what matters most. Take a breath. You're in good hands now. I'm going to help you get this claim started. First, let me just confirm: is anyone hurt? Any injuries at all, even if they seem minor?
CUSTOMERNo. Nothing like that. I promise.
CUSTOMERWe're both okay. Just a little shaking up, but, really, no injuries at all.
CUSTOMERIs that alright?
AGENTThat's alright. I'm really glad to hear that. You did the right thing getting to safety. Now let me get some information from you so we can open your claim. I'll need your policy number, and if you have it handy, your last name would help me verify everything. What's your policy number?
CUSTOMERYeah. I got it here. It's n g four four seven one nine zero three... oh, wait. Sorry. The last one is two. So n g four four seven one nine zero two.
CUSTOMERIs that okay?
AGENTGot it.
CUSTOMERand my last name's Carter.
CUSTOMERIs that gonna be enough?
AGENTLet me check your coverage details for you.
AGENTGood news. You've got collision coverage with a $500 deductible. You also have rental reimbursement at $40 a day for up to 30 days, starting from when we open the claim today. And towing is covered up to 25 miles. So you're in good shape. Now let me get the details of what happened so we can open your claim. Can you tell me: 1. When did this happen? What's the date and time? 2. Where did it happen—what's the location or address? 3. What happened? Just tell me in your own words.
CUSTOMERAlright. So it was about twenty minutes ago. So today's date, and it's... I think it's around one PM, maybe a little after. We stopped at a red light at Southeast fifth Avenue in Alder Street, and this other car just hit the back of mine. My bumper's crushed, and the rear wheel's rubbing, so I can't drive it. Nobody's heard. Police didn't come, but I got the other driver's info. Is that gonna be enough for you?
AGENTThat's helpful, thanks. I've got most of what I need. Let me just get the other driver's information from you so I can complete the claim. Can you give me:
1. The other driver's name
2. Their insurance company
3. Their license plate number
CUSTOMERSure. So the other driver's name is Kevin Lund. His insurance is with Pacific Shore, and the license plate is seven k, x like X-ray, r two one four.
CUSTOMERIs that what you need?
AGENTPerfect. That's exactly what I need. Let me open your claim now.
AGENTExcellent. Your claim is open. Let me read back what we have: Policy Number: ng44719302
Other Driver's License Plate7KXR214
Claim NumberNGM-904417
Your adjuster is Priya Shah, and she'll be in touch with you within one business day.
Now, since your vehicle isn't drivable, do you need me to arrange a tow truck to come get it?
CUSTOMERYes, please. If you can.
CUSTOMERI'm worried about it sitting here. I really can't drive it at all.
CUSTOMERcould you tell me where it'll be taken? And, uh, will I get a rental car right away?
CUSTOMERsorry if I'm asking too much.
CUSTOMERjust wanna make sure we're covered.
AGENTYou're not asking too much at all—that's what I'm here for. Let me get the tow arranged for you right now. I'll need a callback number so the tow truck driver can reach you when they're on the way. What's the best number to call you at? As for the rental car—your coverage starts today when we opened the claim. You've got $40 a day for up to 30 days. Your adjuster Priya will work with you on the rental details when she contacts you tomorrow. She'll have all the information about where your vehicle is being taken and can help coordinate the rental from there. What's your callback number?
CUSTOMERYeah. The best number is four three five three eight three eight three one five.
CUSTOMERIs that alright?
CUSTOMERAnd is there anything else you need from me?
CUSTOMERI just wanna make sure nothing gets missed.
AGENTYou're all set. Here's what's happening: A tow truck from Eastside Towing is on the way to you at Southeast Fifth Avenue and Alder Street. They'll be there in about 45 minutes, and they'll take your 2021 Honda CR-V to our Northgate partner repair shop at 9th and Morrison. They have your callback number, so they'll call you when they're close. Let me confirm everything one more time: Policy Number: ng44719302
Other Driver's License Plate7KXR214
Claim NumberNGM-904417 Your adjuster Priya Shah will contact you within one business day. She'll help you with the rental car and answer any questions about repairs and next steps.
You've done everything right. Stay safe, keep the baby comfortable, and you're good to go. Is there anything else I can help you with?
CUSTOMERNo. I think that's everything.
CUSTOMERThank you so much for helping me out.
CUSTOMERI was real nervous about all this.
CUSTOMERjust one nice thing. Are you sure my premium isn't gonna go up? And since he hit me, I shouldn't have to pay that deductible. Right?
AGENTI'm glad I could help, and I understand your concerns—that's a natural thing to worry about. But those are really good questions for your adjuster Priya Shah. She'll have all the details about how this claim affects your premium and the deductible situation, especially since this was a rear-end collision where you were stopped at a red light. She'll go over all of that with you when she calls tomorrow. What I can tell you is that you've got collision coverage and a $500 deductible, and Priya will walk you through exactly how everything works out. You take care of yourself and that baby. You did great today.