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 + Sonic-3.6

Cascade19 scored calls · Nov 13, 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.

19 calls
91%Completed

#394 of 1127 on the board · best 99%

Flow adherence

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

19 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.

19 calls
4.4/ 5avg

med

4

#85 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.

11 barge-ins
100%Handled correctly(11/11 barge-ins)

#1 of 658 on the board · best 100%

Incorrect interruptions

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

19 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.

19 calls
0.81%avg

p50

0.00%

p95

3.75%

#1 of 1127 on the board · best 0.0%

Agent self-cutoffs

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

19 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.

24 calls
0.42per 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.

19 calls
0.23%avg

p50

0.00%

p95

1.04%

#48 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.

19 calls
0.82%avg

p50

0.52%

p95

2.84%

#38 of 1111 on the board · best 0.3%

Voice

Human-likeness

How human the agent's voice sounds, scored by an audio model on intonation, rhythm and expressiveness. 5 = hard to tell from a person.

19 calls
2.9/ 5avg

med

2.9

#1032 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.

19 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.

139 turns
2.76savg

p50

2.58s

p95

4.24s

#171 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.

19 calls
0.92savg

p50

0.94s

p95

1.34s

#578 of 1127 on the board · best 0.45 s

Latency spikes

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

19 calls
2.32per callavg

p50

2.00 per call

p95

4.10 per call

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

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare91%2.45 s—
Home services92%2.63 s—
Insurance87%2.41 s—
Customer support98%2.68 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line94%2.82 s—
Spanish-accented English, city street96%2.87 s—
Indian English, busy café96%2.74 s—
Fast and interrupting, construction outside79%2.35 s100%

The calls behind the numbers

Customer support

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

CUSTOMERHey, Alex. My internet's been down for about 2 hours now. I work from home, so this is urgent. There's a road crew digging up the street right outside, and ever since they started, the internet light on my gateway's been blinking orange. I already rebooted the gateway twice and checked every cable. Nothing changed. Can you check what's going on? My account number is BW883017. Sorry, last digit is 1.

AGENTThanks for the details. I'll pull up your account now.

CUSTOMEROkay.

AGENTYour account is BW883011, and there's no known outage in your area. The construction

CUSTOMERYeah, that's right. Let's just get to what's causing this outage. The road crew outside, is that the problem?

AGENTThe line test shows signal reaching your gateway is good, but the gateway itself isn't registered

CUSTOMERMm-hm.

AGENTYour gateway

CUSTOMERRight. I already rebooted. Yeah, I rebooted the gateway twice already and checked every single cable. The internet light's still blinking orange. What else can we try?

AGENTI understand, and I'm sorry you've been dealing with this for two hours. I should correct something first: I read your account number back wrong earlier. It's BW-883011,

CUSTOMEROkay, but I just need this fixed. Can you reset my gateway remotely or check if it's the street work?

AGENTI already sent the remote reset to your gateway, and it reports as registered and online now. It

CUSTOMERYeah.

CUSTOMERAll right. The internet light just went solid white. How long until my devices reconnect? And I'd like a credit for the downtime.

AGENTGood news, the light going solid white means the gateway is connected. Devices can take about two

CUSTOMEROkay.

CUSTOMERYep, got it. So how long until everything's back online? And about that credit for the downtime, what can you do?

AGENTYour devices should be back online within about two minutes. Your gateway is already registered,

CUSTOMERUh-huh.

CUSTOMERAll right. And what about the credit for being down 2 hours? How much will that be?

AGENTA $10.00 service credit has been applied to your account for the downtime. It will show on your next bill. Your account number is BW-883011. Your gateway is registered and online,

CUSTOMERRight.

AGENTYour gateway is back online and your devices should reconnect within about two minutes. If they don't come back, or the light turns orange again, let me know and I can run

CUSTOMERUh-huh.

CUSTOMERYeah, but I lost 2 hours of work. Can you make that credit more than 10 dollars?

AGENTI can't change the amount. The credit I applied is $10.00, and that's the amount I'm able to issue for this outage. I'm sorry about the lost work. If you'd like

CUSTOMERAll right. If that's the most you can do, thanks for your help. Goodbye.

AGENTYou're welcome. Your account is BW-883011, your gateway is online, and the $10.00 credit will appear on your next

CUSTOMEROkay.

AGENTbill.

AGENTTake care,

AGENTand I hope the rest of your workday goes smoothly.

Healthcare

AGENTRiverbend Health

CUSTOMERHi there. Um, sorry, I've got a baby fussing in the background, but I was hoping y'all could help me reschedule my dermatology appointment. It's supposed to be next Wednesday morning, but I just found out I got a work shift then. My name's Wade Carter.

AGENTHi Wade, no problem at all. I can help with that. First I need to verify your identity. Could you please give me your date of birth?

CUSTOMERYeah, of course. Uh, it's March 17, 1948. Oh, wait, sorry, no, that's not right. I always get mixed up when I'm flustered. It's actually March 17, 1984. Is that okay?

AGENTYes, that's fine. I'll use March 17, 1984.

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

AGENTI found your dermatology appointment with Dr. Okafor next Wednesday at 9:15 AM at Main Campus, Building B. What day and time would you like to move it to? If you'd like, I can check Dr. Okafor's open slots for you. Also, let me know if there are any constraints, like a preferred day or time of day.

CUSTOMEROh, thank you for checking on that. Sorry, it's a bit hectic here. Um, I can only come in after 3 PM, just with my work schedule and all. Do you mind seeing what's open with Dr. Okafor after 3? I appreciate it.

AGENTDr. Okafor has these openings after 3 PM: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. Which one works better for you? Once you choose, I'll confirm the details before making the change.

CUSTOMEROh, sorry, Tuesdays don't actually work for me after all. I have to pick up my daughter that day. Um, what about Friday? If that's not available, I guess Thursday at 4:10 would be fine. Is that okay?

AGENTFriday's only opening is at 11:30 AM, which is before 3 PM, so it doesn't fit your constraint. Thursday at 4:10 PM is the option that works. Shall I move your appointment to Thursday at 4:10 PM with Dr. Okafor?

CUSTOMERYeah, I'm a little nervous about missing work, so Thursday at 4:10 PM sounds good. Can you please move me to that slot? And, uh, just to double-check, there won't be any kind of fee for changing the appointment, will there?

AGENTI'll check the change policy for you first, then make the move.

AGENTGood news: changes made more than 24 hours before the appointment are free. Since your appointment is next Wednesday, this change is free. Here's what I'm about to do: - Patient: Wade Carter, DOB March 17, 1984. - Move appointment APT-20931 with Dr. Okafor from next Wednesday at 9:15 AM. - To Thursday at 4:10 PM. Should I go ahead?

CUSTOMERThat's a relief. Thank you. I was worried about a fee. Yes, please, go ahead and move it to Thursday at 4:10 PM. Can you also tell me, um, where should I park when I come in? I always get a little lost around Main Campus.

AGENTYour appointment is moved. Here are the details: - Patient: Wade Carter, DOB March 17, 1984 - New appointment: Thursday at 4:10 PM with Dr. Okafor, Main Campus, Building B. - Confirmation code: RVB-3M8P2. 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.

CUSTOMEROkay, that helps a lot. Thank you. Uh, just one more thing: does Dr. Okafor accept Aetna insurance? I want to be sure before I come in. And, sorry, could you read back that confirmation code for me one more time? I just want to make sure I got it right.

AGENTThe confirmation code is RVB-3M8P2. As for Aetna, I don't have any information about which insurance plans Dr. Okafor accepts, so I can't confirm that. I'd recommend calling the clinic directly or checking with your insurance provider before your visit.

CUSTOMERAll right. Thank you for saying that again. I'll double-check with my insurance, then. Um, I think that's everything. Thanks for all your help today. Goodbye.

AGENTYou're welcome, Wade. Your appointment is set for Thursday at 4:10 PM with Dr. Okafor, confirmation code RVB-3M8P2. Take care, and good luck with the baby. Goodbye!

Home services

AGENTCopperline Home Services,

CUSTOMERUh, hi. Sorry, I, um, I've got a real emergency here. There's a pipe under my kitchen sink just burst, and there's water all over the floor. It's running toward this power strip, and my baby's crying. I just, I really need someone out here as soon as possible. Can y'all help with that?

AGENTYes, we'll get someone out to you. First, safety, right now: 1. Get your baby and yourself away from the water and out of the kitchen. 2. Do not touch the power strip or any outlet while standing in water. If you can reach it safely without stepping in water, unplug it. If not, leave it alone and turn off the breaker for the kitchen at your electrical panel only if you can do so without wading through water. 3. Shut off the water to the sink. Look for the two small valves under the sink and turn them clockwise. If you can't, shut off the main water supply to the house. Once you're safe, tell me your name and the service address, including unit number if there is one.

CUSTOMEROkay. Uh, thank you for walking me through that. Hang on, let me just— okay, I turned the valves under the sink and the water stopped. My goodness. I've got my baby out of there too. Sorry. I'm a bit shaken. M-my name's Wade Carter. The address is 1480 Larkspur Avenue, and, um, I just moved to unit 4D last month, not 4B. Will that be a problem?

AGENTThank you, Wade. I'm glad you and your baby are out of the kitchen and the water is shut off. That was exactly the right move. No problem at all about the unit. I'll look up your account with the address at 1480 Larkspur Avenue, Unit 4D, and make sure the record reflects your current unit.

AGENTI found your account, but it still lists you in Unit 4B. Since you've moved to 4D, I'll use 4D for this service request. Before I open the ticket, I need two more things: is there a gate code or access instruction for the building, and what's the best callback number for you?

CUSTOMERUh, thanks for checking on that. Yeah, the gate code is £2719, and the callback number is 503-555-0139. Wait, sorry, no, it's 503-555-0193. Is that okay? Will that be enough for the tech to get in?

AGENTYes, I have the callback number as 503-555-0193. The gate code is noted as "£2719." Please double-check that, since the pound sign is unusual for a gate code. Is it 2719? Once you confirm the code, I'll open the emergency ticket now.

CUSTOMEROh, sorry. I should've said it clearer. It's the pound sign first, then 2719. So, £2719. Is that all you need? And, um, can you tell me how much this visit will cost before I say yes?

AGENTI'll note the gate code as "#2719" to match what you've said, and I'll check the fees for your account before we book anything. Let me pull those up now.

AGENTYour ticket is open,

CUSTOMERAll right.

AGENTYour ticket is CPL-58210,

CUSTOMEROh, sorry.

AGENTNo need to apologize,

CUSTOMERSorry.

AGENTNo

CUSTOMEROh, uh, sorry.

CUSTOMERUm, sorry, did you need anything?

AGENTWade, don't worry about it. Here's where things stand. Your emergency ticket is CPL-58210. I have your service address as 1480 Larkspur Avenue, Unit 4D, gate code #2719, and callback number 503-555-0193. Your account is a Copperline Care membership, so the emergency callout fee is $99. The next available windows are: - Today, 2:00 PM to 4:00 PM (emergency). - Tomorrow, 8:00 AM to 10:00 AM (standard, $79 fee). Since the water is already shut off, you might prefer the earlier emergency window today. Would you like me to book the 2:00 to 4:00 PM visit today for the $99 fee? No apology

AGENTneeded, Wade. You're doing fine. Here's where things stand. Your emergency ticket is CPL-58210. Please confirm the details: - Address: 1480 Larkspur Avenue, Unit 4D - Gate code: #2719 - Callback number: 503-555-0193. Your account is a Copperline Care membership, so the emergency callout fee is $99. The next emergency window is today, 2:00 to 4:00 PM. The other option is tomorrow, 8:00 to 10:00 AM, but that is a standard visit at $79 and it isn't an emergency slot, so I'd recommend today. Are those details correct, and do you want the 2:00 to 4:00 PM window at $99?

CUSTOMERYeah, that all sounds right. Thank you for walking me through it. I'm just, uh, a little anxious about all this. The address is 1480 Larkspur Avenue, Unit 4D. The gate code is £2719, and my callback is 503-555-0193. And the ticket number is CPL-58210, right? I do want the 2:00 to 4:00 PM emergency window today, please. Can you tell me who's coming and how I'll know when they're on their way?

AGENTYes, the ticket is CPL-58210. Booking the 2:00 to 4:00 PM window now.

AGENTYou're booked, Wade. - Ticket: CPL-58210 - Window: Today, 2:00 to 4:00 PM - Technician: Dana - Fee: $99 (Copperline Care emergency callout) - Address: 1480 Larkspur Avenue, Unit 4D. - Gate code: #2719. - Callback: 503-555-0193. Dana will text the callback number about 30 minutes before arriving, so you'll know when they're on the way. Until then, keep the kitchen area clear, keep the baby out of the room, and don't turn the water back on. Stay off the wet floor and away from the power strip. If the water starts spreading again or you smell gas or see sparks, get everyone out and call 911 first. Is there anything else I can help with?

CUSTOMERNo, I think that covers it. Thanks for being so thorough and talking me through everything. I really appreciate it. Bye.

Insurance

AGENTNorthgate Mutual

CUSTOMERUh, sorry. Could you repeat that? Are you asking about Northgate, or is that part of your company name or address? I just want to make sure I'm answering your question right.

AGENTNo problem, I apologize for that. Northgate Mutual" is our company name. I'm Alex, the claims intake assistant for Northgate Mutual Insurance, and I can help you report an accident today. First, are you safe right now? Is anyone hurt or in danger? If anyone is injured or near traffic, please call 911 before anything else.

CUSTOMERThank you for checking. Yeah, I'm safe. Nobody's hurt, and we're away from traffic. I'm just a little shaken up, but the car's not drivable. Uh, sorry if I sound flustered. I've got a baby crying here too. Is it all right to go ahead and start the claim?

AGENTYes, of course. Take your time, and it's completely fine to sound flustered. We'll go step by step. To start, I need your policy number. If you give me your last name too, I can verify the policy.

CUSTOMERAll right. Thank you. I appreciate that. My last name's Carter. The policy number is, uh, NG4471903. No, sorry, last one is 2. So it's NG4471902. Is that coming up right on your end?

AGENTThanks for correcting that. I'll verify NG4471902 with the last name Carter.

AGENTThank you,

CUSTOMERRight. So, um, could you let me know if that's all set? I just want to make sure nothing gets lost. Can we keep going?

AGENTYes, it's all set. Your policy NG4471902 is verified under the name Carter, and it covers a 2021 Honda CR-V with collision, rental reimbursement, and roadside towing. Since the car isn't drivable, I can arrange a tow once we have the location. Now, when and where did the accident happen?

CUSTOMEROkay. Thank you. That's a relief. Uh, the accident happened about 20 minutes ago. I was stopped at a red light at Southeast 5th Avenue and Alder Street. Do you need a cross street, or is that enough?

AGENTThat's enough, thank you. Southeast 5th Avenue and Alder Street is a clear location. Now, what happened? Please tell me in your own words what took place.

CUSTOMERAll right. So, um, I was stopped at the red light, just sitting there, and another car came up behind me and hit the back of my car. It was a pretty solid hit. The back bumper's crushed, and now the rear wheel's rubbing, so I can't drive it. Nobody's hurt, but, uh, police didn't come out. Does that cover what you need?

AGENTYes, that's clear, thank you. I'm sorry you're dealing with this. Next I need the other driver's details: their name, their insurance company, and their license plate number. If you don't have all of them, just give me what you have.

CUSTOMEROh, uh, thank you for saying that. I do have the info. The other driver's name is Kevin Lund. He's insured with Pacific Shore. The license plate is 7KXR214, X like X-ray. Is that enough, or do you need more off his insurance card?

AGENTThank you. That's enough for now. Let me read back the plate to make sure I have it right: 7KXR214, with X as in X-ray. The other driver is Kevin Lund, insured with Pacific Shore. Before I open the claim, I'll confirm the details. Is there anything else about the accident you'd like to add, such as the time it happened? You mentioned it was about 20 minutes ago, so I'll note that as the loss time.

CUSTOMERYeah, that's right. And, uh, sorry, I don't think there's anything else. It was about 20 minutes ago, like I said. No injuries, just the car damage and all. Is that enough to get things started?

AGENTYes, that's enough to get started. I'm opening the claim now.

AGENTYour claim is open. The claim number is NGM-904417, and adjuster Priya Shah has been assigned. You can expect contact from her within one business day. Since your car can't be driven, I can arrange a tow from Southeast 5th Avenue and Alder Street. What phone number should the driver use to reach you?

CUSTOMEROkay. Thank you. That's good to hear. Uh, the number they should use is 802-898-0095. That's the one I'm calling from right now. Is that going to work all right?

AGENTYes, that number works. I'll arrange the tow now.

AGENTA tow truck from Eastside Towing has been dispatched to Southeast 5th Avenue and Alder Street. The estimated arrival is about 45 minutes, and the driver will call you at 802-898-0095. The car will be taken to our partner repair shop at 9th and Morrison. Here's a summary to read back: - Policy number: NG4471902. - Claim number: NGM-904417. - Other driver's license plate: 7KXR214. - Adjuster: Priya Shah, contact within one business day. Is there anything else I can help you with right now?

CUSTOMERAll right. Uh, thanks for reading all that back. Just a couple quick things. How much am I going to have to pay out of pocket for this? Is there a deductible, or since he hit me, do I still have to pay that? And, um, do I get a rental car while mine's in the shop? Also, I'm a little worried. Will my premium go up because of this?

AGENTI understand those are important questions. I'll check your coverage details now.

AGENTHere's what your policy shows: - Deductible: Your collision deductible is $500. Whether you pay it in the end depends on how the claim is resolved, including whether the other driver's insurer accepts responsibility. Priya Shah can explain how that works once she's reviewed the claim. - Rental car: Your policy includes rental reimbursement of $40 per day for up to 30 days, starting from the day the claim was opened. - Towing: Towing is covered up to 25 miles, so this tow should fall within that. I don't have information about whether your premium will change. Priya Shah or your agent can answer that question.

CUSTOMERAll right. Uh, thank you for explaining all that. But just to be clear, I'm still worried. Since he hit me, I shouldn't have to pay that 500 dollar deductible, right? Or do I have to pay it up front and then maybe get it back? And for the rental, do I just go to the shop and they'll help me set that up, or do I need to call someone first? Sorry to keep asking. I just want to make sure I do this right.

AGENTPlease don't apologize. These are fair questions. On the deductible, I can't tell you whether you'll owe it or get it back. That depends on how the claim is handled, including whether the other driver's insurer, Pacific Shore, accepts responsibility. I don't have information on how a recovery would work, so please ask Priya Shah about that when she calls. On the rental, I also don't have information about how to set it up, such as whether the shop arranges it or whether you need to call first. I'd suggest asking Priya Shah

AGENTwhen she contacts you. She'll be the best person to confirm the steps. Your rental coverage is $40 per day for up to 30 days, starting from the day the claim was opened. For now, keep your claim number, NGM-904417, handy when you talk to anyone. Would you like me to note anything else before you go?

How these numbers are measured →