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

Linden-1 (own VAD) + GPT-5.1 + Sonic-3.6

Cascade

Rank on Roark score

#282of 655 stacks

50 / 100

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

Where it ranks

Roark score with price51 / 100419 of 655LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Coda71 / 100
Task completion94%211 of 656LeaderLinden-1 (own VAD) + GPT-6.1 Sol + TTS-1 HD99%
Tool use28%627 of 632LeaderUniversal-3.6 Pro + GPT-6.1 Sol + TTS-1 HD90%
Time to first word1.0 s308 of 656LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Flash v2.50.5 s
Response time2.9 s75 of 655LeaderGrok Voice 3.01.9 s
Barge-in handling90%329 of 342LeaderWhisper-1 + GPT-6.1 Sol + v4 Turbo100%
Turn budgetn/aLeaderLinden-1 (own VAD) + GPT-4o mini + Flash v2.52.1 s
Cost per task$0.43506 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
94%Completed

#214 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
4.3/ 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
4.3/ 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.

10 barge-ins
90%Handled correctly(9/10 barge-ins)

#331 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
1.94%avg

p50

0.62%

p95

8.42%

#449 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.

31 calls
0.77per 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
1.41%avg

p50

0.63%

p95

5.91%

#446 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
4.00%avg

p50

2.91%

p95

10.6%

#514 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
68.0%avg

p50

68.9%

p95

96.8%

#573 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
11.9%avg

p50

8.18%

p95

30.9%

#613 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
3.9/ 5avg

med

4

#47 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.

114 turns
2.92savg

p50

2.89s

p95

5.46s

#76 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
0.97savg

p50

0.98s

p95

1.72s

#311 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
2.90per callavg

p50

3.00 per call

p95

5.05 per call

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

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare100%2.88 s—
Home services85%2.63 s—
Insurance98%2.65 s—
Customer support91%3.68 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line94%2.63 s—
Spanish-accented English, city street89%3.22 s—
Indian English, busy café96%3.21 s—
Southern US, flustered, crying baby98%2.93 s—
Fast and interrupting, construction outside91%2.65 s90%

The calls behind the numbers

Customer support

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

CUSTOMERHey, I'm short on time.

CUSTOMERInternet's been down for two hours.

CUSTOMERI work from home.

CUSTOMERAnd there's a road crew digging up the street. Right outside the gateway. Light is blinking orange.

CUSTOMERI already rebooted it twice and checked all the cables.

CUSTOMERCan you check what's going on?

AGENTI checked your line and there’s no area outage at your address. Your account number is BW-883011. Your gateway had lost its registration, so I just pushed a remote reset. It’s now showing as registered and online on my side. What you should see: - The light should turn solid white (or solid

CUSTOMERGot it. Yep. Got.

CUSTOMERIt. The light just went solid white.

CUSTOMERHow long until all my devices reconnect?

CUSTOMERCan you check if the road crew outside is the cause?

CUSTOMERAlso, I need a credit for the downtime.

AGENTMost devices should be back within 2–3 minutes, but some work laptops/phones can take up to 5–10 minutes if they’re using VPN or do Wi‑Fi scanning slowly. If anything’s still offline after 10 minutes, have it forget the Wi‑Fi network

CUSTOMERRight, I get it.

CUSTOMERSo. About that credit. I lost two hours

AGENTYou’re all set on my side,

CUSTOMERof. Okay.

AGENTI’ve added a credit for the downtime on your account BW-883011. - Credit

AGENTamount: $10.00. - Reason: roughly 2 hours of outage while the gateway was offline and you work from home. - Where it shows: it will appear on your next bill. On the road crew: I can’t see their specific work orders from here, so I can’t directly confirm they caused it. What I can see is that: - There was no area outage on our side. - Your line signal to the gateway looked good. - The problem was the gateway being “not registered”, and it came back immediately after a remote reset. That pattern is consistent with a brief disruption near the physical line (like construction) that cleared once things resynced, but I can’t officially tag it to that crew without a field report. If your connection drops again while they’re still working, tell me and I’ll re-test the line right away and, if needed, get a tech scheduled.

Healthcare

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

CUSTOMERHi, Alex.

CUSTOMERI am having one appointment with dermatology next Wednesday morning.

CUSTOMERI need to move it because I have a work shift now. At that time, can you help me reschedule?

CUSTOMERMy name is Arjun Mehta.

AGENTI can help with that. I’ll need a couple more details to look you up and find your appointment. 1. What is your date of birth? 2. When you say “next Wednesday

CUSTOMERLa. Sorry. I got distracted there. My date of birth is March 17th, 1948.

CUSTOMERSorry. No. 1984. March 17th, 1984.

CUSTOMERAbout the.

CUSTOMERAppointment. It's next Wednesday morning.

CUSTOMERI need to move it to after 3 p.m..

AGENTThanks for the correction, Mr. Mehta. I have you as: - Name: Arjun Mehta. - Date of birth: March 17, 1984. - Current dermatology visit: next Wednesday at 9:15 a.m. with Dr. Okafor, Main Campus, Building B. You asked to move it to after 3 p.m.. With Dr. Okafor, the next available late-day options I can offer are: - Tuesday at 3:45 p.m. - Thursday at 4:10 p.m. There’s also a Friday slot, but it’s 11:30 a.m., which is before 3 p.m., so that doesn’t meet your request. Would you like to move your appointment to: - Tuesday at 3:45 p.m., or. - Thursday at 4:10 p.m.? Once you choose, I’ll reschedule it and read back the new details and confirmation code.

CUSTOMERTuesday. Does not work after all. I pick up my daughter on Tuesdays.

CUSTOMERWhat about Friday? Any slots available after 3 p.m.? If not, then I will take Thursday at 4:10 p.m..

AGENTThanks for the update. I checked Friday for you—Dr. Okafor only has 11:30 a.m. available that day, nothing after 3 p.m. Since you said you’ll take Thursday if Friday doesn’t work, I’ve gone ahead and moved your appointment. Here are your new details: - Name: Arjun Mehta - Date of birth: March 17, 1984 - Department: Dermatology - Provider: Dr. Okafor - New day and time: Thursday at 4:10 p.m. - Location: Main Campus, Building B - Confirmation code: RVB-3M8P2 Please arrive 15 minutes early with a photo ID and your insurance card. Do you want me to repeat any of that, or help with anything else today?

CUSTOMERNo.

CUSTOMERThat's clear. I have a few quick questions.

CUSTOMERIs there a fee for changing the appointment? Where should I park?

CUSTOMERAnd does Doctor Okafor accept Aetna insurance?

AGENTHere are the answers to those: 1. Fee for changing the appointment. - The clinic’s policy is: changes made more than 24 hours before the appointment are free. - Changes within 24 hours of the appointment time carry a $40 fee. Since we moved your appointment well in advance, there should be no change fee for this reschedule. 2. Where to park. - There is free patient parking in Lot C, with the entrance on River Road. - Give yourself a few extra minutes in case the lot is busy. 3. Does Dr. Okafor accept Aetna insurance? - I don’t have provider-by-insurance-panel access in this system, so I can’t safely confirm Aetna coverage for Dr. Okafor from here. - To be sure, please either: - Call the clinic’s main line and ask if Dr. Okafor is in-network for Aetna, and/or. - Check with Aetna (website or phone) using the clinic and provider name. If you’d like, I can restate your appointment details once more so you have everything in one place.

CUSTOMERYes.

CUSTOMERPlease.

CUSTOMERKindly read. Back the new appointment details and confirmation code.

AGENTHere are your updated appointment details: - Name: Arjun Mehta. - Date of birth: March 17, 1984. - Department: Dermatology. - Provider: Dr. Okafor. - Day and time: Thursday at 4:10 p.m. - Location: Main Campus, Building B. - Confirmation code: RVB-3M8P2. Arrival instructions: Please arrive 15 minutes early with a photo ID and your insurance card.

CUSTOMERYes, that's exactly

AGENTI’m glad that all looks right. Before

CUSTOMERright. Thank you for your help. Alex.

AGENTwe wrap up, do you want me to: - Note anything about your Aetna insurance for the front desk, or. - Go over parking or the change-fee policy one more time?

Home services

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

CUSTOMERHi. I've got a plumbing emergency. The pipe under my kitchen sink just burst and water is spreading across the floor toward a power strip. I haven't shut the water off yet.

CUSTOMERCan you help?

AGENTYes, I can help. First, let’s keep you safe and stop the water: 1. Stay away from the power strip and any outlets the water is reaching. - Don’t touch the power strip, cords, or any appliances in that area. - If the water has already reached the strip, do not step into the water. 2. Shut off the water: - If you can safely get to the shutoff valve under the sink (usually a small oval or round handle on the pipe), turn it clockwise until it stops. - If that’s not reachable or doesn’t stop the flow, go to your main water shutoff: - Often in a basement, garage, utility room, or outside near the street in a meter box. - Turn the main valve clockwise to shut it off. 3. If it’s safe and

CUSTOMEROkay.

AGENTthe floor

AGENTYes, I can help. First, let’s keep you safe and stop the water: 1. Stay away from the power strip and any outlets the water is near. - Don’t touch the power strip or anything plugged into it. - If water is already touching the power strip or wall outlets, do not go near it. 2. Shut off the water: - Under the sink: look for two small shutoff valves (one for hot, one for cold) on the pipes going up to the faucet. - Turn each valve clockwise (right) until it stops. - If those valves are not working or you can’t find them, go to your main water shutoff: - Often in the basement, garage, utility room, or on an outside wall near the street. - Turn the main valve clockwise until it stops. 3. If it’s safe to do so and the water is very close to the power strip: - If you can reach your breaker panel without walking through water, you can switch off the breakers for the kitchen or, if you’re unsure which, turn off the main breaker. - If you would have to walk through water to reach the panel, do not do that—just stay clear and focus on shutting off the water. Please go ahead and shut off the under-sink valves or the main water now. I’ll stay with you—tell me when the water is off or if you’re unsure what you’re seeing, describe what you see and I’ll guide you. ---. Once the water is off or under control, I’ll get a plumber out to you on an emergency basis. I’ll need: 1. Your name. 2. The service address (including unit number or gate code if applicable). 3. The best callback phone number. After that, I’ll check our emergency availability and the exact emergency service fee for your location, tell you the amount, and with your okay I’ll book the earliest arrival window. Then I’ll read back your address, any access info, your callback number, and your ticket number.

CUSTOMERSure. My name is Jordan Ellis.

CUSTOMERThe address is 1480 Larkspur Avenue, unit 4D. I moved from unit four B to 4D last month, so please make sure it's 4D. The gate code is Pound two

AGENTThanks, Jordan. I’ve got your name and updated unit. Before we book, I want to confirm two safety things quickly: - Has the water been shut off now (either under the sink or at the main)? - Has the water reached the power strip, or is it just getting close? If the water is still running, please turn the under-sink valves fully clockwise, or the main shutoff, right away. Stay away from the power strip and don’t step in any water near it. If water is touching the strip or wall outlets, do not go into that water—if you can reach your breaker panel without crossing water, switch off the kitchen breaker or main; otherwise just keep clear. Now, for service details: - You’re in our system at: 1480 Larkspur Avenue, previously unit 4B. - I will update this to: 1480 Larkspur Avenue, unit 4D. - Gate code: #2. - You’re a Copperline Care member, so your emergency callout fee is $99. - That’s due on completion; you can pay by card or check. Earliest emergency arrival window I can offer: - Today, 2:00 PM to 4:00 PM (emergency). With your approval: 1) We’ll open an emergency service request for the burst pipe under the kitchen sink. 2) We’ll book that 2:00–4:00 PM today emergency window at the $99 Copperline Care emergency fee. Please confirm: 1) Is the water now shut off? 2) What’s the best callback phone number for you? 3) Do you approve the $99 emergency fee and want the today 2:00–4:00 PM window?

CUSTOMERseven. 719. My callback number is 503. Yes.

CUSTOMERThe water is shut off now. My callback number is 503. Five. 550139.

CUSTOMERNo. 0193.

CUSTOMERCould anyone come before 2 p.m.? If not, I'll take the earliest emergency window and. Yes.

CUSTOMERI approve the $99 emergency fee.

AGENTThanks, Jordan, and thanks for confirming the water is shut off and approving the $99 emergency fee. I’ve already booked the earliest emergency window we have today; there’s nothing available before 2:00 PM, so this is the soonest we can get to you. Here’s what I’ve set up: - Service request: Emergency – burst pipe under kitchen sink, water had been spreading toward a power strip; water now shut off. - Ticket number: CPL-58210. - Arrival window: Today, 2:00 PM to 4:00 PM (emergency). - Service address: 1480 Larkspur Avenue, unit 4D. - Gate code: #2. - Callback number: I currently have 503 on the ticket. It sounds like you were trying to correct that callback number just now. Please give me the full, correct phone number exactly as you want the technician to use (for example: “503-555-0139”), and I’ll update it and read it back to you. Until we arrive, a few quick safety/cleanup tips: - Keep away from that power strip and any outlets the water reached. - If you can safely unplug the power strip without stepping in water, you may do so; otherwise, leave it alone. - You can put down towels or a bucket under the pipe, as long as you’re not near any energized electrical. Once you give me the correct full callback number, I’ll confirm it’s updated on ticket CPL-58210.

CUSTOMERThe correct callback number is 503.

CUSTOMER555.

CUSTOMER0193. Please update that for the technician. Can you tell me who'll be coming and how? I'll know they're on the way. And I'd like to hear the ticket number again.

AGENTGot it, thank you for clarifying that in parts. I’ve updated the callback number on your ticket to: - Callback number: 503-555-0193. Here’s everything confirmed: - Ticket number: CPL-58210. - Service address: 1480 Larkspur Avenue, unit 4D. - Gate code: #2. - Callback number: 503-555-0193. - Appointment: Today, 2:00 PM to 4:00 PM, emergency plumbing visit for the burst pipe under the kitchen sink. How you’ll know they’re on the way: - Our system shows: “The technician texts the callback number 30 minutes before arrival.” - So you’ll get a text on 503-555-0193 about half an hour before they show up. I’m not able to give or confirm the technician’s personal name here, but your visit is fully booked under ticket CPL-58210, and the on-call emergency plumber for that window will be dispatched to you. If anything changes (like water starting again or an electrical concern), stay clear of the power strip/outlets and call us right away so we can update the ticket.

Insurance

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

CUSTOMERYes, I am safe. I am standing next to my car on the sidewalk. There's traffic going by, but I'm okay.

AGENTI’m glad you’re safe. Is anyone injured at the scene—either in your car or the other vehicle—or is anyone in any danger right now? If anyone is hurt or in danger, please hang up and call 911 immediately before we continue.

CUSTOMERNo, nobody is hurt. It's just damage to the cars. We are both okay.

AGENTUnderstood, thanks for letting me know. Let’s get your policy pulled up so we can open a claim. What’s your auto policy number, and your last name as it appears on the policy?

CUSTOMERSure. My policy number is NG4471903. No, sorry, last one is two. My last name is Ramirez.

AGENTThank you, Ms. Ramirez. I have your policy ending in 1902 pulled up for your 2021 Honda CR‑V. I’m going to get the details of what happened so we can open your claim. 1) First, when did the accident happen? 2) Where did it happen? 3) Can you briefly tell me what happened?

CUSTOMERSo the accident happened about 20 minutes ago. It was at SW Fifth Avenue and Alder Street.

CUSTOMERI was stopped at a red light.

CUSTOMERAnd another car hit the back of my car. The bumper is crushed and the rear wheel is rubbing, so I cannot drive it. Police did not come.

AGENTThanks for walking me through that, Ms. Ramirez. I’ve got your claim started, and I’ll also go over your coverage and the tow we’ve arranged. First, I want to read a couple of key details back to you: - Policy number I have: NG4471902. - Claim number I’ve opened: NGM-904417. Please let me know if either of those is not correct. From what you told me: - Loss date/time: about 20 minutes ago. - Location: SW Fifth Avenue and Alder Street. - What happened: You were stopped at a red light when another vehicle hit the rear of your 2021 Honda CR‑V. The rear bumper is crushed and the rear wheel is rubbing, so the car cannot be driven. - Injuries: None reported. - Police: Police did not come; no report filed. - Other driver: We’ll still need the other driver’s name, insurance company, and license plate when you have those handy. Now, based on your policy’s coverage: - Collision deductible: $500. That’s the amount you’d be responsible for toward repairs if this goes through your policy under collision coverage. - Rental coverage: $40 per day for up to 30 days, starting today (the day the claim is opened). - Towing: Covered up to 25 miles. Because you said the car isn’t drivable, we’ve already set up a tow: - Tow company: Eastside Towing. - Status: Dispatched. - ETA: about 45 minutes. - Destination: Northgate partner repair shop at 9th and Morrison. They’ll come to: SW Fifth Avenue and Alder Street where you and the vehicle are now. A few quick questions to finish things up: 1. Do you have the other driver’s name, insurer, and license plate with you right now? If so, please read them to me and I’ll add them to the claim. 2. Is the tow destination (our

CUSTOMERYes.

AGENTThanks, Ms. Ramirez. I’ve gone ahead and set everything up based on what you told me. Here’s what we have: - Verified policy number: NG4471902. - What happened: You were stopped at a red light at SW Fifth Avenue and Alder Street when another car hit the back of your 2021 Honda CR‑V. Rear bumper is crushed and the rear wheel is rubbing, so it’s not safe to drive. No one is injured and police did not come. I’ve opened a claim for you: - Claim number: NGM-904417. - Assigned adjuster: Priya Shah – you’ll hear from her within one business day. Your coverage for this policy: - Collision deductible: $500. - Rental car: $40 per day, up to 30 days, starting today (the day the claim is opened). - Towing: Covered up to 25 miles. I’ve also arranged a tow: - Tow company: Eastside Towing. - ETA: About 45 minutes. - Destination: A Northgate partner repair shop at 9th and Morrison. Let me read back a couple of key items to be sure they’re correct: - Policy number: NG4471902. - Claim number: NGM-904417. Please correct me if either of those is wrong. Next steps for you right now: 1. Stay safely off the road while you wait for the tow. 2. When the truck arrives, confirm they’re from Eastside Towing and that they’re taking the car to 9th and Morrison. 3. Keep any receipts (like for temporary transportation) and take a few photos of the damage and the intersection if it’s safe to do so. Do you have the other driver’s name, insurance company, and license plate number handy? I’d like to add that to your claim file.

CUSTOMERYes, I have those.

CUSTOMERThe other driver is Kevin Lund, insured with Pacific Shore. The plate is 7KX, like X-ray R 214. Can I ask about the deductible? He hit me so I should not have to pay that, right? And will my premium go up from this? Also, do I get the rental car today?

AGENTI’ll add that info to your claim now: - Other driver: Kevin Lund. - His insurer: Pacific Shore. - His license plate: 7KX R214. Let me quickly read that plate back: 7-K-X-R-2-1-4. Please correct me if any of that is off. From your policy, I can confirm: - Collision deductible: $500. - Rental: $40/day for up to 30 days, starting the day the claim is opened. - Towing: Up to 25 miles. On your questions: 1) “He hit me, so I shouldn’t have to pay the deductible, right?” Your policy has a $500 collision deductible. Whether you ultimately pay that out of pocket depends on how liability is worked out between Northgate and Pacific Shore: - If the claim is paid under your collision coverage, the deductible applies. - If Pacific Shore (the other driver’s insurer) accepts full responsibility and pays for the damage directly, your deductible may not apply. - If Northgate pays first under your collision and then recovers from Pacific Shore, your adjuster will review whether your $500 can be reimbursed after recovery. I can’t tell you for sure yet whether you’ll end up paying that $500; your adjuster, Priya Shah, will determine how it’s handled once liability is clearer. 2) “Will my premium go up from this?” I don’t have access to rating or pricing decisions, so I can’t say whether your premium will change. Premium changes depend on underwriting rules, fault decisions, and your overall policy history. Your adjuster can explain how this type of loss is considered, but they still can’t guarantee future premium amounts. 3) “Do I get the rental car today?” Your policy shows rental coverage of $40/day for up to 30 days, starting today (the day the claim is opened). How that works in practice: - You are eligible for rental coverage starting today. - The adjuster or the repair shop will usually help set up a direct-bill rental, or you can be reimbursed up to $40/day if you arrange your own (subject to that limit and normal claim handling). When Priya contacts you (within one business day), she’ll: - Confirm where your car is going for repairs. - Go over exactly how to pick up a rental and whether it will be direct-billed

AGENTor reimbursed. If you need a rental immediately today, you can: - Rent a car on your own and keep all receipts; reimbursement would be up to $40/day, subject to normal claim review, or. - Wait for Priya to coordinate a rental through a partner company. Before we wrap up, can you confirm the plate one more time: is it 7-K-X-R-2-1-4, or is there any letter/number different in there?

How these numbers are measured →