Skip to content

Roark Live Bench · Suite v1.3 · Sweep of 15 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.

1176 stacks published23,380 scored callsPublished at 20 scored calls

Our picks

The read

  • 496 of 890 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 832 of 890 on task completion; the most complete is Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD at 99%.

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.
CascadeSpeech-to-speech
Task completionTool useTime to first wordResponse timeBarge-in handlingCost per task255075100
MeasureCascadeSpeech-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.

  • Pick Soniox v6: it leads on semantic word error rate (0.2%). If speed matters more, Deepgram Flux is the quickest, at 0.38 s.
  • 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 2.1% for Speechmatics Linden-1 (own VAD).
  • In 574 of 1,161 cascades the transcriber is the slowest step of the turn, whichever model runs it.

Roark score, best first

100Soniox v691Universal-3.6 Pro83Nova-382Universal-3.5 Pro72Enhanced (realtime)70Flux68Nova-268Linden-167Scribe v3 Live64Standard (realtime)56Linden-1 (own VAD)54Whisper-150GPT Transcribe
Every transcriber on every figure, sorted by roark score. Column headers sort the table.
#
1Soniox v6Soniox100 / 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)
2Universal-3.6 ProAssemblyAI91 / 100. Semantic word error rate 0.8%, 62.9 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
3Nova-3Deepgram83 / 100. Semantic word error rate 1.1%, 54.3 of 71 points; Time to final transcript 0.88 s, 28.6 of 29 points(among the best)1.1%(among the best)0.88 s$0.031
4Universal-3.5 ProAssemblyAI82 / 100. Semantic word error rate 1.1%, 53.3 of 71 points; Time to final transcript 0.90 s, 28.6 of 29 points1.1%(among the best)0.90 s$0.030
5Enhanced (realtime)Speechmatics72 / 100. Semantic word error rate 1.5%, 43.9 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points1.5%0.98 s$0.054
6FluxDeepgram70 / 100. Semantic word error rate 1.5%, 41.9 of 71 points; Time to final transcript 0.38 s, 28.6 of 29 points1.5%0.38 s(among the best)$0.031
7Nova-2Deepgram68 / 100. Semantic word error rate 1.6%, 39.7 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points1.6%0.89 s$0.023
8Linden-1Speechmatics68 / 100. Semantic word error rate 1.6%, 39.7 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points1.6%0.98 s$0.020
9Scribe v3 LiveElevenLabs67 / 100. Semantic word error rate 1.7%, 38.0 of 71 points; Time to final transcript 0.88 s, 28.6 of 29 points1.7%0.88 s$0.015(among the best)
10Standard (realtime)Speechmatics64 / 100. Semantic word error rate 1.8%, 35.1 of 71 points; Time to final transcript 0.96 s, 28.6 of 29 points1.8%0.96 s$0.031
11Linden-1 (own VAD)Speechmatics56 / 100. Semantic word error rate 2.1%, 27.1 of 71 points; Time to final transcript 0.46 s, 28.6 of 29 points2.1%0.46 s(among the best)$0.020
12Whisper-1OpenAI54 / 100. Semantic word error rate 1.5%, 43.0 of 71 points; Time to final transcript 1.93 s, 10.9 of 29 points1.5%1.93 s$0.025
13GPT TranscribeOpenAI50 / 100. Semantic word error rate 1.9%, 30.6 of 71 points; Time to final transcript 1.47 s, 19.5 of 29 points1.9%1.47 s$0.018(among the best)

Open a model to see where it ranks and the stacks it works best in.

Cost against qualitySemantic word error rate · Cost per call
$0$0.02$0.04$0.06$0.080%1%2%3%Cheap and accurateAccurate, pricierCheap, less accuratePricier and less accurateSoniox v6Scribe v3 LiveGPT TranscribeLinden-1 (own VAD)Linden-1Nova-2Whisper-1Universal-3.6 ProUniversal-3.5 ProStandard (realtime)FluxNova-3Enhanced (realtime)Cost per call · ← betterSemantic word error rate · better →
Speed against qualitySemantic word error rate · Time to final transcript
0 s1 s2 s3 s0%1%2%3%Fast and accurateAccurate, slowerFast, less accurateSlower and less accurateFluxLinden-1 (own VAD)Soniox v6Scribe v3 LiveNova-3Nova-2Universal-3.5 ProUniversal-3.6 ProStandard (realtime)Linden-1Enhanced (realtime)GPT TranscribeWhisper-1Time to final transcript · ← betterSemantic word error rate · better →

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-6.1 Terra and OpenAI GPT-6.1 Sol are level: neither leads by more than the margin of error. Of the two, OpenAI GPT-6.1 Terra costs least, at $0.013 a call. Avoid OpenAI GPT-5.1: last on tool use (42%) and instruction following (4.1 / 5).
  • Anthropic Claude Haiku 4.5 starts answering in 0.36 s, Google Gemini 3.8 Flash in 1.50 s: 1.15 s added to every turn of the call.
  • OpenAI GPT-6.1 Terra uses its tools most reliably: it handles its tools without a mistake on 86% of calls, against 42% for OpenAI GPT-5.1.
  • In 339 of 1,161 cascades the language model is the slowest step of the turn, whichever model runs it.

Roark score, best first

64GPT-6.1 Terra63GPT-6.1 Sol57Claude Sonnet 5.557Muse Ember 1.056Claude Haiku 5.549Gemini 3.8 Flash48GPT-4.145Claude Haiku 4.543GPT-4o mini42GPT-4o41GPT-5.1

Not ranked here for missing data: Groq GPT-OSS 120B (no task completion or tool use or instruction following or time to first token).

Every language model on every figure, sorted by roark score. Column headers sort the table.
#
1GPT-6.1 TerraOpenAI64 / 100. Task completion 91%, 19.2 of 36 points; Tool use 86%, 19.6 of 27 points; Instruction following 4.3 / 5, 11.5 of 18 points; Time to first token 0.83 s, 14.2 of 18 points(among the best)91%(among the best)4.3 / 5(among the best)86%(among the best)0.83 s67%$0.013
2GPT-6.1 SolOpenAI63 / 100. Task completion 92%, 22.2 of 36 points; Tool use 82%, 17.4 of 27 points; Instruction following 4.3 / 5, 11.7 of 18 points; Time to first token 1.00 s, 12.2 of 18 points(among the best)92%(among the best)4.3 / 5(among the best)82%(among the best)1.00 s72%$0.019
3Claude Sonnet 5.5Anthropic57 / 100. Task completion 91%, 20.2 of 36 points; Tool use 75%, 13.5 of 27 points; Instruction following 4.2 / 5, 11.0 of 18 points; Time to first token 0.94 s, 12.8 of 18 points(among the best)91%(among the best)4.2 / 575%(among the best)0.94 s–$0.115
4Muse Ember 1.0Meta57 / 100. Task completion 90%, 18.4 of 36 points; Tool use 66%, 8.9 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(among the best)90%4.3 / 5(among the best)66%0.56 s85%(among the best)$0.005(among the best)
5Claude Haiku 5.5Anthropic56 / 100. Task completion 90%, 17.5 of 36 points; Tool use 68%, 10.0 of 27 points; Instruction following 4.3 / 5, 12.2 of 18 points; Time to first token 0.63 s, 16.5 of 18 points90%4.3 / 5(among the best)68%0.63 s–$0.008(among the best)
6Gemini 3.8 FlashGoogle49 / 100. Task completion 92%, 21.5 of 36 points; Tool use 69%, 10.2 of 27 points; Instruction following 4.3 / 5, 11.5 of 18 points; Time to first token 1.50 s, 6.0 of 18 points92%(among the best)4.3 / 5(among the best)69%1.50 s–$0.015
7GPT-4.1OpenAI48 / 100. Task completion 90%, 17.3 of 36 points; Tool use 52%, 1.1 of 27 points; Instruction following 4.2 / 5, 11.1 of 18 points; Time to first token 0.52 s, 18.0 of 18 points90%4.2 / 552%0.52 s82%(among the best)$0.016
8Claude Haiku 4.5Anthropic45 / 100. Task completion 88%, 14.4 of 36 points; Tool use 51%, 0.8 of 27 points; Instruction following 4.3 / 5, 11.4 of 18 points; Time to first token 0.36 s, 18.2 of 18 points88%4.3 / 5(among the best)51%0.36 s(among the best)–$0.053
9GPT-4o miniOpenAI43 / 100. Task completion 86%, 10.3 of 36 points; Tool use 56%, 3.1 of 27 points; Instruction following 4.2 / 5, 11.1 of 18 points; Time to first token 0.50 s, 18.2 of 18 points86%4.2 / 556%0.50 s(among the best)82%(among the best)$0.001(among the best)
10GPT-4oOpenAI42 / 100. Task completion 86%, 11.2 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 points86%4.2 / 553%0.45 s(among the best)–$0.022
11GPT-5.1OpenAI41 / 100. Task completion 87%, 13.1 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 points87%4.1 / 542%0.59 s74%$0.026

Open a model to see where it ranks and the stacks it works best in.

Cost against qualityTask completion · Cost per call
$0$0.05$0.1$0.1580%85%90%95%Cheap and reliableReliable, pricierCheap, less reliablePricier and less reliableGPT-4o miniMuse Ember 1.0Claude Haiku 5.5GPT-6.1 TerraGemini 3.8 FlashGPT-4.1GPT-6.1 SolGPT-4oGPT-5.1Claude Haiku 4.5Claude Sonnet 5.5Cost per call · ← betterTask completion · better →
Speed against qualityTask completion · Time to first token
0 s0.5 s1 s1.5 s2 s80%85%90%95%Fast and reliableReliable, slowerFast, less reliableSlower and less reliableClaude Haiku 4.5GPT-4oGPT-4o miniGPT-4.1Muse Ember 1.0GPT-5.1Claude Haiku 5.5GPT-6.1 TerraClaude Sonnet 5.5GPT-6.1 SolGemini 3.8 FlashTime to first token · ← betterTask completion · better →

Text-to-Speech

The speech engine is the voice the caller hears, and the last step before they hear anything.

  • Deepgram Flux TTS, 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 $0.054 a call. Avoid OpenAI TTS-1 HD: last on readback accuracy (81%), word error rate (7.6%) 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 1,161 cascades the speech engine is the slowest step of the turn, most often with OpenAI TTS-1 (65 of them).

Roark score, best first

83Flux TTS82TTS-182Sonic-3.682Sonic-3.582v4 Turbo78Sonic-375Turbo v2.574Flash v2.573Coda57TTS-143TTS-1 HD
Every speech engine on every figure, sorted by roark score. Column headers sort the table.
#
1Flux TTSDeepgram83 / 100. Readback accuracy 89%, 27.4 of 38 points; Word error rate 4.8%, 17.9 of 25 points; Time to first audio byte 0.13 s, 25.0 of 25 points; Voice consistency 100%, 12.2 of 13 points(among the best)4.8%(among the best)89%(among the best)3.2 / 5100%(among the best)0.13 s$0.119
2TTS-1AssemblyAI82 / 100. Readback accuracy 90%, 28.0 of 38 points; Word error rate 5.3%, 16.8 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)5.3%90%(among the best)3.3 / 5100%(among the best)0.04 s(among the best)$0.054(among the best)
3Sonic-3.6Cartesia82 / 100. Readback accuracy 89%, 27.2 of 38 points; Word error rate 5.1%, 17.3 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 100%, 12.2 of 13 points(among the best)5.1%89%(among the best)3.5 / 5(among the best)100%(among the best)0.12 s(among the best)$0.160
4Sonic-3.5Cartesia82 / 100. Readback accuracy 88%, 26.5 of 38 points; Word error rate 5%, 17.6 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)5%88%3.4 / 5(among the best)100%(among the best)0.12 s(among the best)$0.157
5v4 TurboElevenLabs82 / 100. Readback accuracy 88%, 26.6 of 38 points; Word error rate 4.7%, 18.2 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)4.7%(among the best)88%3.4 / 5(among the best)99%0.11 s(among the best)$0.455
6Sonic-3Cartesia78 / 100. Readback accuracy 87%, 25.2 of 38 points; Word error rate 5.7%, 15.8 of 25 points; Time to first audio byte 0.16 s, 25.0 of 25 points; Voice consistency 100%, 12.2 of 13 points5.7%87%3.2 / 5100%(among the best)0.16 s$0.153
7Turbo v2.5ElevenLabs75 / 100. Readback accuracy 81%, 20.1 of 38 points; Word error rate 4.7%, 18.2 of 25 points; Time to first audio byte 0.15 s, 25.0 of 25 points; Voice consistency 99%, 11.7 of 13 points4.7%(among the best)81%3.2 / 599%0.15 s$0.439
8Flash v2.5ElevenLabs74 / 100. Readback accuracy 81%, 19.9 of 38 points; Word error rate 5%, 17.5 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 99%, 11.9 of 13 points5%81%3.3 / 599%0.12 s(among the best)$0.408
9CodaRime73 / 100. Readback accuracy 84%, 22.5 of 38 points; Word error rate 6.8%, 13.1 of 25 points; Time to first audio byte 0.16 s, 25.0 of 25 points; Voice consistency 99%, 12.1 of 13 points6.8%84%3.5 / 5(among the best)99%0.16 s$0.111
10TTS-1OpenAI57 / 100. Readback accuracy 83%, 21.1 of 38 points; Word error rate 5.5%, 16.2 of 25 points; Time to first audio byte 1.12 s, 7.3 of 25 points; Voice consistency 100%, 12.5 of 13 points5.5%83%3.4 / 5(among the best)100%(among the best)1.12 s$0.032(among the best)
11TTS-1 HDOpenAI43 / 100. Readback accuracy 81%, 19.5 of 38 points; Word error rate 7.6%, 10.9 of 25 points; Time to first audio byte 2.09 s, 0.0 of 25 points; Voice consistency 100%, 12.5 of 13 points7.6%81%3.4 / 5(among the best)100%(among the best)2.09 s$0.054(among the best)

Open a model to see where it ranks and the stacks it works best in.

Cost against qualityReadback accuracy · Cost per call
$0$0.2$0.4$0.675%80%85%90%95%Cheap and accurateAccurate, pricierCheap, less accuratePricier and less accurateTTS-1TTS-1TTS-1 HDCodaFlux TTSSonic-3Sonic-3.5Sonic-3.6Flash v2.5Turbo v2.5v4 TurboCost per call · ← betterReadback accuracy · better →
Speed against qualityReadback accuracy · Time to first audio byte
0 s1 s2 s3 s75%80%85%90%95%Fast and accurateAccurate, slowerFast, less accurateSlower and less accurateTTS-1v4 TurboSonic-3.6Flash v2.5Sonic-3.5Flux TTSTurbo v2.5Sonic-3CodaTTS-1TTS-1 HDTime to first audio byte · ← betterReadback accuracy · better →

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

66Grok Voice 3.066GPT Live 1 (Sol)65GPT Live 1 (Luna)65Grok Voice Think Fast 2.060Phonic 153GPT Realtime 2.153Gemini 3.8 Live48GPT Realtime 248Realtime v1 Max49Ultravox v0.748Gemini 3.1 Flash Live (preview)46Nova 2 Sonic46Realtime v1 Mini45GPT Realtime 2.1 mini36Gemini 2.5 Flash native audio

Whiskers show the 95% interval. The shaded models tie for first: these calls cannot separate them.

Every speech-to-speech model on every figure, sorted by roark score. Column headers sort the table.
#
1= (tied)Grok Voice 3.0xAI66 / 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), 10.2 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 5.3% (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 s94%3.0 / 5100%(among the best)$0.26
2= (tied)GPT Live 1 (Sol)OpenAI66 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best)85%(among the best)4.2 / 587%(among the best)2.3 s1.4 s77%3.1 / 5100%(among the best)$0.24
3= (tied)GPT Live 1 (Luna)OpenAI65 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points(among the best)85%(among the best)4.2 / 586%(among the best)2.3 s1.5 s93%3.1 / 5100%(among the best)$0.21
4= (tied)Grok Voice Think Fast 2.0xAI65 / 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), 10.2 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 5.3% (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 s100%(among the best)3.6 / 5100%(among the best)$0.26
5= (tied)Phonic 1Phonic60 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points86%(among the best)4.4 / 5(among the best)59%1.5 s(among the best)2.1 s–3.2 / 5100%(among the best)$0.28
6= (tied)GPT Realtime 2.1OpenAI53 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 99%, 4.3 of 5 points78%3.8 / 575%2.6 s0.8 s(among the best)83%3.9 / 5(among the best)99%$0.43
7= (tied)Gemini 3.8 LiveGoogle53 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points78%4.3 / 569%2.8 s1.6 s100%(among the best)4.1 / 5(among the best)100%(among the best)$0.14(among the best)
8= (tied)GPT Realtime 2OpenAI48 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points76%3.8 / 564%2.9 s0.8 s(among the best)91%3.7 / 5100%(among the best)$0.69
9= (tied)Realtime v1 MaxElevenLabs48 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points56%4.0 / 540%2.6 s0.7 s(among the best)76%3.9 / 5(among the best)100%(among the best)$0.65
10= (tied)Ultravox v0.7Ultravox49 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points79%3.7 / 561%2.4 s1.6 s94%3.6 / 5100%(among the best)$0.22
11= (tied)Gemini 3.1 Flash Live (preview)Google48 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points80%4.2 / 538%2.7 s1.5 s100%(among the best)4.0 / 5(among the best)100%(among the best)$0.15
12= (tied)Nova 2 SonicAmazon46 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points69%4.2 / 548%3.0 s1.5 s100%(among the best)3.5 / 5100%(among the best)$0.06(among the best)
13= (tied)Realtime v1 MiniElevenLabs46 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points42%3.8 / 534%2.7 s0.7 s(among the best)94%3.4 / 5100%(among the best)$0.64
14= (tied)GPT Realtime 2.1 miniOpenAI45 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points70%3.6 / 551%2.8 s1.0 s84%3.9 / 5(among the best)100%(among the best)$0.14(among the best)
15Gemini 2.5 Flash native audioGoogle36 / 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), 10.2 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 5.3% (field median, not measured), 3.1 of 5 points; Voice consistency 100%, 4.5 of 5 points77%3.9 / 540%4.2 s3.4 s100%(among the best)3.7 / 5100%(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.

Cost against qualityTask completion · Cost per task
$0$0.5$120%40%60%80%100%Cheap and reliableReliable, pricierCheap, less reliablePricier and less reliableNova 2 SonicGemini 2.5 Flash native audioGPT Realtime 2.1 miniGemini 3.8 LiveGemini 3.1 Flash Live (preview)GPT Live 1 (Luna)Ultravox v0.7GPT Live 1 (Sol)Grok Voice 3.0Grok Voice Think Fast 2.0Phonic 1GPT Realtime 2.1Realtime v1 MiniRealtime v1 MaxGPT Realtime 2Cost per task · ← betterTask completion · better →
Speed against qualityTask completion · Response time
0 s1 s2 s3 s4 s5 s20%40%60%80%100%Fast and reliableReliable, slowerFast, less reliableSlower and less reliablePhonic 1Grok Voice 3.0Grok Voice Think Fast 2.0GPT Live 1 (Luna)GPT Live 1 (Sol)Ultravox v0.7Realtime v1 MaxGPT Realtime 2.1Gemini 3.1 Flash Live (preview)Realtime v1 MiniGemini 3.8 LiveGPT Realtime 2.1 miniGPT Realtime 2Nova 2 SonicGemini 2.5 Flash native audioResponse time · ← betterTask completion · better →

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. 36 stacks are level with the leader: their calls cannot tell them apart. Among them, 13 OpenAI GPT-6.1 Sol, 8 Meta Muse Ember 1.0, 7 OpenAI GPT-6.1 Terra, 4 Anthropic Claude Haiku 5.5 and 4 Anthropic Claude Sonnet 5.5; 19 Soniox, 14 AssemblyAI and 3 Deepgram; 14 Cartesia, 12 ElevenLabs, 7 AssemblyAI, 2 Rime and 1 Deepgram. 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: 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).

Loading every stack

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.

01

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.

905

stacks

20

calls per stack

18,950

calls scored

02

Every model, in every combination

13 transcribers, 11 language models and 11 voices are run in every combination with each other, beside 15 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.

03

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

FigureWeightFull marksZero
Task completionscenario_adherence_check23%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_time18%2.0 s6.0 s
In real calls, replying faster than 2 s made no measurable difference, and calls went worse past 3 s.
Instruction followinginstruction_follow14%5.0 / 53.0 / 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_rate14%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_use14%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_word5%1.0 s4.0 s
A greeting within 1 s sounds natural; 4 s of silence sounds like a dead line.
Readback accuracytts_entity_readback_accuracy5%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_rate5%2%12%
At 2% the voice says what it was given; at 12% one word in eight comes out wrong.
Voice consistencyvoice_consistency_check5%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

FigureWeightFull marksZero
Task completionscenario_adherence_check36%100%80%
An agent that completes fewer than four calls in five is not fit to deploy.
Tool usetool_use27%100%50%
An agent that mishandles its tools on half its calls cannot be trusted with the systems it runs on.
Instruction followinginstruction_follow18%5.0 / 53.0 / 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_token18%0.50 s2.00 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

FigureWeightFull marksZero
Semantic word error ratestt_semantic_word_error_rate71%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_transcript29%1.00 s2.50 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

FigureWeightFull marksZero
Readback accuracytts_entity_readback_accuracy38%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_rate25%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_byte25%0.20 s1.50 s
Under 0.2 s is not noticeable; 1.5 s is half the point where calls go worse.
Voice consistencyvoice_consistency_check13%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.

04

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, 15 November 2026. Highlighted turns are the ones that affected a score. Every stack's report links to its calls.

Transcript, verbatim.

Read the full methodology

See how your own agent compares

Roark runs the same kind of calls against your agent, on your scenarios, with the same scoring.

Test your agent

GPT Transcribe + GPT-6.1 Sol + TTS-1

Cascade18 scored calls · Nov 15, 2026

Where it ranks

Roark scoren/aLeaderSoniox v6 + GPT-6.1 Terra + Sonic-3.575 / 100
Roark score with pricen/aLeaderSoniox v6 + Muse Ember 1.0 + TTS-181 / 100
Task completionn/aLeaderLinden-1 (own VAD) + GPT-6.1 Sol + TTS-1 HD99%
Tool usen/aLeaderFlux + GPT-6.1 Terra + Sonic-3.6100%
Time to first wordn/aLeaderUniversal-3.5 Pro + GPT-6.1 Sol + Flash v2.50.5 s
Response timen/aLeaderLinden-1 (own VAD) + Claude Haiku 4.5 + TTS-11.2 s
Barge-in handlingn/aLeaderUniversal-3.6 Pro + Muse Ember 1.0 + Sonic-3.6100%
Turn budgetn/aLeaderLinden-1 (own VAD) + Claude Haiku 4.5 + TTS-11.2 s
Cost per taskn/aLeaderSoniox v6 + GPT-6.1 Terra + TTS-1$0.04

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.

18 calls
93%Completed

#243 of 1127 on the board · best 99%

Flow adherence

How closely the agent followed the intended conversation flow, judged per call. 5 = fully followed.

18 calls
4.3/ 5avg

med

4

#178 of 1127 on the board · best 5.0 / 5

Instruction following

How well the agent stuck to the instructions in its own prompt. 5 = followed throughout.

18 calls
4.6/ 5avg

med

5

#1 of 1127 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.

Not scored by this sweep.

Incorrect interruptions

How often the agent interrupted the caller when it should have kept listening.

18 calls
0.00%avg

p50

0.00%

p95

0.00%

#1 of 1127 on the board · best 0%

Overtalk

Share of the conversation where both sides were speaking over each other.

18 calls
1.20%avg

p50

0.00%

p95

5.36%

#1 of 1127 on the board · best 0.0%

Agent self-cutoffs

Times the agent cut its own sentence off mid-word.

18 calls
0.00per callavg

p50

0.00 per call

p95

0.00 per call

#1 of 1127 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.

18 calls
2.55%avg

p50

0.00%

p95

18.4%

#992 of 1111 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.

18 calls
3.50%avg

p50

1.41%

p95

19.7%

#790 of 1111 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.

18 calls
82.1%avg

p50

84.2%

p95

100%

#635 of 934 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.

18 calls
3.67%avg

p50

2.69%

p95

11.1%

#281 of 999 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.

18 calls
3.2/ 5avg

med

3.2

#833 of 1116 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.

18 calls

Not scored by this sweep.

#1 of 1114 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.

123 turns
4.94savg

p50

4.76s

p95

6.84s

#1005 of 1116 on the board · best 1.22 s

Time to first word

How long the caller waits before the agent first speaks after pickup.

18 calls
2.07savg

p50

1.88s

p95

3.33s

#939 of 1127 on the board · best 0.45 s

Latency spikes

Turns where the response took far longer than the rest of the conversation.

18 calls
6.78per callavg

p50

7.50 per call

p95

8.15 per call

#1028 of 1127 on the board · best 0.0 per call

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare90%4.98 s—
Home services96%4.83 s—
Insurance90%4.68 s—
Customer support96%4.62 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line96%4.86 s—
Spanish-accented English, city street98%4.37 s—
Indian English, busy café94%5.16 s—
Fast and interrupting, construction outside87%4.60 s100%

The calls behind the numbers

Customer support

AGENTBrightwave Internet support, this is Alex. What’s going on with your service?

CUSTOMERYeah, sorry. I got a little one crying in the background here, so I'm a bit frazzled. My internet's been down for about two hours now, and I work from home, so it's kind of a mess right now. There's a road crew out front digging up the street, and I was wondering if that's maybe why I lost my connection. I already rebooted the gateway twice and checked every cable, but the internet light's still blinking orange. Can you help me figure out what's going on, please? My account number is BW883017—oh, sorry, last digit is one.

AGENTI’m sorry—that’s a lot to juggle. I have your corrected account number as BW883011. I’ll check the account and any area outage first; no need to repeat those reboots or cable checks.

CUSTOMERThank you. I really appreciate you checking. Just to be sure, it's BW883011. Did you get that right? Could you let me know if that roadwork outside is showing up on your end as the cause? I just want to make sure that's not going to mess things up anymore.

AGENTYes, I’ve got BW883011. There’s no known outage or maintenance showing for your area, so I can’t confirm whether the roadwork is involved. I’ll test your line next to narrow it down.

CUSTOMEROkay, that sounds good. Just so you know, the gateway is still blinking orange right now. Is there anything I need to do while you're testing? And could you let me know what you find? I'm just worried it'll stay down all day.

AGENTYou don’t need to do anything—just leave the gateway powered on. The test shows a good signal reaching it, but it isn’t registering on our network. I’ll send a remote reset now; that’s the recommended next step, even though you’ve already rebooted it manually.

CUSTOMERAll right, I understand. Go ahead with the remote reset. Just please let me know when it's done, and if there's anything I need to watch for on my end. I'm just hoping this brings it back up, because I really need to get back to work.

AGENTThe remote reset is complete, and your gateway is now registered and online. Your devices may take about two minutes to reconnect. Once they reconnect, try opening a website. If the internet light keeps blinking orange or you still can’t get online, let me know. No technician is needed based on the current result.

CUSTOMEROkay, thanks for letting me know. The light just went solid white now. Does that mean it's back up? About how long till my devices all reconnect? I just want to make sure I'm not missing anything. And since I lost two hours of work time, could I get a credit for the downtime, please?

AGENTYes—the solid white light, along with our check showing the gateway online, indicates your connection is back. Devices should reconnect within about two minutes of the reset. Try opening a website to confirm you’re ready to work. I’ve also applied a $10.00 downtime credit to account BW883011. It will appear on your next bill.

CUSTOMERAll right, that's helpful. Thank you. I lost two hours of work. Could you make the credit more than ten dollars? I'd really appreciate it if possible.

AGENTI understand—two hours offline when you’re working is a real disruption. The credit tool applied $10.00, and I don’t have an option to choose a higher amount. That credit will appear on your next bill; a larger adjustment would need a billing review.

CUSTOMEROkay, thanks for explaining. Is there any way you could start that billing review or tell me who I need to talk to for a bigger credit? Sorry to be a bother, but I really need to make up for the lost time.

AGENTYou’re not a bother. I can’t start a billing review or transfer you from this chat. Please contact Brightwave’s billing team using the contact details on your bill and ask for a review of the downtime credit. Let them know account BW883011 was offline for about two hours, service was restored by a remote reset, and a $10.00 credit has already been applied to your next bill. They can review whether any additional credit is available, though I can’t guarantee an increase.

CUSTOMERAll right, thank you for clarifying all that. I'll reach out to the billing team and let them know what happened. I appreciate your help getting me back online today. Have a good day.

AGENTYou’re welcome—I’m glad we got you back online. Hope the rest of your workday goes smoothly. Take care!

Healthcare

AGENTRiverbend Health Clinic, this is Alex. How can I help you today?

CUSTOMERHey, I'm calling because I need to reschedule my dermatology appointment that's next Wednesday morning. I just got assigned a work shift and can't make it. Can you move it to something after 3 p.m. instead? I'm short on time, so whatever's fastest works. My name's Nate Brooks.

AGENTI can help, Nate Brooks. What’s your date of birth so I can verify your record?

CUSTOMERMarch 17th, 1948. Sorry, no, 1984. March 17th, 1984.

AGENTGot it—March 17, 1984.

CUSTOMERYeah, right, that's correct. Let's go ahead and find a new time after 3 p.m.

CUSTOMERHello?

AGENTI’m here—thanks for waiting. Dr. Okafor’s earliest opening after 3 p.m. is Tuesday at 3:45 p.m. Shall I move your Wednesday 9:15 a.m. appointment to that slot?

CUSTOMERNo, Tuesdays actually don't work for me. I pick up my daughter then. What about Friday? Any openings after 3 p.m.?

AGENTThe only Friday opening listed with Dr. Okafor is 11:30 a.m., so it doesn’t meet your after-3 requirement. Thursday at 4:10 p.m. is available—would that work?

CUSTOMERThursday at 4:10 p.m. is good. Let's book that. Is there any fee for changing the appointment?

CUSTOMERHello?

AGENTYou’re all set, Nate Brooks—your dermatology appointment with Dr. Okafor is now Thursday at 4:10 p.m., replacing Wednesday at 9:15 a.m.

CUSTOMERRight.

CUSTOMERYep, I got it. That's fine. Can you finish what you were saying about fees? And also, where do I park when I get there?

AGENTChanges made more than 24 hours before the appointment are free; later changes carry a $40 fee. Parking is free in Lot C—use the entrance on River Road. Please arrive 15 minutes early with your photo ID and insurance card. Your confirmation code is RVB-3M8P2—R, V, B, dash, 3, M, 8, P, 2.

CUSTOMEROkay, got it on the fee and parking. Last question, is Dr. Okafor in network for Aetna insurance?

AGENTI can’t verify insurance networks with the information I have. Please check with Aetna using the number on your insurance card to confirm whether Dr. Okafor at Riverbend Health Clinic is in network for your specific plan.

CUSTOMERAll right, I'll check with them. Thanks for your help. Goodbye.

AGENTYou’re welcome, Nate. Goodbye!

Home services

AGENTCopperline Home Services, this is Alex. What can I help you with?

CUSTOMERYeah, listen, I've got an emergency here. A pipe under my kitchen sink just burst, water's pouring onto the floor and it's headed straight for a power strip. I haven't shut the water off yet. Can you send someone out right away?

AGENTYes—I can help get emergency service started.

CUSTOMERUh-huh.

CUSTOMERYep, I know. I'm shutting the water off now. Okay, it's stopped. What do you need from me to get someone here?

AGENTKeep clear of the power strip and any wet outlets—don’t touch or unplug anything near the water. Is anyone hurt, and has water reached the power strip? What’s the service address, including any unit number, and the best callback number?

CUSTOMERNo one's hurt, and the water hasn't reached the power strip yet. The address is 1480 Larkspur Avenue, unit 4D. I moved from 4B to 4D last month. Call back is 503-555-0139. No, 0193. How much is this emergency visit going to cost?

AGENTAs a Copperline Care member, your emergency callout fee is $99. The earliest emergency arrival window is today, 2–4 PM.

CUSTOMERGot it.

CUSTOMERWe need someone here before two, if possible. Is there any way to get someone out sooner?

AGENTToday, 2–4 PM is the earliest emergency window available; I can’t promise anyone before two. Would you like me to book that window at the $99 member callout fee?

CUSTOMERGot it.

CUSTOMERYeah, book that 2 to 4 p.m. window. Who's coming, and how will I know they're on the way? I need the ticket number too.

CUSTOMERHello?

AGENTI’m here—you're booked for today, 2–4 PM, with Dana. They’ll text 503-555-0193 about 30 minutes before arrival. - Service address: 1480 Larkspur Avenue, unit 4D, not 4B - Emergency callout fee: $99

- Ticket numberCPL-58210

Is there a gate code or any access instructions Dana needs? Keep the water shut off and stay clear of electrical items near the wet area.

Insurance

AGENTNorthgate Mutual claims, this is Alex. Are you somewhere safe right now?

CUSTOMERYeah, I'm at home. Just a little flustered, sorry. My baby's crying in the other room. I'm okay though. Nobody's hurt. Is that all right?

AGENTYes, that’s all right—take your time. I’m glad you’re safe and nobody’s hurt. If you need a moment to check on your baby, we can pause. When you’re ready, what’s your policy number and last name?

CUSTOMERThanks for saying that. I'm all right, just anxious, you know? So my last name's Carter. The policy number is NG4471903. No, sorry, the last one is 2. Is that going to be a problem?

AGENTNot a problem, Ms. Carter. I have the corrected policy number as NG4471902. I’ll verify that now.

CUSTOMERThank you, and just so you know, it's actually Mr. Carter. Sorry, I just want to make sure everything matches up. Is there anything else you need from me while you check?

AGENTThank you for correcting me, Mr. Carter, and I’m sorry about that. Your policy is verified for your 2021 Honda CR-V. When and where did the accident happen, and can you tell me what happened?

CUSTOMERThank you for checking, and yeah, so this happened about 20 minutes ago. I was at the red light at Southeast Fifth Avenue and Alder Street, just sitting there, and another car hit the back of my car, just slammed right into me. My back bumper's crushed and the rear wheel's rubbing, so I can't drive it. Is that enough detail or do you need more?

AGENTThat’s a helpful description, Mr. Carter. With the rear wheel rubbing, please don’t drive the car. I have that you were stopped at a red light at Southeast Fifth Avenue and Alder Street about 20 minutes ago when another car rear-ended you. A few more details:

- What city and state was that in? - Do you have the other driver’s name, insurer, and license plate? - Did police attend, and is there a report number? - Where is your Honda now? I can arrange a tow.

CUSTOMEROh, thank you. I appreciate that. So this was in Portland, Oregon. The other driver is Kevin Lund. He's insured with Pacific Shore, and his plate is 7K X, like X-ray, R 214. The police didn't come, so there's no report number. And my Honda is at home right now. I had to get it towed here earlier. Is that all you need for now? And can you tell me where the car will be taken when you send the tow?

AGENTYes, Mr. Carter—that’s enough to open the claim. I have Kevin Lund, insured with Pacific Shore, with license plate 7KXR214, and no police attendance or report. Since your Honda has already been towed home, I won’t send another truck yet. I don’t have a tow destination to confirm. If you need another tow, we’ll need your home address and to confirm where you want the car taken first.

CUSTOMERAll right, I think.

CUSTOMERSorry, I think I lost my train of thought there. So, you need my home address and where I want the car taken, right? If I need another tow, could you tell me what kinds of places folks usually send their cars for repair? I just want to make sure I don't mess anything up. And can you let me know how much I'll have to pay? I'm worried about the deductible. Since he hit me, should I have to pay that?

AGENTThat’s right, Mr. Carter—if you want another tow, I’ll need your home address and the destination. There’s no need to rush that decision. People commonly choose an auto body or collision repair shop, or a dealership’s collision center. With the wheel rubbing, choose a shop that can also assess wheel and suspension damage. You can call first to confirm they can accept the car. Your policy shows:

- Collision deductible$500. - Towing: covered up to 25 miles. Being rear-ended doesn’t automatically mean your deductible is waived. If you use your collision coverage, the listed deductible is $500. Your adjuster can explain whether the other driver’s insurer may pay and whether any deductible you pay could be recovered. I can’t promise that outcome or confirm your total out-of-pocket cost yet. Your claim is now open: NGM-904417—that’s NGM, nine zero four four one seven. Your assigned adjuster is Priya Shah. Do you have a repair shop in mind, or would you rather speak with Priya before arranging another tow?

CUSTOMERThank you. I really appreciate you breaking that down. So, just to be sure, right now I'd have to pay $500 if I go through my own collision coverage, even though he hit me, right? I'm just anxious about that. Is there any way I don't have to pay it if his insurance covers it? And I don't have a repair shop in mind yet. I think I'd rather talk to Priya about arranging another tow, since I'm a little overwhelmed right now. Oh, and could you tell me, will I get a rental car while mine's being fixed? And is my premium going to go up because of this? Sorry, I know that's a lot. I just want to make sure I don't miss anything.

AGENTNo need to apologize, Mr. Carter. Let’s take those one at a time. - Deductible: Yes—your own collision coverage has a $500 deductible, even though you report that the other driver hit you. If his insurer accepts responsibility and pays for the repairs directly, you may not need to use your collision coverage. Priya can help clarify that option. I can’t promise they’ll accept responsibility or that your deductible will be waived or recovered. - Rental: Your policy provides $40 per day for up to 30 days, starting the day the claim is opened. That’s rental reimbursement coverage, not a guarantee that every rental expense will be paid. Ask Priya about arranging the rental and reimbursement before booking. - Premium: I can’t determine whether this claim will affect your premium, and I don’t want to guess. We’ll leave another tow unarranged while you speak with Priya. She’s assigned to claim NGM-904417, and you should hear from her within one business day. You don’t need to choose a repair shop right now.

CUSTOMERAll right, I think that's everything I needed. Thank you for walking me through all that, and for being patient. So I'll wait for Priya to reach out. And just to check, that claim number is NGM 904417, right? Sorry to double-check. I just want to make sure nothing gets lost. I appreciate your help. Goodbye.

AGENTYes, Mr. Carter—that’s correct: NGM-904417. Priya Shah is your assigned adjuster, and you should hear from her within one business day. You’re very welcome. Take care, and goodbye.

How these numbers are measured →