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

Flux + Claude Haiku 5.5 + Sonic-3.6

Cascade20 scored calls · Nov 15, 2026

Rank on Roark score

#12of 903 stacks

65 / 100

Leader Soniox v6 + OpenAI GPT-6.1 Terra + Cartesia Sonic-3.5, 75 / 100

Where it ranks

Roark score with price65 / 10038 of 903LeaderSoniox v6 + Muse Ember 1.0 + TTS-181 / 100
Task completion93%272 of 905LeaderLinden-1 (own VAD) + GPT-6.1 Sol + TTS-1 HD99%
Tool use68%324 of 881LeaderFlux + GPT-6.1 Terra + Sonic-3.6100%
Time to first word0.9 s417 of 905LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Flash v2.50.5 s
Response time1.9 s39 of 903LeaderLinden-1 (own VAD) + Claude Haiku 4.5 + TTS-11.2 s
Barge-in handling100%114 of 517LeaderUniversal-3.6 Pro + Muse Ember 1.0 + Sonic-3.6100%
Turn budget1.9 s33 of 833LeaderLinden-1 (own VAD) + Claude Haiku 4.5 + TTS-11.2 s
Cost per task$0.27507 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
93%Completed

#281 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
4.4/ 5avg

med

4

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

Instruction following

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

20 calls
4.3/ 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.

15 barge-ins
100%Handled correctly(15/15 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.

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
2.13%avg

p50

0.93%

p95

8.65%

#946 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.

36 calls
0.89per callavg

p50

1.00 per call

p95

2.00 per call

#313 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
1.84%avg

p50

0.68%

p95

5.46%

#867 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
3.43%avg

p50

2.60%

p95

7.88%

#771 of 1111 on the board · best 0.3%

Text-to-Speech

Readback accuracy

Share of the codes, amounts, dates and phone numbers the agent wrote that its voice read out correctly. One wrong digit is a miss.

18 calls
85.9%avg

p50

92.6%

p95

100%

#497 of 934 on the board · best 100%

Word error rate

The share of the words the agent wrote that its voice dropped or changed, read back from Roark’s transcription of the recording; the same transcriber hears every voice.

18 calls
5.48%avg

p50

3.53%

p95

17.4%

#581 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
2.9/ 5avg

med

2.9

#1008 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.

160 turns
2.14savg

p50

1.91s

p95

3.97s

#44 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
0.92savg

p50

0.92s

p95

1.46s

#539 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
1.30per callavg

p50

1.00 per call

p95

3.00 per call

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

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare92%1.78 s—
Home services92%2.02 s—
Insurance92%1.68 s—
Customer support95%1.99 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line92%2.19 s—
Spanish-accented English, city street96%2.01 s—
Indian English, busy café89%1.99 s—
Southern US, flustered, crying baby98%1.76 s—
Fast and interrupting, construction outside88%1.63 s100%

The calls behind the numbers

Customer support

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

CUSTOMERHi, Alex.

CUSTOMERMy Internet's been down for about two hours. I work from home, and there's a road crew digging up the street outside. I already restarted the gateway twice and checked all the cables, but the Internet light is blinking orange. Can you check if the roadwork is causing this?

CUSTOMERMy account number is b w eight eight three zero one seven. Sorry. Last digit is one.

AGENTThanks. Let me pull up the account and check for an outage.

AGENTI have your account as BW883017. Checking for an outage at your address now.

AGENTNo area

CUSTOMERYeah.

AGENTSending a remote

CUSTOMERCould you

CUSTOMERSorry. I didn't

AGENTNo problem. The remote reset worked: your gateway is registered and online. It can take about two minutes for your devices to reconnect, so give it a moment, then try loading a page. To confirm, the account is BW883017. There's no area outage, so the roadwork isn't affecting your line. If you still have no connection after a few minutes, let me know and I can run another test or schedule a technician.

CUSTOMEROkay. The light just went solid white. How long until my devices should be back online?

CUSTOMERAlso, since I lost two hours of work, can I get a credit for the downtime?

AGENTThe solid white light means the gateway is fully connected. Your devices should reconnect within about two minutes, and some may need you to toggle Wi-Fi off and on. For the credit, I can apply a service credit for the downtime. Should I go ahead and apply it to account BW883017 for the two hours of outage?

CUSTOMERYeah. That's right. Can you tell me how much the credit will be?

CUSTOMERI lost two hours of work. Can you make it more than just the standard amount?

AGENTI can apply the credit, but I can't see the dollar amount from here, and I can't set a custom amount or make it larger than standard. Applying the credit now will record the two-hour outage on your account, and the exact amount will show on your bill. Shall I apply it?

CUSTOMERGo ahead and apply it.

CUSTOMERIs there a way to request a review for a larger credit? Since I was working during the outage.

AGENTA $10.00 service credit has been applied to account BW883017. It will appear on your next bill. I don't have a way to request a larger credit through this tool. I can only apply the standard downtime credit. For a review of additional compensation for lost work, you'd need to contact Brightwave billing or customer relations directly. I can't promise the outcome, but they can review your situation. Is there anything else I can check on your connection?

CUSTOMERNo. That covers it. Thanks for your help. Goodbye.

AGENTYou're welcome. Your

AGENTaccount is BW883017, the $10.00 credit will appear on your next bill, and your gateway is online. Goodbye.

Healthcare

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

CUSTOMERHello, Alex. I am having one dermatology appointment next Wednesday morning, but I need to move it because my work shift has changed. Can you help me reschedule it? My name is Arjun Mehta.

AGENTI can help with that, Arjun. First I need to verify your identity. Could you please give me your date of birth?

CUSTOMERMarch seventeen nineteen forty eight.

CUSTOMERSorry. No. Nineteen eighty four.

CUSTOMERMarch seventeen nineteen eighty four.

AGENTThank you, Arjun. Your identity is 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 have a specific day or time range in mind, let me know and I'll check Dr. Okafor's availability.

CUSTOMERI can only come after three PM. Do you have anything available after that time?

AGENTDr. Okafor has these openings after 3 PM: - Tuesday at 3:45 PM. - Thursday at 4:10 PM. Would either of those work for you? Note that the Friday and morning slots don't fit your after-3 PM requirement.

CUSTOMERTuesdays do not work after all because I pick up my daughter. What about Friday?

CUSTOMERIs there anything after three PM on Friday?

AGENTI'm sorry, but Friday's only opening is at 11:30 AM, which doesn't fit your after-3 PM requirement. Dr. Okafor's remaining after-3 PM option is Thursday at 4:10 PM. Would that work for you?

CUSTOMERThursday at four ten PM works for me. Please move my appointment to that time.

AGENTTo

CUSTOMERSo is there any fee for changing the appointment?

AGENTChanges made more than 24 hours before your appointment are free. Changes made later carry a $40 fee. Since your appointment is next Wednesday morning, moving it to Thursday is free as long as it's done more than 24 hours before the original appointment. Before I make the change, here's what I'll do: move appointment APT-20931 with Dr. Okafor from next Wednesday at 9:15 AM to Thursday at 4:10 PM. Should I go ahead?

CUSTOMERYes. Kindly go ahead and move it. Also, can you tell me where to park for the Thursday appointment?

AGENTI'll move the appointment now and get the parking details.

AGENTYour appointment with Dr. Okafor is moved to Thursday at 4:10 PM at Main Campus, Building B. Your new confirmation code is RVB-3M8P2. For parking, there is free patient parking in Lot C, with the entrance on River Road. Please arrive 15 minutes early with your photo ID and insurance card. Is there anything else I can help you with?

CUSTOMERThat's clear. Thank you. One more thing. Does doctor Rokafor accept Aetna insurance?

AGENTI'm sorry, but I don't have information about which insurance plans Dr. Rokafor or any other provider accepts. I can only help with scheduling, appointment changes, clinic hours, parking, and the change policy. For insurance questions, please contact the clinic's billing or front desk staff directly. Also, just to confirm: did you mean Dr. Okafor, your dermatologist? I can't look up insurance coverage for either of them, but I want to make sure I understood the name correctly.

CUSTOMERYes. I meant doctor Okafor, the dermatologist. That's all I needed. Thank you for your help. Goodbye.

AGENTYou're welcome, Arjun. Your

AGENTappointment with Dr. Okafor is set for Thursday at 4:10 PM, confirmation code RVB-3M8P2. For insurance questions about Aetna, please contact the clinic's front desk. Goodbye, and take care.

Home services

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

CUSTOMERHi. Uh, I have a problem in my apartment. The pipe under my kitchen sink just burst, and there's water spreading across the floor heading toward a power strip. I haven't shut the water off yet. Can you help me with this?

AGENTYes, I'll help you. First, the most important thing: water and electricity are dangerous together. 1. Don't touch the power strip or any electrical outlet, and don't step into water near them. If you can safely reach the power strip and it's not in the water, unplug it. If it's in the water or you have to wade through water to reach it, leave it alone and go to your breaker panel to cut power to that area, or stay out of the room. 2. Shut off the water under the sink. Look for the two small valves under the sink and turn them clockwise. If you can't turn them, shut off the main water supply for the building or unit. 3. Move anything valuable up off the floor if you can do it safely. Tell me when the water is off and whether anyone is hurt or has been shocked. Then I'll get your details and send someone out.

CUSTOMEROkay. I'm turning the valves now. Yeah. The water has stopped. No one is hurt, and nobody got shocked. So what do you need from me next?

AGENTGood, thank you. I'll look up your account next. What's the phone number on your account, or the service address?

CUSTOMERSure. The address is thirteen Euche Larkspur Avenue, and my phone number is Cinco Ceros, Cinco Cinco, Ferro Unters Nueva. No. Ferro Novetras.

AGENTI'm sorry, I didn't catch that phone number clearly. Could you say it again, digit by digit? And for the address, could you confirm the unit number too?

CUSTOMERUh-huh. The phone number is five zero three five five five zero one nine three. And I'm in unit four d, not four b. I moved last month.

AGENTThanks. I'll look up your account with that phone number and the new unit.

AGENTI found

CUSTOMEROkay. Well, sorry. Could you repeat that?

CUSTOMERI didn't catch what you said.

AGENTI found an account under your phone number, but the address on file is 1480 Larkspur Avenue, Unit 4B. That doesn't match what you gave me, which is 13 Euche Larkspur Avenue, Unit 4D. Since you've moved, I'll use the address you just gave me. Before I open the request, I need to confirm a few things. Is 13 Euche Larkspur Avenue, Unit 4D the correct service address? Is there a gate code or entry instruction I should note for the technician? And what's the best callback number for you right now?

CUSTOMERIt's one four eight zero Larkspur Avenue, unit four d. The building gate code is pound two seven one nine, and the best callback number is five zero three five five five zero one nine three.

AGENTThanks. Just to be sure I have it right: the service address is 1480 Larkspur Avenue, Unit 4D, not 13 Euche Larkspur Avenue. Is that correct?

CUSTOMERYes. That's right.

CUSTOMERIt's one four eight zero Larkspur Avenue, unit four d.

AGENTGot it: 1480 Larkspur Avenue, Unit 4D. I'll use the address on file's correction and open an emergency request now.

AGENTBefore I book,

CUSTOMEROkay.

AGENTHere's what I have.

CUSTOMERSorry.

AGENTNo need to apologize. Here's where things stand. Your account shows a Copperline Care membership, so the emergency callout fee for you is $99. The earliest visit is today from 2:00 to 4:00 PM. The other option is tomorrow from 8:00 to 10:00 AM, but that's a standard visit at $79, not an emergency. Would you like the emergency visit today at $99? If so, I'll open the request and book it.

CUSTOMERIs it possible for anyone to come before two PM today? The water is stopped, but I really need help as soon as possible.

AGENTI checked, and the earliest window the system offers for an emergency visit today is 2:00 to 4:00 PM. I can't offer anything sooner. Do you want me to book that window at the $99 Copperline Care emergency rate? Your water is off, so you're safe until the technician arrives. Keep the valves closed and stay clear of the wet area.

CUSTOMERAlright. Yes. Please book the two o'clock to four PM window at ninety nine dollars. The water is off, and I'll keep clear. Can you tell me who's coming?

CUSTOMERand how I know they're on the way? Also, will I get a ticket number for this visit?

AGENTI'll open the request and book that window now.

CUSTOMEROkay.

AGENTYou're booked. Here are the details to confirm: - Ticket number: CPL-58210. - Service address: 1480 Larkspur Avenue, Unit 4D. - Gate code: #2719. - Callback number: 503-555-0193. - Visit: today, 2:00 to 4:00 PM. - Technician: Dana. - Fee: $99 (Copperline Care emergency rate). The technician will text your callback number about 30 minutes before arrival, so you'll know they're on the way. Until then, keep the water valves under the sink closed, stay away from the wet area and the power strip, and let me know right away if the water starts again or you notice any electrical problems.

CUSTOMERAlright. I understand. The technician is Dana. They will text me about thirty minutes before arriving, and my ticket number is c p l fifty eight thousand two hundred ten. Thank you for your help. Goodbye.

AGENTThat's right: ticket

AGENTCPL-58210, technician Dana, and a text about 30 minutes before arrival. Thank you for your patience, and I hope the repair goes smoothly. Goodbye.

Insurance

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

CUSTOMERYes.

CUSTOMERI'm in a safe spot. I'm standing next to my car off the road.

AGENTThank you for getting to safety. Before we go further, is anyone injured, including you, your passengers, or the other driver? If anyone is hurt or in danger, please call 911 right away. Once that's taken care of, I'll need your auto policy number to get started. If you have it handy, please also give me the policyholder's last name.

CUSTOMERNo. Nobody is injured.

CUSTOMERIt's just damage to the car. My policy number is n g four four seven one nine zero three. No. Sorry. Last one is two. The last name is Ellis.

AGENTThank you. I heard the policy number as NG4447190 3... let me confirm the digits. Ellis, is that right? I'll verify using the number NG44471902 with last name Ellis.

CUSTOMERYeah. That's right. It's n g four four seven one nine zero two.

CUSTOMERand the last name is Ellis. Go ahead.

AGENTThank you for the correction. I've verified policy NG44471902 under the name Ellis. It's a 2021 Honda CR-V with collision, rental reimbursement, and roadside towing coverage. Now, can you tell me: 1. When and where did the accident happen? 2. What happened? 3. Is the car safe to drive?

CUSTOMERSure. The accident happened about twenty minutes ago. At the intersection of Southeast Fifth Avenue and Alder Street, I was stopped at a red light and another car hit the back of my car. The back bumper is crushed, and the rear wheel is rubbing. So I can't drive it.

AGENTI'm sorry you're dealing with this. Since the car can't be driven safely, I can arrange a tow. First I need a few more details for the claim. 1. Was a police officer at the scene, and if so, do you have a report number? 2. What is the other driver's name, insurer, and license plate number? Also, what is the best callback number for the tow driver?

CUSTOMERNo. A police officer did not come to the scene, so there's no report number. The other driver is Kevin Lund, insured with Pacific Shore. His license plate is seven k, x like X-ray, r two one four. The best callback number for the tow driver is my phone, eight five six two six nine eight five eight three.

AGENTThank you. Let me read those back to confirm: the other driver's license plate is 7KXR214, and the callback number is 856-269-8583. Is that correct? Once you confirm, I'll open your claim and arrange the tow.

CUSTOMERYes.

CUSTOMERThat's correct.

CUSTOMERPlease go ahead and open the claim and arrange the tow.

AGENTYour claim is open and the tow is arranged. - Claim number: NGM-904417 - Policy number: NG44471902 - Other driver: Kevin Lund, Pacific Shore, plate 7KXR214 - Adjuster: Priya Shah, who will contact you within one business day - Tow: Eastside Towing is on the way and should arrive in about 45 minutes. It will take your CR-V to a Northgate partner repair shop at 9th and Morrison. The driver will call 856-269-8583. While you wait, please stay somewhere safe away from traffic. If you have any questions about your coverage, such as rental or deductible details, I can look those up for you.

CUSTOMERYeah. I do have a few questions. How much will I have to pay for the deductible?

CUSTOMERAnd since he hit me, I shouldn't have to pay that. Right?

CUSTOMERAlso, do I get a rental car while mine's in the shop?

CUSTOMERAnd is my premium going to go up because of this?

AGENTI can't tell you whether your premium will change. That isn't something my system covers, and I don't want to guess. Your adjuster, Priya Shah, can explain how this claim might affect your policy, and you can also ask your agent or Northgate's customer service team. What I can tell you from your coverage: your collision deductible is $500, and your policy includes rental reimbursement of $40 per day for up to 30 days from the day the claim was opened. Towing is covered up to 25 miles. On the deductible and fault: I can't decide who is at fault or whether the deductible will be recovered from Kevin Lund's insurer, Pacific Shore. Your adjuster will look into that. Your collision coverage applies now, so you would pay the $500 deductible up front, and it may be recoverable depending on how fault is determined. Is there anything else I can help with?

CUSTOMEROkay. Got it. So I pay the five hundred dollars for now, and the adjuster will see if I get it back from the other insurance.

CUSTOMERThat makes sense. No. I think that covers everything for now. Thanks for your help. Goodbye.

AGENTThat's right. You'd pay the $500 deductible for now, and your adjuster, Priya Shah, will look into whether it can be recovered from Pacific Shore. Your claim number is NGM-904417. Please keep it handy. Thank you for calling Northgate Mutual, Mr. Ellis. Take care, and I hope you're okay.

How these numbers are measured →