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

Soniox v6 + Claude Haiku 5.5 + TTS-1

Cascade20 scored calls · Nov 13, 2026

Rank on Roark score

#1of 903 stacks

72 / 100

The leader

Where it ranks

Roark score with price77 / 1001 of 903Leads
Task completion91%444 of 905LeaderLinden-1 (own VAD) + GPT-6.1 Sol + TTS-1 HD99%
Tool use74%225 of 881LeaderFlux + GPT-6.1 Terra + Sonic-3.6100%
Time to first word0.6 s54 of 905LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Flash v2.50.5 s
Response time2.5 s108 of 903LeaderLinden-1 (own VAD) + Claude Haiku 4.5 + TTS-11.2 s
Barge-in handling97%421 of 517LeaderUniversal-3.6 Pro + Muse Ember 1.0 + Sonic-3.6100%
Turn budget2.5 s89 of 833LeaderLinden-1 (own VAD) + Claude Haiku 4.5 + TTS-11.2 s
Cost per task$0.0730 of 903LeaderSoniox 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.

20 calls
91%Completed

#483 of 1127 on the board · best 99%

Flow adherence

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

20 calls
4.5/ 5avg

med

5

#1 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.

20 calls
4.7/ 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.

29 barge-ins
97%Handled correctly(28/29 barge-ins)

#549 of 658 on the board · best 100%

Incorrect interruptions

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

20 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.

20 calls
2.11%avg

p50

0.42%

p95

8.59%

#736 of 1127 on the board · best 0.0%

Agent self-cutoffs

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

20 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

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.

27 calls
0.52per callavg

p50

0.00 per call

p95

1.00 per call

#1 of 810 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.

20 calls
0.38%avg

p50

0.00%

p95

2.03%

#100 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.

20 calls
0.98%avg

p50

0.39%

p95

4.20%

#52 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.

20 calls
85.6%avg

p50

89.9%

p95

100%

#506 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.

20 calls
3.06%avg

p50

1.50%

p95

13.4%

#174 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.

20 calls
3.2/ 5avg

med

3.2

#692 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.

20 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.

156 turns
2.54savg

p50

2.50s

p95

3.76s

#160 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.

20 calls
0.60savg

p50

0.65s

p95

0.98s

#66 of 1127 on the board · best 0.45 s

Latency spikes

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

20 calls
1.65per callavg

p50

1.00 per call

p95

4.05 per call

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

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare89%2.60 s—
Home services95%2.20 s—
Insurance92%2.10 s—
Customer support87%2.87 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line86%2.73 s—
Spanish-accented English, city street96%2.57 s—
Indian English, busy café90%2.64 s—
Southern US, flustered, crying baby98%2.65 s—
Fast and interrupting, construction outside83%2.08 s96%

The calls behind the numbers

Customer support

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

CUSTOMERHi, Alex. My internet has been down for about 2 hours. I work from home, so it's pretty disruptive. There's a road crew digging up the street outside, so I wanted to ask if that might be the cause. I already rebooted my gateway twice and checked every cable. The internet light is blinking orange. Can you help me get this resolved?

AGENTI'm sorry about the disruption, and that's a reasonable thing to suspect with the road crew. Let me pull up your account first. Can you give me your account number or the phone number on the account?

CUSTOMERSure. My account number is BW883011. Sorry, last digit is 1, or the phone number is 320-703-3893.

AGENTI've found your account, BW-883011, on the Brightwave 500 plan. There's no known outage in your area, so let's run a line test to check the connection from the network to your gateway.

AGENTThe line test shows a good signal to your gateway,

CUSTOMEROkay. Okay, but the internet light is still blinking orange. Since there's a road crew outside, could they have caused something that wouldn't show up on your test? What else can we try?

AGENTI understand the frustration. The reset reported your gateway as registered and online, but you're still seeing an orange blink, so I don't want to assume it's fixed. The orange light may just be the gateway still reconnecting, since devices can take about two minutes after a reset. If it's still orange after a few minutes, that's a sign the problem is on our side of the line, and the road work could be the reason. Our line test came back clean, so I can't confirm damage from here. The next step is a technician visit, which I can schedule now to check the line where the crew is working. Would you like me to look up available windows?

CUSTOMERActually, I already rebooted the gateway twice before calling. The light's been orange for a couple hours, not just a few minutes. Can you try resetting it remotely from your end? If that doesn't work, then, yeah, let's talk about getting a tech out.

AGENTI already sent a remote reset a moment ago, and the system reported the gateway as registered and online. Sending another one won't change the physical line, and the test showed the signal to your gateway is good, so a second reset is unlikely to help. I don't want to repeat it without a reason. But since the light is still orange, I can run the line test again now to see whether the gateway has registered since the reset. If it still shows not registered, I'll schedule a technician. Would you like me to do that?

CUSTOMERYes, go ahead and run the line test again. Let's see if anything changed since your reset.

AGENTThe retest still shows your gateway as not registered, even though the signal to it is good. The system recommends a technician if a reset doesn't fix it, and the reset didn't hold, so I'll schedule one now.

AGENTThe technician

CUSTOMEROkay.

CUSTOMERCould you let me know what time slots you have available for the technician?

AGENTThe available technician windows on your account are: - Monday, 8:00 AM to 10:00 AM - Monday, 1:00 PM to 3:00 PM Which one works for you? Once you pick, I'll confirm it back to you.

CUSTOMERMonday, 1 PM to 3 PM works for me. Please schedule that window.

AGENTI've requested the Monday, 1:00 PM to 3:00 PM window for account BW-883011. I should be clear: the scheduling tool only showed me the available windows and didn't return a confirmation number, so I can't yet confirm that the booking is locked in. Please check with Brightwave to verify the appointment before Monday. Until then, it's worth keeping the gateway powered on and leaving the orange light as is, so the technician can see the current state.

CUSTOMEROkay, I'll keep the gateway on so the technician can check it. Can you also add a note that there's a road crew working outside, in case that helps them? Also, since my internet has been down for 2 hours, can I get a credit for the downtime?

AGENTI can apply a service credit for the downtime. I can't add a free-text note to the technician's ticket with the tools I have, so I'll include the road crew detail in the credit reason, which is what I can record. Applying the credit now.

AGENTA $10.00 service credit has been applied to account BW-883011 for the downtime. It will appear on your next bill. To confirm what we have: - Account: BW-883011 - Credit: $10.00, on your next bill - Technician: Requested for Monday, 1:00 PM to 3:00 PM, pending confirmation. Please verify it with Brightwave. - Note: The road crew detail is recorded in the credit reason. I wasn't able to add it as a separate note to the technician's ticket. Keep the gateway powered on until the technician arrives.

CUSTOMERI lost 2 hours of work. Can you make it more than that?

AGENTI understand that two hours of lost work is a real cost. Unfortunately, I can't increase the credit beyond what I've applied. The $10.00 credit is the amount I'm able to apply for this downtime. If you feel the amount should be higher, you can ask Brightwave's billing team to review it, and they can consider the lost work as part of that request.

CUSTOMERAll right. Thanks for your help. Goodbye.

AGENTYou're welcome. Here's your summary: account BW-883011, a $10.00 credit on your next bill, and a technician requested for Monday, 1:00 PM to 3:00 PM, which still needs confirmation. Keep the gateway powered on until then. Goodbye.

Healthcare

AGENTRiverbend

CUSTOMERHey there. Um, sorry, is this Riverbend Health Clinic? I, uh, I need some help moving my dermatology appointment, if you've got a minute.

AGENTYes, this is Riverbend Health Clinic, and I'm Alex, the scheduling assistant. I'd be happy to help you move your dermatology appointment. First, I need to verify who I'm speaking with. Could you please give me your full name and date of birth?

CUSTOMEROh, yeah, sure. Sorry, uh, my name's Wade Carter, and my date of birth is March 17, 1948. Oh, wait, sorry, no, that's not right. It's March 17, 1984. Sorry about that. Just a little distracted over here. Is that okay?

AGENTNo problem at all. I'll use March 17, 1984. Let me verify your details.

AGENTThank you, Wade. You're verified. Let me pull up your upcoming appointments.

AGENTI found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at the Main Campus, Building B. What day and time would you like to move it to?

CUSTOMERThanks for checking. So, I actually need to move it to sometime after 3 PM, please. I've got a work shift in the morning now, and, uh, that's the only time I can make it. Is that gonna be a problem?

AGENTNot necessarily. I'll check Dr. Okafor's availability for after 3 PM. What day would you like me to start searching from? Or should I look from next Wednesday onward?

CUSTOMERUm, yeah. If you could start from next Wednesday and just look for anything after 3 PM, that'd be great. Sorry if that's a hassle. Just need it as soon as possible after that day. Is that all right?

AGENTNo hassle at all. I'll search Dr. Okafor's availability from next Wednesday onward.

AGENTI found a few options with Dr. Okafor: - Tuesday at 3:45 PM - Thursday at 4:10 PM The Tuesday at 9:00 AM and Friday at 11:30 AM slots are morning times, so they don't fit your after-3 PM requirement. Which of the two afternoon options works better for you?

CUSTOMERSorry, I just realized Tuesdays won't work after all. I pick up my daughter then. Uh, could you tell me if there are any Friday afternoon slots? If not, I guess Thursday at 4:10 PM would be okay. Is that possible?

AGENTI checked, and the only Friday slot Dr. Okafor has open is at 11:30 AM, which doesn't fit your after-3 PM requirement. So there are no Friday afternoon options. Thursday at 4:10 PM is available. Would you like me to move your appointment to Thursday at 4:10 PM with Dr. Okafor? Please confirm with a yes, and I'll make the change.

CUSTOMERYeah, uh, I guess that's gonna have to work. Yes, please. Go ahead and move it to Thursday at 4:10 PM with Dr. Okafor. Are you sure there's no extra fee for changing it this close? I just wanna make sure.

AGENTBefore I make the change, I'll check the clinic's change policy so you have the accurate information.

AGENTGood question. Changes made more than 24 hours before the appointment are free. Changes within 24 hours carry a $40 fee. Your appointment is next Wednesday at 9:15 AM, so if we move it now, there's no fee, as long as the change is made more than 24 hours before that appointment. Shall I go ahead and move your appointment to Thursday at 4:10 PM with Dr. Okafor?

CUSTOMEROkay. Thank you for explaining that. Uh, yeah, please move it to Thursday at 4:10 PM. Sorry, just wanna double-check: that's definitely free, right? And, um, could you tell me where I should park for that appointment? I get kinda anxious about parking.

AGENTYes, the change is free since you're making it well over 24 hours before your current appointment. I'll make the move now.

AGENTYour appointment is moved. Here are the details: - Provider: Dr. Okafor (Dermatology) - New time: Thursday at 4:10 PM - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2 - Arrival: Please arrive 15 minutes early with your photo ID and insurance card. For parking, there's free patient parking in Lot C, with the entrance on River Road. Is there anything else I can help you with?

CUSTOMERThanks. That's a relief. Sorry, just one last thing: does Dr. Okafor accept Aetna insurance? I just wanna make sure I'm covered. Is that okay?

AGENTI'm sorry, but I don't have information about which insurance plans Dr. Okafor accepts. I can only help with scheduling, clinic hours, parking, and the change policy. I'd recommend calling the clinic directly or checking with your insurance provider to confirm coverage before your Thursday appointment. Is there anything else I can help you with?

CUSTOMERAll right. I'll double-check with them. Um, you said the confirmation code was RVB-3M8P2, right? I just wanna make absolutely sure I've got it down.

AGENTYes, your confirmation code is RVB-3M8P2. Your appointment is Thursday at 4:10 PM with Dr. Okafor at Main Campus, Building B. Is there anything else I can help you with?

CUSTOMERNo, that covers everything. Thank you so much. I really appreciate your help. Have a good day.

AGENTYou're welcome, Wade. Good luck at your shift, and have a great day!

Home services

AGENTCopperline Home Services,

CUSTOMERHey, um, sorry to bother y'all, but I've got a real emergency here. The pipe under my kitchen sink just burst, and there's water going everywhere, heading right toward a power strip. I, uh, haven't shut the water off yet.

CUSTOMERCan you help me out with this?

AGENTYes, I'm here to help. Let's deal with the water and the electricity first. 1. Shut off the water now. Look under the sink for the two small valves on the supply lines (one hot, one cold). Turn them clockwise until they stop. If you can't turn them, or they don't stop the flow, shut off the main water valve for the house. 2. Stay away from the power strip and any outlets near the water. Don't touch them with wet hands or stand in water to reach them. 3. If the water is reaching the power strip or an outlet, go to your breaker panel and switch off the circuit for that kitchen area, but only if you can reach it without standing in water. 4. Move anything valuable off the floor if you can do it safely. Once the water is off, tell me when you're clear and I'll get your details and send a technician out urgently. What's the address, and is anyone hurt or in danger right now?

CUSTOMEROkay. Um, thank you. Hang on, I'm turning the valves now. Okay, I think the water stopped. Thank goodness. The power strip, yeah. I stayed clear, didn't touch anything. Nobody's hurt, just my nerves and, uh, my baby's upset, but we're safe for now. My address is 1480 Larkspur Avenue. I'm in unit 4D. Sorry, we moved from 4B last month. Just want to make sure you got the right one. Can you please tell me how much this visit's going to cost before you send anyone? And, uh, is there anything else you need from me right now?

AGENTThank you, I'm glad you're safe and the water is off. Let me look up your account. I'll use 1480 Larkspur Avenue, unit 4D, since you've told me you moved from 4B.

AGENTI found your account, but it

CUSTOMEROkay. Oh, sorry. Is there a problem with the account? Do you see it under 4D? I just want to make sure it's all matched up right before anyone comes out. Is there anything I can do on my end?

AGENTYes, the account on file still shows unit 4B, so I need to correct that. I'll use 4D, since that's where you are now. I'm updating the service address on this request, and I'll confirm everything with you before anyone is booked. Your account shows you as a Copperline Care member, so the emergency callout fee is $99 instead of the standard $149. Today's earliest emergency window is 2:00 PM to 4:00 PM. The next option is tomorrow morning, 8:00 AM to 10:00 AM, a standard visit at $79. Before I open

CUSTOMERUm, sorry, is there any chance someone could come before 2? It's just, I'm a little worried with the baby and everything. If not, I'll take the earliest emergency slot you've got, but I just want to check first. Sorry, can you confirm. So the emergency visit will be 99 dollars, right?

AGENTthe

AGENTYes, the emergency visit is $99 with your Copperline Care membership. The 2:00 PM to 4:00 PM emergency window is the earliest I have available today, so I can't offer anything sooner. Would you like me to book that window? Once you confirm, I'll open the service request with these details: - Address: 1480 Larkspur Avenue, Unit 4D (correcting the 4B on file) - Issue: Burst pipe under kitchen sink, water shut off, water near a power strip - Callback number: the best number to reach you. What is it? - Gate code or access notes, if there are any

CUSTOMERAll right. Thank you for explaining all that. I'll take the 2 PM to 4 PM emergency window, then, if that's the earliest. My callback number is 503-555-0139. No, sorry, 0193. And the gate code for the building is pound 2719. Is there anything else you need from me? Could you tell me who's coming out and how I'll know they're on the way? Also, I'd like to get the ticket number, if you can give me that.

AGENTYou're booked. Here's what I have: - Ticket number: CPL-58210 - Visit: today, 2:00 PM to 4:00 PM, emergency - Technician: Dana - Service address: 1480 Larkspur Avenue, Unit 4D (I've corrected this from 4B) - Gate code: #2719 - Callback number: 503-555-0193 - Fee: $99 with your Copperline Care membership Dana will text the callback number about 30 minutes before arriving, so keep your phone nearby. Until Dana arrives, keep the water shut off and stay away from the wet area and the power strip. If you see water reaching any outlets or the breaker panel, or you smell burning, get everyone out of the kitchen and call 911 first. Is there anything else I can help with?

CUSTOMERNo, that covers everything. I really appreciate it. I'll keep an eye on things until Dana gets here. Thank you so much. Goodbye.

AGENTYou're welcome. Dana will be there between 2:00 and 4:00 PM. Take care of yourself and your baby, and goodbye.

Insurance

AGENTNorthgate Mutual

CUSTOMEROh, I'm sorry. I'm not sure what you mean by Northgate. Could you, uh, explain what you're asking about? I just had an accident, so I'm a little flustered.

AGENTNo need to apologize. I'm Alex, the claims assistant for Northgate Mutual Insurance. I'm here to help you report your accident and open a claim. First, the most important thing: are you safe right now? Is anyone hurt or in danger, including you, your passengers, or the other driver? If anyone is injured or you're in a dangerous spot, please call 911 before anything else.

CUSTOMEROh, thank you for checking. Uh, no, nobody's hurt. I'm okay, and the other driver's all right too. We're both standing next to the cars, and there's no danger here. Sorry, I just want to make sure everything's handled right. Is that okay?

AGENTThat's good to hear, and it's completely okay to ask questions. Let's get this handled step by step. To start, could I have your policy number? If you know the policyholder's last name, please include that too, so I can verify the policy.

CUSTOMERAll right. Um, my policy number is NG4471903. No, sorry, last one is 2. Carter's the last name. Wade Carter. Is that coming up right on your end?

AGENTThank you, Wade. Let me check that for you with the corrected policy number.

AGENTThanks, Wade. I've verified your policy, NG4471902, for your 2021 Honda CR-V. It includes collision, rental reimbursement, and roadside towing. Next, could you tell me when and where the accident happened, and what happened?

CUSTOMERUh-huh, that's right. Yeah, that's my car. So, um, about 20 minutes ago, I was stopped at a red light at Southeast 5th Avenue and Alder Street. The other car hit me from behind, right into my back bumper. It's all crushed, and the rear wheel is rubbing, so I can't drive it. Nobody was hurt, but I'm just, you know, a little shaken up. Is that enough detail for you?

AGENTYes, that's helpful, and I'm sorry you're dealing with this. Since your car can't be driven safely, I'll arrange a tow. I also need a few more details for the claim: the other driver's name, insurer, and license plate, and whether police attended. Could you also tell me where your car is right now, and a callback number where the tow driver can reach you?

CUSTOMERThank you. I appreciate you helping me through this. So, um, the other driver's name is Kevin Lund. He's got insurance with Pacific Shore, and his plate is 7KXR214. That's X like X-ray. The police didn't come, just us 2 drivers. My car's still at the scene, Southeast 5th Avenue and Alder Street. And, uh, if the tow driver needs to call, my number is 618-212-0446. Is all that clear?

CUSTOMERSorry if I missed anything.

AGENTYes, that's clear, and you didn't miss anything. Let me read it back: - Other driver: Kevin Lund, insured with Pacific Shore, license plate 7KXR214 - No police attended - Your car is at Southeast 5th Avenue and Alder Street - Callback number: 618-212-0446 I'll now arrange the tow and open your claim.

AGENTYour claim is open. - Claim number: NGM-904417 - Adjuster: Priya Shah, who will contact you within one business day - Policy number: NG4471902 - Other driver's plate: 7KXR214 A tow truck from Eastside Towing has been dispatched to Southeast 5th Avenue and Alder Street. They should arrive in about 45 minutes and will call you at 618-212-0446. The car is being taken to a Northgate partner repair shop at 9th and Morrison. Would you like me to check your coverage for the collision deductible and rental reimbursement?

CUSTOMERYes, please. If you don't mind. I'm really worried about what I'll have to pay. Can you tell me how much the deductible is? And, um, do I get a rental car while mine's being fixed? Also, is my insurance premium going to go up because of this? Sorry for so many questions. I just want to make sure I'm not missing anything.

AGENTOf course, these are good questions.

AGENTHere's what your policy shows: - Collision deductible: $500. This is what you pay toward the repair of your car. - Rental: Your policy covers $40 per day for up to 30 days, starting from the day the claim was opened. - Towing: Covered up to 25 miles. The tow to the repair shop is part of this. I can't tell you whether your premium will go up. That depends on underwriting decisions I don't have access to, so please ask your adjuster, Priya Shah, who will contact you within one business day. You're not asking too many questions. Is there anything else I can help you with right now?

CUSTOMERAll right. Thank you. That helps a lot. But, um, he hit me, so I should not have to pay that 500 dollar deductible, right? Or does that still come out of my pocket? I just want to be sure before anything moves forward.

AGENTI understand why you'd expect that, but I can't say for certain. I don't have information on whether the $500 deductible would be recovered from the other driver's insurer, Pacific Shore. Your policy shows the $500 collision deductible as the amount under your coverage. Whether any of it gets reimbursed later depends on how fault is determined and on the other insurer's decision, and that's something your adjuster, Priya Shah, can review with you. Please mention to her that the other driver rear-ended you and that Kevin Lund's insurer is Pacific Shore. Is there anything else I can help with today?

CUSTOMEROkay. I understand. Thank you for explaining. I'll definitely mention all that to Priya. So, just to double-check, I'll get a rental car covered up to 40 dollars a day, and the tow is on its way to the shop at 9th and Morrison. My claim number's NGM904417, and I should wait to hear from the adjuster. Is that all right? Sorry, I just want to make sure I've got everything straight.

AGENTYes, you have it right, with one small clarification on the rental: it's covered at up to $40 per day for up to 30 days, starting from the day the claim was opened. It isn't a guaranteed rental car, so check with Priya about how to arrange one. Your details: - Claim number: NGM-904417 - Tow: Eastside Towing, arriving in about 45 minutes at Southeast 5th Avenue and Alder Street, then taken to the partner shop at 9th and Morrison - Adjuster: Priya Shah, who will contact you within one business day Please stay safe while you wait for the tow, and if anything changes at the scene, call 911 first. Take care, Wade.

How these numbers are measured →