Skip to content

Roark Live Bench · Suite v1.3 · Sweep of 30 October 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.

662 stacks published14,070 scored callsPublished at 20 scored calls

Our picks

Roark scoreTask completionMedian responseCost per minute

The read

  • 430 of 642 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 2.0 s to 6.2 s on the same agent and the same caller, a spread of 4.2 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 + ElevenLabs Turbo v2.5 at 2.0 s, ranks 559 of 642 on task completion; the most complete is Speechmatics Linden-1 (own VAD) + OpenAI GPT-6.1 Sol + OpenAI TTS-1 HD at 99%.
  • The language model matters most: swapping it moves task completion by 7 points, against 3 for the speech engine and 2 for the transcriber.
  • The fastest speech-to-speech model answers 0.1 s sooner than the fastest cascade, and its completion rate sits 12 points below the best cascade.

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 task completion, tool use, time to first word, barge-in handling and cost per task; speech-to-speech leads on response time. Neither wins outright, so the right choice depends on what your calls need.
  • Speech-to-speech costs 1.6 times as much per completed task: $0.24 for speech-to-speech against $0.15 for cascades.
  • The biggest difference is response time: 3.8 s for cascades against 2.1 s for speech-to-speech.
CascadeSpeech-to-speech
Task completionTool useTime to first wordResponse timeBarge-in handlingCost per task255075100
MeasureCascadeSpeech-to-speech
Task completion
94% (leads)85%
Tool use
78% (leads)78%
Time to first word
0.8 s (leads)1.1 s
Response time
3.8 s2.1 s (leads)
Barge-in handling
100% (leads)96%
Cost per task
$0.15 (leads)$0.24

The three strongest of each, averaged. Cascades: AssemblyAI Universal-3.6 Pro + OpenAI GPT-6.1 Sol + Rime Coda; Speechmatics Linden-1 (own VAD) + OpenAI GPT-4.1 + Rime Coda; AssemblyAI Universal-3.6 Pro + Google Gemini 3.8 Flash + Rime Coda. 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.

  • AssemblyAI Universal-3.6 Pro, AssemblyAI Universal-3.5 Pro, Deepgram Nova-3 and Speechmatics Enhanced (realtime) are level: none leads by more than the margin of error. Of them, AssemblyAI Universal-3.6 Pro costs least, at $0.030 a call. Avoid Speechmatics Linden-1 (own VAD): last on semantic word error rate (2.2%).
  • Speechmatics Linden-1 (own VAD) delivers its transcript in 0.49 s, OpenAI Whisper-1 in 1.93 s: 1.44 s added to every turn of the call.
  • AssemblyAI Universal-3.6 Pro is the most accurate: it changes the meaning of 0.9% of the caller's words, against 2.2% for Speechmatics Linden-1 (own VAD).
  • In 341 of 648 cascades the transcriber is the slowest step of the turn, whichever model runs it.

Roark score, best first

90Universal-3.6 Pro84Universal-3.5 Pro82Nova-382Enhanced (realtime)79Linden-171Nova-266Standard (realtime)56Whisper-152Linden-1 (own VAD)
Every transcriber on every figure, sorted by roark score. Column headers sort the table.
#
1Universal-3.6 ProAssemblyAI90 / 100. Semantic word error rate 0.9%, 61.2 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points(among the best)0.9%(among the best)0.89 s(among the best)$0.030
2Universal-3.5 ProAssemblyAI84 / 100. Semantic word error rate 1.1%, 55.7 of 71 points; Time to final transcript 0.90 s, 28.6 of 29 points(among the best)1.1%(among the best)0.90 s$0.030
3Nova-3Deepgram82 / 100. Semantic word error rate 1.1%, 53.5 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points(among the best)1.1%(among the best)0.89 s(among the best)$0.031
4Enhanced (realtime)Speechmatics82 / 100. Semantic word error rate 1.1%, 53.3 of 71 points; Time to final transcript 0.98 s, 28.6 of 29 points(among the best)1.1%(among the best)0.98 s$0.054
5Linden-1Speechmatics79 / 100. Semantic word error rate 1.3%, 50.0 of 71 points; Time to final transcript 0.99 s, 28.6 of 29 points1.3%0.99 s$0.020(among the best)
6Nova-2Deepgram71 / 100. Semantic word error rate 1.5%, 42.2 of 71 points; Time to final transcript 0.89 s, 28.6 of 29 points1.5%0.89 s(among the best)$0.023(among the best)
7Standard (realtime)Speechmatics66 / 100. Semantic word error rate 1.7%, 37.5 of 71 points; Time to final transcript 0.96 s, 28.6 of 29 points1.7%0.96 s$0.031
8Whisper-1OpenAI56 / 100. Semantic word error rate 1.4%, 45.5 of 71 points; Time to final transcript 1.93 s, 10.9 of 29 points1.4%1.93 s$0.025
9Linden-1 (own VAD)Speechmatics52 / 100. Semantic word error rate 2.2%, 23.1 of 71 points; Time to final transcript 0.49 s, 28.6 of 29 points2.2%0.49 s(among the best)$0.020(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$0.080.5%1%1.5%2%2.5%Cheap and accurateAccurate, pricierCheap, less accuratePricier and less accurateLinden-1 (own VAD)Linden-1Nova-2Whisper-1Universal-3.6 ProUniversal-3.5 ProStandard (realtime)Nova-3Enhanced (realtime)Cost per call · ← betterSemantic word error rate · better →
Speed against qualitySemantic word error rate · Time to final transcript
0 s1 s2 s3 s0.5%1%1.5%2%2.5%Fast and accurateAccurate, slowerFast, less accurateSlower and less accurateLinden-1 (own VAD)Nova-3Nova-2Universal-3.6 ProUniversal-3.5 ProStandard (realtime)Enhanced (realtime)Linden-1Whisper-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.

  • Pick OpenAI GPT-6.1 Sol: it leads on task completion (95%), tool use (77%) and instruction following (4.2 / 5). If speed matters more, Anthropic Claude Haiku 4.5 is the quickest, at 0.36 s, and completes 91%. Avoid OpenAI GPT-4o: last on task completion (88%).
  • Anthropic Claude Haiku 4.5 starts answering in 0.36 s, Google Gemini 3.8 Flash in 1.47 s: 1.11 s added to every turn of the call.
  • OpenAI GPT-6.1 Sol uses its tools most reliably: it handles its tools without a mistake on 77% of calls, against 38% for OpenAI GPT-5.1.
  • In 161 of 648 cascades the language model is the slowest step of the turn, whichever model runs it.

Roark score, best first

66GPT-6.1 Sol61Claude Sonnet 5.551Gemini 3.8 Flash50GPT-4.149Claude Haiku 4.547GPT-4o mini44GPT-5.144GPT-4o
Every language model on every figure, sorted by roark score. Column headers sort the table.
#
1GPT-6.1 SolOpenAI66 / 100. Task completion 95%, 27.0 of 36 points; Tool use 77%, 15.0 of 27 points; Instruction following 4.2 / 5, 11.3 of 18 points; Time to first token 0.97 s, 12.4 of 18 points(among the best)95%(among the best)4.2 / 5(among the best)77%(among the best)0.97 s73%$0.019(among the best)
2Claude Sonnet 5.5Anthropic61 / 100. Task completion 94%, 25.1 of 36 points; Tool use 72%, 11.8 of 27 points; Instruction following 4.2 / 5, 10.8 of 18 points; Time to first token 0.90 s, 13.3 of 18 points(among the best)94%(among the best)4.2 / 5(among the best)72%(among the best)0.90 s–$0.138
3Gemini 3.8 FlashGoogle51 / 100. Task completion 95%, 26.5 of 36 points; Tool use 62%, 6.7 of 27 points; Instruction following 4.2 / 5, 11.1 of 18 points; Time to first token 1.47 s, 6.4 of 18 points(among the best)95%(among the best)4.2 / 5(among the best)62%(among the best)1.47 s–$0.016(among the best)
4GPT-4.1OpenAI50 / 100. Task completion 92%, 21.2 of 36 points; Tool use 48%, 0.0 of 27 points; Instruction following 4.2 / 5, 10.8 of 18 points; Time to first token 0.52 s, 18.0 of 18 points92%4.2 / 5(among the best)48%0.52 s82%(among the best)$0.022
5Claude Haiku 4.5Anthropic49 / 100. Task completion 91%, 19.4 of 36 points; Tool use 47%, 0.0 of 27 points; Instruction following 4.2 / 5, 11.0 of 18 points; Time to first token 0.36 s, 18.2 of 18 points91%4.2 / 5(among the best)47%0.36 s(among the best)–$0.062
6GPT-4o miniOpenAI47 / 100. Task completion 90%, 17.4 of 36 points; Tool use 51%, 0.7 of 27 points; Instruction following 4.2 / 5, 10.8 of 18 points; Time to first token 0.45 s, 18.2 of 18 points90%4.2 / 5(among the best)51%0.45 s(among the best)81%(among the best)$0.002(among the best)
7GPT-5.1OpenAI44 / 100. Task completion 89%, 17.0 of 36 points; Tool use 38%, 0.0 of 27 points; Instruction following 4.1 / 5, 10.1 of 18 points; Time to first token 0.59 s, 17.1 of 18 points89%4.1 / 538%0.59 s74%(among the best)$0.031
8GPT-4oOpenAI44 / 100. Task completion 88%, 15.0 of 36 points; Tool use 50%, 0.0 of 27 points; Instruction following 4.2 / 5, 10.9 of 18 points; Time to first token 0.45 s, 18.2 of 18 points88%4.2 / 5(among the best)50%0.45 s(among the best)–$0.027

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$0.15$0.285%90%95%100%Cheap and reliableReliable, pricierCheap, less reliablePricier and less reliableGPT-4o miniGemini 3.8 FlashGPT-6.1 SolGPT-4.1GPT-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 s85%90%95%100%Fast and reliableReliable, slowerFast, less reliableSlower and less reliableClaude Haiku 4.5GPT-4o miniGPT-4oGPT-4.1GPT-5.1Claude 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.

  • Cartesia Sonic-3.6, ElevenLabs v4 Turbo and Cartesia Sonic-3.5 are level: none leads by more than the margin of error. Of them, Cartesia Sonic-3.5 costs least, at $0.165 a call. Avoid OpenAI TTS-1 HD: last on readback accuracy (80%), word error rate (8.7%) and time to first audio byte (2.09 s).
  • ElevenLabs v4 Turbo starts speaking in 0.11 s, OpenAI TTS-1 HD in 2.09 s: 1.97 s added to every turn of the call.
  • Cartesia Sonic-3.6 is the most accurate: it reads codes, amounts and dates back correctly 87% of the time, against 80% for OpenAI TTS-1 HD.
  • Cartesia Sonic-3.6 sounds the most human: 3.8 / 5, against 3.4 / 5 for ElevenLabs Flash v2.5.
  • In 99 of 648 cascades the speech engine is the slowest step of the turn, most often with OpenAI TTS-1 HD (54 of them).

Roark score, best first

77Sonic-3.677v4 Turbo77Sonic-3.573Sonic-371Turbo v2.570Flash v2.568Coda55TTS-139TTS-1 HD
Every speech engine on every figure, sorted by roark score. Column headers sort the table.
#
1Sonic-3.6Cartesia77 / 100. Readback accuracy 87%, 25.6 of 38 points; Word error rate 6.2%, 14.5 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 99%, 12.1 of 13 points(among the best)6.2%87%(among the best)3.8 / 5(among the best)99%0.12 s(among the best)$0.168
2v4 TurboElevenLabs77 / 100. Readback accuracy 87%, 25.1 of 38 points; Word error rate 5.7%, 15.8 of 25 points; Time to first audio byte 0.11 s, 25.0 of 25 points; Voice consistency 98%, 11.2 of 13 points(among the best)5.7%(among the best)87%(among the best)3.6 / 598%0.11 s(among the best)$0.470
3Sonic-3.5Cartesia77 / 100. Readback accuracy 86%, 24.6 of 38 points; Word error rate 6.2%, 14.6 of 25 points; Time to first audio byte 0.13 s, 25.0 of 25 points; Voice consistency 100%, 12.4 of 13 points(among the best)6.2%86%(among the best)3.8 / 5(among the best)100%(among the best)0.13 s$0.165
4Sonic-3Cartesia73 / 100. Readback accuracy 85%, 23.3 of 38 points; Word error rate 6.9%, 12.8 of 25 points; Time to first audio byte 0.17 s, 25.0 of 25 points; Voice consistency 99%, 12.1 of 13 points6.9%85%3.4 / 599%0.17 s$0.165
5Turbo v2.5ElevenLabs71 / 100. Readback accuracy 80%, 19.0 of 38 points; Word error rate 5.7%, 15.6 of 25 points; Time to first audio byte 0.15 s, 25.0 of 25 points; Voice consistency 98%, 11.5 of 13 points5.7%(among the best)80%3.4 / 598%0.15 s$0.451
6Flash v2.5ElevenLabs70 / 100. Readback accuracy 80%, 18.5 of 38 points; Word error rate 6%, 14.9 of 25 points; Time to first audio byte 0.12 s, 25.0 of 25 points; Voice consistency 98%, 11.5 of 13 points6%(among the best)80%3.4 / 598%0.12 s(among the best)$0.437
7CodaRime68 / 100. Readback accuracy 83%, 21.7 of 38 points; Word error rate 8.1%, 9.8 of 25 points; Time to first audio byte 0.18 s, 25.0 of 25 points; Voice consistency 99%, 11.8 of 13 points8.1%83%3.7 / 5(among the best)99%0.18 s$0.116(among the best)
8TTS-1OpenAI55 / 100. Readback accuracy 82%, 21.0 of 38 points; Word error rate 6.1%, 14.8 of 25 points; Time to first audio byte 1.13 s, 7.1 of 25 points; Voice consistency 100%, 12.5 of 13 points6.1%82%3.6 / 5100%(among the best)1.13 s$0.036(among the best)
9TTS-1 HDOpenAI39 / 100. Readback accuracy 80%, 18.3 of 38 points; Word error rate 8.7%, 8.4 of 25 points; Time to first audio byte 2.09 s, 0.0 of 25 points; Voice consistency 100%, 12.4 of 13 points8.7%80%3.6 / 5100%(among the best)2.09 s$0.065(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%Cheap and accurateAccurate, pricierCheap, less accuratePricier and less accurateTTS-1TTS-1 HDCodaSonic-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%Fast and accurateAccurate, slowerFast, less accurateSlower and less accuratev4 TurboSonic-3.6Flash v2.5Sonic-3.5Turbo 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%.
  • xAI Grok Voice 3.0 answers in 1.9 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

65GPT Live 1 (Sol)66Grok Voice 3.065GPT Live 1 (Luna)65Grok Voice Think Fast 2.053Gemini 3.8 Live53GPT Realtime 2.148Ultravox v0.748Gemini 3.1 Flash Live (preview)48GPT Realtime 246Nova 2 Sonic47Realtime v1 Max45Realtime v1 Mini44GPT 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)GPT Live 1 (Sol)OpenAI65 / 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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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 s(among the best)1.4 s77%3.1 / 5100%(among the best)$0.24
2= (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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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
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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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 s(among the best)1.5 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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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)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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 of 5 points; Voice consistency 100%, 4.5 of 5 points78%4.3 / 5(among the best)69%2.8 s1.6 s100%(among the best)4.1 / 5(among the best)100%(among the best)$0.14(among the best)
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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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)Ultravox v0.7Ultravox48 / 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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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
8= (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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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
9= (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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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
10= (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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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)
11= (tied)Realtime v1 MaxElevenLabs47 / 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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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
12= (tied)Realtime v1 MiniElevenLabs45 / 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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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
13= (tied)GPT Realtime 2.1 miniOpenAI44 / 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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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)
14Gemini 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), 10.6 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 84% (field median, not measured), 2.7 of 5 points; Word error rate 5.9% (field median, not measured), 2.8 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 2.0GPT Realtime 2.1Realtime v1 MiniRealtime v1 MaxGPT Realtime 2Cost per task · ← betterTask completion · better →
Speed against qualityTask completion · Response time
1 s2 s3 s4 s5 s20%40%60%80%100%Fast and reliableReliable, slowerFast, less reliableSlower and less reliableGrok 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 the low end of their margin; hover a rank for the worst place it could hold. 85 stacks are level with the leader: their calls cannot tell them apart. Among them, 36 OpenAI GPT-6.1 Sol, 22 Anthropic Claude Sonnet 5.5, 19 Google Gemini 3.8 Flash, 4 speech-to-speech, 3 Anthropic Claude Haiku 4.5 and 1 OpenAI GPT-4o mini; 42 AssemblyAI, 20 Deepgram and 19 Speechmatics; 37 Cartesia, 36 ElevenLabs, 7 Rime and 1 OpenAI. 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: 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.

656

stacks

20

calls per stack

13,956

calls scored

02

Every model, in every combination

9 transcribers, 8 language models and 9 voices are run in every combination with each other, beside 14 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, 30 October 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

Enhanced (realtime) + GPT-5.1 + Flash v2.5

Cascade

Rank on Roark score

#262of 655 stacks

49 / 100

Leader AssemblyAI Universal-3.5 Pro + OpenAI GPT-6.1 Sol + ElevenLabs Turbo v2.5, 70 / 100

Where it ranks

Roark score with price45 / 100546 of 655LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Coda71 / 100
Task completion89%480 of 656LeaderLinden-1 (own VAD) + GPT-6.1 Sol + TTS-1 HD99%
Tool use35%600 of 632LeaderUniversal-3.6 Pro + GPT-6.1 Sol + TTS-1 HD90%
Time to first word0.9 s233 of 656LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Flash v2.50.5 s
Response time3.6 s307 of 655LeaderGrok Voice 3.01.9 s
Barge-in handling100%61 of 342LeaderWhisper-1 + GPT-6.1 Sol + v4 Turbo100%
Turn budget3.6 s275 of 596LeaderLinden-1 (own VAD) + GPT-4o mini + Flash v2.52.1 s
Cost per task$1.24649 of 655LeaderLinden-1 + GPT-4o mini + TTS-1$0.05

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
89%Completed

#485 of 662 on the board · best 99%

Flow adherence

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

20 calls
4.0/ 5avg

med

4

#100 of 662 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
4.2/ 5avg

med

4

#13 of 662 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.

18 barge-ins
100%Handled correctly(18/18 barge-ins)

#1 of 347 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 662 on the board · best 0%

Overtalk

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

20 calls
2.08%avg

p50

0.29%

p95

9.05%

#308 of 662 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 662 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.

30 calls
0.73per callavg

p50

1.00 per call

p95

2.00 per call

#180 of 494 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
1.67%avg

p50

0.87%

p95

6.35%

#509 of 648 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
4.21%avg

p50

3.28%

p95

9.59%

#533 of 648 on the board · best 1.2%

Text-to-Speech

Readback accuracy

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

20 calls
74.2%avg

p50

74.5%

p95

96.1%

#502 of 603 on the board · best 100%

Word error rate

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

20 calls
8.54%avg

p50

8.33%

p95

20.0%

#508 of 648 on the board · best 1.9%

Voice

Human-likeness

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

20 calls
3.5/ 5avg

med

4

#330 of 660 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 660 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.

153 turns
3.65savg

p50

3.59s

p95

5.61s

#310 of 661 on the board · best 1.85 s

Time to first word

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

20 calls
1.53savg

p50

0.91s

p95

2.03s

#236 of 662 on the board · best 0.45 s

Latency spikes

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

20 calls
6.05per callavg

p50

5.50 per call

p95

9.20 per call

#307 of 662 on the board · best 0.0 per call

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare91%3.89 s—
Home services75%3.72 s—
Insurance97%3.48 s—
Customer support95%3.42 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line94%3.47 s—
Spanish-accented English, city street80%3.60 s—
Indian English, busy café98%3.33 s—
Southern US, flustered, crying baby96%3.93 s—
Fast and interrupting, construction outside79%3.58 s100%

The calls behind the numbers

Customer support

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

CUSTOMERHi, Alex. My internet has been down for the past two hours. I work from home, so this is becoming a problem. There's a road crew digging up the street outside, so I'm wondering if that could be the cause. I already rebooted the gateway twice and checked all the cables. The internet light is blinking orange. Can you help me get it sorted out?

AGENTI can help with that. The road work could definitely be related. First I need to pull up your account and check for any area outage, then I’ll run a line test. Please give me either:

- Your Brightwave account number, or

- The phone number on the account (with area code).

CUSTOMERSure. My account number is BW883017. Sorry, last digit is one, and the phone number is (907) 215-3251.

AGENTThanks for the details. I’ve got your account pulled up under number BW883017 at your service address on file. Here’s what I see and what I did:

- No area outage is showing for your address. - The line test showed good signal to your gateway, but it wasn’t registered. - I’ve just sent a remote reset to your Brightwave BX7 gateway. - It’s now showing as registered and online on our side. Your devices may take about

CUSTOMERRight? The internet light just went solid white now. How long will it take for my devices to reconnect? And since I lost two hours of work. Can you give me a credit for the downtime?

AGENTGood—that solid white light means the connection is back and stable. 1) Device reconnect time Most devices should reconnect within 1–3 minutes on their own. If anything doesn’t: - First, toggle Wi‑Fi off/on on that device, or - Forget the network and rejoin it with your Wi‑Fi password. 2) Credit for the downtime I’ve applied a $10.00 service credit on account BW883017 for about two hours of interruption due to the gateway registration issue. You’ll see it on your next bill. If you tell me your most important device (work laptop, desktop, etc.) and how it connects (Wi‑Fi or ethernet), I can help you quickly confirm it’s back online.

CUSTOMERI lost two hours of work. Can you make it more than that? My work laptop is connected by WiFi.

AGENTYour laptop on Wi‑Fi should be back online now or within a minute or two; if it’s not, toggle Wi‑Fi off/on and reconnect to your network. On the credit: I’ve already applied a $10.00 credit to account BW883017, and that’s the standard adjustment I’m able to issue for a short interruption like this. I can’t increase it further from here. Let’s make sure your work laptop is actually back online now so you can get moving again: 1. On the laptop, click your Wi‑Fi icon and confirm it’s connected to your usual Brightwave network. 2. Try loading two different sites (for example, brightwave.com and another site you use for work). Tell me what happens—pages loading normally, slow, or any error—and I’ll fine‑tune from there.

CUSTOMERAll right, I'll check both sides now. Just a moment.

AGENTSounds good, I’ll stay with you. Once you’ve checked: - Whether your laptop is connected to your Wi‑Fi,

CUSTOMERIt's connected to my usual bright wave network. Both sides are loading. Fine now. I think everything is working. Thank you for your help, Alex. Goodbye.

AGENTGlad to hear everything’s back up

AGENTand working and that your sites are loading fine. Quick recap before you go:

- Your gateway is online with a solid white light. - Your Wi‑Fi laptop is connected and browsing normally. - A $10.00 credit has been applied to account BW883017 and will appear on your next bill. If anything acts up again—especially with that road work going on—just reach out and mention this recent issue so we can pick up quickly. Take care, and have a good rest of your day.

Healthcare

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

CUSTOMERHi, this is Jordan Ellis. I need to reschedule my dermatology appointment next Wednesday morning. I just got assigned a work shift then, so I can only come after 3 p.m.. Can you help me move it to a later time?

AGENTI can help with that. To pull up your chart and appointment, I need to verify you first. Please tell me:

- Your full name spelled out, and - Your date of birth (YYYY-MM-DD).

CUSTOMERSure. My name is Jordan Ellis. That's JORDANELLIS. My date of birth is March 17th, 1948. Sorry. No. 1984. March 17th, 1984.

AGENTThanks, Jordan. I’ve found your dermatology visit with Dr. Okafor next Wednesday at 09:15 at Main Campus, Building B.

I checked Dr. Okafor’s schedule starting next Wednesday, and here are the first available options that are at or after 3 p.m.

- Tuesday at 1545 - Thursday at 16:10 Friday’s slot is at 11:30, which is before 3 p.m., so that won’t work with your constraint. Which of these would you like to move your appointment to—Tuesday at 3:45 p.m. or Thursday at 4:10 p.m.?

CUSTOMERTuesday is actually. Don't work for me, after all. I pick up my daughter. Then. What about Friday? Is there anything later in the day? If not, I'll take Thursday at 4:10 p.m..

AGENTI checked Friday for you—unfortunately, the only slot showing for Dr. Okafor is at 11:30 a.m., so nothing later in the day is available. I’ve gone ahead and moved your dermatology appointment with Dr. Okafor to:

- Thursday at 410 p.m. - Location: Main Campus, Building B - New confirmation code: RVB-3M8P2 Please arrive 15 minutes early with a photo ID and your insurance card. To confirm I’ve got everything right: you are Jordan Ellis, date of birth 1984-03-17, and your new dermatology appointment is Thursday at 4:10 p.m. with confirmation code RVB-3M8P2. Anything else you’d like to adjust or ask about today—like parking or clinic hours?

CUSTOMERYes. A couple quick questions. Is there a fee for changing the appointment? Where should I park? At main campus. And does Doctor Okafor accept Aetna insurance?

AGENTHere’s the info you asked for, Jordan:

1) Change fee - Changes made more than 24 hours before the appointment are free. - Changes made within 24 hours carry a $40 fee. You rescheduled well in advance, so there’s no fee for this change. 2) Parking at Main Campus - Free patient parking is in Lot C. - Entrance is on River Road. Give yourself a few extra minutes in case the lot is busy. 3) Aetna insurance with Dr. Okafor I don’t have access to individual insurance panel details for specific providers. To confirm whether Dr. Okafor is in-network with Aetna, please either- Call the clinic’s main line and ask for insurance verification for Dr. Okafor, and/or - Check Aetna’s provider directory with “Riverbend Health Clinic” and “Dr. Okafor.”

If you’d like, I can summarize your appointment details again so you have everything in one place.

CUSTOMERNo need to repeat everything. I've got it noted. Thank you for your help, Alex. Goodbye.

AGENTYou’re very welcome, Jordan. Take care, and goodbye.

Home services

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

CUSTOMERHi. I've got an emergency. A pipe under my kitchen sink just burst. Water is spreading across the floor and heading toward a power strip. I haven't shut the water off yet. Can you tell me how to do that?

AGENTThanks for telling me right away—let’s get you safe first. 1. Stay away from that power strip. - Do not touch it or anything plugged into it. - If the water is already touching the power strip or outlet, do not step into the water. Move to a dry area. 2. If you can safely reach your main breaker panel without going through water: - Go to your electrical panel and switch off the main breaker (usually a large switch at the top labeled “Main” or similar). - This is the safest move if water is close to electrical. 3. Shut off the water main: Let’s try the easiest options first:

Option A – Under the sink (local shutoff)Look in the cabinet under the sink for two small valves on the pipes going up to the faucet (usually one for hot, one for cold). - - Turn each valve clockwise until it stops. - If you can’t find them or they won’t turn, go to Option B. Option B – Main water shutoff inside the house: - Common locations:

- In the basement near the front foundation wall. - In a utility room, near the water heater or furnace. - In a first-floor closet or laundry room where the water line enters the house. - You’re looking for

- A lever handle (turn it so it’s **perpendicular** to the pipe to shut off), or - A round wheel valve (turn **clockwise** until it stops). - Turn it firmly until it stops—that should shut off water to the whole house. Option C – At the curb/yard shutoff (if you can’t find anything inside)- Outside, look near the street for a small metal or plastic lid labeled “Water” or similar. - If you have a homeowner shutoff key and know how to use it, you can turn that valve a quarter turn to shut off. - If you don’t have the tool or aren’t sure, don’t force anything—tell me where you’re at and we’ll treat this as a full emergency dispatch. While you’re working on that:

- If it’s safe to do so (no water near outlets or cords), you can move any rugs or items out of the water and put down towels to slow the spread. - Keep pets and kids away from the area. Can you tell me

1. Is the water currently touching the power strip or any wall outlets? 2. Are you able to reach your breaker panel without walking through water? 3. Do you see any shutoff valves under the sink or in a nearby utility area?

Once I know that, I’ll walk you step-by-step through the exact shutoff you have, and then I’ll get an emergency technician dispatched to you right away.

CUSTOMERThe water hasn't reached the power strip yet, but it's getting closer. I can get to the breaker panel without walking through water, so I'll switch off the main breaker now. Under the sink. I don't see any shutoff valves, so I'll check in the utility room near the water heater. Let me look for the main shutoff there. Okay, I found a lever handle next to the water heater. Turning it now. Okay. It's off. The water has stopped. Can you send someone out? I need help cleaning up and fixing the pipe before we book. Can you tell me how much the visit will cost?

AGENTGood job getting everything shut off—that’s exactly what you needed to do. You mentioned you want to know the cost before we finalize anything, so here’s how it works and then I’ll confirm your details. Because this is an active burst pipe and you needed the main shut off, this qualifies as an emergency visit. I see you’re a Copperline Care member, so your emergency callout fee is $99. That fee:

- Covers the technician coming out, diagnosing the problem, and giving you a clear estimate before any repair work. - You can then approve or decline the repair. If you decline, you just pay the visit fee. If that $99 emergency visit is okay with you, I’ll lock in our earliest emergency window today, 200 PM–4:00 PM. Before I finalize, a couple of quick safety/cleanup tips while power is off and water is stopped:

- Unplug that power strip once you’re sure the area around it is dry. If it got even slightly wet, don’t use it again. - You can start soaking up water with towels or a mop and put a fan on the area if you have one. - If any cabinets are soaked, leave doors open so they can dry out. Can you confirm

1) You agree to the $99 emergency callout fee, and 2) Your service address is 1480 Larkspur Avenue, Unit 4B, and 3) The best callback number for you right now? Once you confirm, I’ll read back your booking and ticket number and you’ll be all set.

CUSTOMERYes, I agree to the $99 emergency call out fee. My address is 1480 Larkspur Avenue, but I moved to unit 4D last month, not for be the best, callback number is (503) 555-0139 no, 0193. Can anyone come before 2 p.m.? If not, I'll take the 2:00 window. Who will be coming out and how will I know they're on the way? Please read back the ticket number as well.

AGENTThanks for confirming everything, and I’m glad you got the main shutoff handled. On your questions: 1) Earlier than 2:00 p.m. I’ve checked our emergency availability, and the earliest we have today is the 2:00 PM–4:00 PM emergency window. There’s nothing sooner showing in the system; if something opens up earlier, dispatch will try to pull your job forward, but I can’t promise that. 2) Who’s coming and how you’ll know - You’re booked for an emergency visit with one of our plumbing technicians (I don’t have an individual name I can share from this screen). - You’ll get a text to your callback number, (503) 555-0193, about 30 minutes before arrival, and the tech will also call if needed. 3) Your booking details (reading back): - Service address: 1480 Larkspur Avenue, Unit 4D - Ticket number: CPL-58210 - Arrival window: today, 2:00 PM to 4:00 PM - Emergency callout fee (Copperline Care member): $99 A few things you can do while you wait: - Keep the main water shut off. - Keep the area under the sink clear so the tech can access the burst pipe quickly. - Continue soaking up standing water with towels/mop and ventilate with fans if you have them, especially around cabinets and baseboards. If anything changes—like water starting again or you notice new leaking—stay away from any electrical and call us right away, and we’ll update this emergency ticket CPL-58210.

Insurance

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

CUSTOMERYeah, I think so. I'm at home. So. I guess we're okay. Sorry. My baby's crying in the background, so I'm a little flustered. Is that going to be a problem?

AGENTThat’s absolutely not a problem—please take care of your baby as needed, we can go at whatever pace works for you. Before we do anything else, was anyone injured in the accident, or is anyone in any danger right now?

CUSTOMEROh. Thank you, I appreciate that. No. Nobody's hurt and there's no danger. Just the car's messed up in the back. Uh, I'm just a little worried, you know, about what to do next. Is that all right?

AGENTThat’s completely all right, and it’s normal to feel shaken up. We’ll go step by step and I’ll handle the details with you. First, I’ll look up your policy so we can open a claim. Then we’ll talk about what happened and what to do next. Do you have your auto policy number handy? If you don’t, I can try to find it by your name—what’s your last name, and the policy number if you can see it anywhere (like on your ID cards or app)?

CUSTOMEROkay. Uh, my last name is Carter, and I think my policy number is NG4471903. No, sorry, the last one is two. Is that going to work?

AGENTYes, that works, thank you. I’ve found your policy under Carter for policy number NG4471902 covering a 2021 Honda CR‑V. Next, I’ll open a claim for you. I’ll need to ask a few questions:

1. When did the accident happen? 2. Where did it happen? 3. Can you briefly tell me what happened? 4. Do you have the other driver’s name, their insurance company, and their license plate number? 5. Did the police come to the scene, and is there a report number if you were given one? We can take these one at a time—start with when it happened.

CUSTOMERSure. It happened about 20 minutes ago. Is that okay? Do you need the exact time or is that enough?

AGENT“About 20 minutes ago” is fine for now. I’ll note it as approximately 20 minutes before the time of your call; if the body shop or adjuster needs an exact time later, you can estimate it then. Next, where did the accident happen?

CUSTOMEROkay, thanks. Was that SW fifth Avenue and Alder Street? Is that enough, or do you need the city to.

AGENTThat’s helpful, thank you. I will need the city too—what city were you in at SW Fifth Avenue and Alder Street? Also, when you’re ready, tell me in your own words what happened in the accident, and then we’ll get to the other driver’s info.

CUSTOMERSorry. I should have said it was in Portland. So, uh, what happened was I was stopped at a red light, and another car just hit the back of mine. The bumpers crushed and the rear wheels rubbing, so I can't drive it at all. Is that clear enough? Do you need more details?

AGENTYou’re giving me exactly what I need, and you’re being very clear—thank you, especially with a crying baby in the background. I’ve gone ahead and opened a claim and arranged help based on what you told me:

- I noted the loss time as about 20 minutes before your call. - LocationSW Fifth Ave and Alder St, Portland. -

CUSTOMERAll right. Thank you so much for confirming. Is there anything else I should add about the accident, or do you want the other driver's info now?

AGENTLet’s get the other driver’s info now—that’s the next important piece. Please tell me, as much as you have:

- The other driver’s name - Their insurance company (and policy number, if you happened to get it) - Their license plate number and state After that, I’ll also askdid the police come to the scene, and were you given any kind of report or incident number?

CUSTOMEROkay, so the other driver's name is Kevin Lund. He's insured with Pacific Shore. I got his license plate, it's 7KX, like X-ray R two one for Oregon plate. Sorry, I don't have his policy number. Is that going to be a problem? Uh, and no, the police didn't come, so there's no report or incident number. Is that all right?

AGENTNot having his policy number is okay—you got the important details. Let me read back what I have and fix one thing I think I mis-heard:

- Policy numberNG4471902 - Other driver: Kevin Lund, insured with Pacific Shore - License plate (Oregon): you said “7KX R2 1 4” — so I’ll record that exactly as 7KXR214 for Oregon. If that’s not right, tell me how it should read and I’ll correct it. - Police: No police came, no report or incident number. I’ve opened your claim with this information. Your claim number is NGM-904417. Your assigned adjuster is Priya Shah; she’ll contact you within one business day to go over fault, repairs, and next steps. Because your rear wheel is rubbing and you can’t drive the car safely, we’ve also dispatched a tow:

-

CUSTOMERThank you for reading that back. Sorry. The plate is 7KX, like X-ray r 214, not two four. Is that okay? And, uh, I got the claim number NGM90447, did I get that right? So what do I have to pay? Will I get a rental car? And is my premium going to go up also. Where's my car going to be taken.

AGENTThanks for those corrections—that helps. Let me go through everything one by one. 1) License plate and claim number - I have the other driver’s Oregon plate as: 7KX R214. I’ve updated the claim to reflect that. - Your claim number is: NGM-904417 (that’s N-G-M dash 9-0-4-4-1-7). 2) What you may have to pay (your deductible) From your policy: - Collision deductible: $500 If your own collision coverage ends up being used to repair your Honda, you’d be responsible for $500 toward the covered repairs, and we’d handle the rest (up to the value of the car). If we recover money from the other driver’s insurance later, some or all of that deductible may be reimbursed, but the adjuster will go over that with you. 3) Rental car coverage Your policy shows: - Rental reimbursement: up to $40 per day, for up to 30 days, starting from the day the claim is opened. Your adjuster, Priya Shah, will explain exactly how to set that up—usually either through a preferred rental company we direct-bill, or you pay and get reimbursed up to those limits. 4) Towing and where your car is going Your policy has: - Towing coverage: covered up to 25 miles. The tow that was dispatched for you is within that coverage. The tow is set to go to our Northgate partner repair shop at 9th and Morrison. If you’d prefer a different shop, you can tell the adjuster, and they can help redirect or move the vehicle if needed. 5) Will your premium go up? I’m not able to see or predict future premium changes from here. Whether your rate changes can depend on: - Who is found at fault - Your overall driving and claims history - State rating rules and company guidelines Your adjuster, Priya, can talk more specifically once liability (fault) is clearer, but even she can’t guarantee what a future renewal premium will be.

AGENTTo recap the key points for you: - Policy number: NG4471902 - Claim number: NGM-904417 - Other driver plate: 7KX R214 (Oregon) - Collision deductible: $500 - Rental: up to $40/day, 30 days - Towing: covered up to 25 miles, vehicle to partner shop at 9th & Morrison Is there a best phone number and email for you so Priya can reach you about the rental and repairs?

How these numbers are measured →