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 + v4 Turbo

Cascade

Rank on Roark score

#377of 655 stacks

47 / 100

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

Where it ranks

Roark score with price43 / 100579 of 655LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Coda71 / 100
Task completion87%579 of 656LeaderLinden-1 (own VAD) + GPT-6.1 Sol + TTS-1 HD99%
Tool use35%606 of 632LeaderUniversal-3.6 Pro + GPT-6.1 Sol + TTS-1 HD90%
Time to first word1.0 s358 of 656LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Flash v2.50.5 s
Response time2.8 s52 of 655LeaderGrok Voice 3.01.9 s
Barge-in handling100%237 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$1.17643 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
87%Completed

#585 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
4.2/ 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.

34 barge-ins
100%Handled correctly(34/34 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
4.64%avg

p50

1.39%

p95

19.2%

#608 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.

34 calls
0.82per 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
2.77%avg

p50

2.22%

p95

8.95%

#598 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
6.36%avg

p50

5.55%

p95

15.1%

#624 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
74.8%avg

p50

82.0%

p95

100%

#491 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
7.62%avg

p50

5.58%

p95

17.1%

#461 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

3

#433 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.

130 turns
2.95savg

p50

2.77s

p95

6.48s

#53 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
2.99savg

p50

1.02s

p95

15.8s

#361 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
3.25per callavg

p50

3.00 per call

p95

6.15 per call

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

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare88%3.17 s—
Home services87%2.74 s—
Insurance93%2.62 s—
Customer support80%2.62 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line91%3.15 s—
Spanish-accented English, city street87%3.22 s—
Indian English, busy café91%2.71 s—
Southern US, flustered, crying baby86%2.82 s—
Fast and interrupting, construction outside79%2.52 s100%

The calls behind the numbers

Customer support

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

CUSTOMERHi, Alex.

CUSTOMERI'm calling from a cafe. My home internet has been down for two hours now. There is a road crew digging up the street outside, so I'm wondering if that is the reason. I already rebooted the gateway twice and checked every cable.

CUSTOMERBut the internet light is blinking orange.

CUSTOMERCan you please check what is happening?

CUSTOMERMy account number is BW883.

CUSTOMER017.

CUSTOMERSorry.

CUSTOMERLast digit is one.

AGENTI’ve got you pulled up under account BW8830171, and there’s no area outage showing for your address, so it’s likely related to the work on your line or just your gateway. I just ran a line test and pushed a remote reset to your Brightwave BX7. It’s now showing as registered and online on my side. Here’s what to do next at home (or if someone’s there now, they can check):

1. Watch the lights on the gateway - The internet light should go from blinking orange to solid white/blue within about 2–3 minutes. 2. Test the connection - Try loading a couple of websites or running a speed test on a device connected to Wi‑Fi. 3. If you have any wired devices, have them test too (like a PC or streaming box plugged in via Ethernet). If, when you get home, you see

- Solid white/blue light but no internet on devices → tell me what devices you’re using and what error you see. - Still blinking orange after 5+ minutes → I’ll run another test and likely schedule a technician, since the line test says that’s the next step if the gateway won’t stay registered. Given the road crew digging, if the problem comes back or the light goes orange again later today, contact me and I’ll check the line again and set up a tech visit if needed.

CUSTOMEROkay.

CUSTOMERThanks for checking.

CUSTOMERThe internet light just went solid white now.

CUSTOMERHow long until my device is reconnect?

CUSTOMERAnd can you do the needful for a credit for the downtime? I lost two hours of work.

AGENTGood—that solid white light means the gateway is back online. 1) Time for devices to reconnect - Most Wi‑Fi devices will reconnect automatically within 1–3 minutes. - If something doesn’t come back on its own, just toggle Wi‑Fi off/on on that device or briefly disconnect/reconnect the Ethernet cable if it’s wired. 2) Credit for downtime I’ve applied a $10.00 service credit on account BW8830171 for about two hours of interruption. - It will appear on your next bill as a service credit. If you get home and see the light go back to blinking orange, let me know and I’ll recheck the line and arrange a technician if needed.

CUSTOMERI. Lost two hours of work.

CUSTOMERCan you make it more than that?

AGENTI understand—losing two hours of work is painful, not just an inconvenience. On my side, I’m limited to applying a standard short‑duration outage credit, which is what the $10.00 covers. I can’t increase that amount directly. What I can do for you now: - The $10.00 credit is already applied to account BW8830171 and will show on your next bill. - I’ve documented on your account that you experienced about two hours of downtime and that it impacted your work. That note is visible to our billing team if you choose to follow up. If you’d like to push for a larger adjustment, your best option is to contact Billing/Customer Care from home (or via the number on your bill) and reference today’s outage and the note on your account. They have more flexibility than I do in support. If the connection drops again today—especially with that road work going on—come back to me and I’ll re-test the line right away and set up a technician if

AGENTneeded.

CUSTOMEROkay.

CUSTOMERUnderstood.

CUSTOMERI will follow up with. The billing team if needed.

CUSTOMERThanks for your help. Alex.

CUSTOMERGoodbye.

AGENTYou’re welcome. I’m glad we got you back online. Quick recap before you go:

- Your gateway is online with a solid

AGENTwhite light. - A $10.00 credit has been applied to account BW8830171 and will appear on your next bill. If anything acts up again—especially after that road work—just reach out. Goodbye, and take care.

Healthcare

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

CUSTOMERHi. Oh, yes. Hello. I need to reschedule my dermatology appointment for next Wednesday morning. I just got a work shift then, so I can't make it. My name is Lucia Ramirez. Can you help me move it to a later time?

AGENTI can help with that. I’ll need a couple of details to look up your chart and appointment. 1) What is your full date of birth? 2) “Next Wednesday morning” could be two different dates depending on the calendar—can you confirm the exact date of the appointment you’re talking about? 3) When you say “a later time,” do you prefer later the same day (Wednesday afternoon/evening), or a different day altogether?

CUSTOMEROh, yeah. So my date of birth is March 17th, 1948. Sorry, no, 1980 four, March 17th. Mil, 1984. About the date. It's next Wednesday.

CUSTOMERSo I think that's June 12th. And I can only come after 3 p.m. if there's nothing on Wednesday after three.

CUSTOMERI'd need to move it to a different day.

AGENTThanks, Ms. Ramirez. I have you as:

- NameLucia Ramirez - Date of birth: March 17, 1984 - Current appointment: Dermatology with Dr. Okafor, next Wednesday at 9:15 a.m., Main Campus, Building B

You asked for after 3 p.m. and, if not available Wednesday, a different day. For Dr. Okafor starting from Wednesday, June 12, I’m seeing these open times

- Tuesday at 345 p.m. - Thursday at 4:10 p.m. - Also Tuesday 9:00 a.m. and Friday 11:30 a.m., which are before 3 p.m.)

There’s nothing after 3 p.m. on Wednesday for Dr. Okafor. Would you like to move your appointment to

1) Tuesday at 345 p.m., or 2) Thursday at 4:10 p.m.? And just to confirm, are we talking about Tuesday/Thursday of that same week as June 12?

CUSTOMERYeah. That's right.

CUSTOMERThe same week as June 12th.

AGENTGot

CUSTOMERBut Tuesdays don't actually work for me after all, because I pick up my daughter. What about Friday? Is there anything after 3 p.m.? If not, Thursday at 4:10 p.m. should be okay.

AGENTThanks for the update. For Dr. Okafor that week, I see on Friday only an 11:30 a.m. slot—nothing after 3 p.m. Since Fridays after 3 don’t work, I’ve gone ahead and moved your visit to:

- New appointmentDermatology with Dr. Okafor - Day: Thursday of that same week - Time: 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. Let me read that back once more to be sureYou, Lucia Ramirez, date of birth March 17, 1984, are now scheduled for Thursday at 4:10 p.m., dermatology with Dr. Okafor, confirmation code RVB-3M8P2. Does everything there look correct to you?

CUSTOMERYes, that's exactly right. Okay, just a couple quick questions.

CUSTOMERIs there any fee for changing the appointment?

AGENTThere’s no fee for this change. Our policy is: - Changes made more than 24 hours before the appointment are free. - Changes less than 24 hours before the appointment have a $40 fee. You rescheduled well in advance, so there’s no charge. What was your other question?

CUSTOMERThanks.

CUSTOMEROoh.

CUSTOMERShould I? Talk for the appointment?

AGENTI think I might have misheard—are you asking if you should fast before the appointment, or if you should talk to someone (like your doctor) before it? For a standard dermatology visit with Dr. Okafor (skin check, rash, moles, acne, etc. ): - You do not need to fast. - You can eat and drink normally. - Take your regular medications unless another doctor has told you otherwise. - It helps to come with: - A list of your medications and allergies - A note of any new or changing spots, rashes, or moles - Photos on your phone if the rash or issue comes and goes

If you meant something else—like “Should I talk to the doctor about ?”—tell me what you’re worried about and I’ll let you know if that’s something dermatology can address.

CUSTOMEROh, no, sorry, I.

CUSTOMERWas asking. About parking. Not passing. Where can I park when I come for my appointment?

AGENTThanks for clarifying—that makes much more sense. For your dermatology visit at Main Campus, Building B:

- ParkingFree patient parking in Lot C - Entrance: Off River Road - Just tell the attendant or look for signs for “Patient Parking – Lot C.”

If you’d like, I can also tell you what time the clinic opens on Thursdays so you know how early you can arrive.

CUSTOMERAha. That's helpful. Thank you. One last thing. Does Doctor Okafor accept Aetna insurance?

AGENTI don’t have access to the insurance panel by provider, so I can’t safely confirm whether Dr. Okafor specifically accepts Aetna. To get an accurate answer, you have two good options:

1. Call the front desk/billing at Riverbend Health Clinic and ask- Can you confirm if Dr. Okafor is in‑network with Aetna for dermatology?” They can look it up by your exact Aetna plan. 2. Check with Aetna: - Log in to your Aetna member portal or app. - Search for “Riverbend Health Clinic” or “Dr. Okafor, dermatology” and confirm they’re in‑network for your specific plan. I recommend doing both if you can: confirm with Aetna and then double‑check with the clinic so there are no surprise bills. If you tell me the phone number or portal you usually use, I can outline exactly what to say or click through step by step.

CUSTOMEROh that's okay. I'll call the front desk myself. And check with Aetna. Thanks for your help today. Goodbye.

AGENTYou’re all set, Ms. Ramirez. To recap: you’re scheduled with Dr. Okafor on Thursday at

AGENT4:10 p.m., Main Campus Building B, confirmation code RVB-3M8P2, and you can park for free in Lot C off River Road. Thanks for calling Riverbend Health Clinic, and take care.

Home services

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

CUSTOMERHi.

CUSTOMERSorry. I just need to get this handled fast.

CUSTOMERThere's a pipe under my kitchen sink that's burst water spreading across the floor toward a power strip. I haven't shut the water off yet.

CUSTOMERWhat should I do? And can you send someone out?

AGENTFirst, let’s get you safe and stop the damage:

1. Stay

CUSTOMERYeah.

AGENTThanks for hanging in

CUSTOMERYep.

AGENTUnderstood. Let’s move fast. First, safety and stopping the water:

1. Stay away from that power strip and any outlets the water might reach. - Don’t touch the strip, any plugs, or anything electrical on that wall. 2.

CUSTOMERGot it.

AGENTThanks. Let’s keep this quick and focused. First, we need two things right now: water off and power safe. 1) Shut off the water - Look under the sink for two small shutoff valves (one for hot, one for cold) on the pipes. • Turn both knobs clockwise (right) until they stop. - If you can’t find those or they won’t turn, go to your main water shutoff: • Often in the basement, garage, utility room, or outside near the street in a box in the ground. • Turn the main valve clockwise until it stops. Tell me: - Were you able to shut off under-sink valves, or are you going to the main? 2) Make the area electrically safe - If water is already close to or touching that power strip, do not go near it. - If you can safely reach your breaker panel without crossing

CUSTOMERYeah.

AGENTThanks for staying on the line—let’s move step by step. First, I need to confirm two safety things:

1. Water main / under-sink valve

- Have you shut off the water yet—either

CUSTOMERGot it.

CUSTOMERYeah. I'm doing that now. Okay.

CUSTOMERIt's shut off.

CUSTOMERWater stopped.

AGENTGood—shutting the water off was the big one. Next safety step: If the water got close to or under that power strip, don’t touch the strip or anything plugged into

CUSTOMERRight.

AGENTUnderstood. We

CUSTOMERUnderstood.

CUSTOMERRight. I'm staying clear of

AGENTPerfect,

CUSTOMERit. Let's get someone. Out here.

CUSTOMERWhat's

AGENTGood call staying clear of it. We can get an emergency plumber out today between 2:00 PM and 4:00 PM. - Emergency call-out fee: $149 - If you’re a Copperline Care member, it would be $99 instead. - Payment: Card or check on

CUSTOMERthe. Okay.

CUSTOMEROkay. How much exactly will it be if. I'm not a member?

CUSTOMERCan anyone come before two? I need the earliest window possible.

AGENTI’ve got you—let’s move quickly. 1) Price If you’re not a Copperline Care member, the emergency

CUSTOMERRight. So just to confirm, if I'm not a member, it's $149. Is there any way someone can come before 2 p.m.?

CUSTOMERYou need this handled as soon as possible.

CUSTOMERYeah, I'm not a member.

CUSTOMERI just need the fastest slot. Can anyone get here before two?

CUSTOMERWho's coming? How will I know when they're on their way?

AGENTYou’re correct: if you’re not a Copperline Care member, the emergency call‑out fee is $149, payable by card or check when the work is done. Right now, the earliest emergency arrival window I can see is today between 2:00

CUSTOMERYeah.

AGENTYou’ve got

CUSTOMERIs that.

CUSTOMEROnly the earliest possible.

CUSTOMERSlot. Can anyone come before 2 p.m.? If not, I'll take the 2 to 4 window.

CUSTOMERWho's coming? And how will I know when they're on the way?

AGENTYou’re all set, and you’ve got the earliest possible slot. 1) Timing and price - The earliest emergency window available today is 2:00 PM to 4:00 PM, and I’ve booked that for you. There is nothing sooner showing in our system. - You mentioned you’re not a member, but our

CUSTOMERAll right. Just give

AGENTGot it, I’ll keep

CUSTOMERme that. 2 to 4 p.m. window. Who's

CUSTOMERcoming? Got it.

AGENTI’ve got you in for the earliest possible slot. Here’s what’s set up:

- Arrival windowToday, 2:00 PM to 4:00 PM (earliest emergency slot available; nothing sooner is open in the system). - Fee: You’re actually listed as a Copperline Care member, so the emergency call‑out is $99, payable by card or check on completion. Before I finalize, I need to confirm a couple of details from what I see on file:

- Service address1480 Larkspur Avenue, Unit 4B - Is that the correct address and unit for this kitchen sink? - And what’s the best callback number for you for today, for updates and the “on the way” text? On “who’s

CUSTOMEROkay.

AGENTYou’re booked for the earliest

CUSTOMERIt's

CUSTOMERfour. Actually, I moved to.

AGENTGot it, I’ve already locked in that 2:00 PM–4:00 PM emergency window for you. Here’s what’s set so far:

- Arrival windowToday,

CUSTOMERUnit four D last month.

CUSTOMERIt's not four B. My callback number is (503) 555-0139.

CUSTOMERNo, 0193.

CUSTOMERJust to clarify.

AGENTThanks for

CUSTOMERClarify. It's unit four D, not four

CUSTOMERB. And my callback number.

CUSTOMERIs five. Right, so who's

AGENTThank

AGENTGot

CUSTOMERcoming in? And.

AGENTGot it, thank you for clarifying—that’s important. Here’s what I have locked in for

CUSTOMEROkay. All right. What's the ticket number. For this visit?

CUSTOMERCan you tell me who's coming and how I'll know when. They're on

AGENTHere’s everything confirmed:

1) Booking details - Service address1480 Larkspur Avenue, Unit 4D - Callback number: (503) 555-0193 - Arrival window: Today, 2:00 PM to 4:00 PM (earliest available emergency slot) - Ticket number: CPL-58210 2) Who’s coming / how you’ll know - A Copperline plumber will be dispatched on that ticket. - You’ll get a text to (503)

CUSTOMERthe way? Yeah.

CUSTOMERYeah.

CUSTOMERAll right, so I'll get a text to (503) 555-0193 when they're on their way. Got

CUSTOMERit. Thanks for the

CUSTOMERinfo. Goodbye.

AGENTExactly

AGENTCorrect—you’ll get a text to (503) 555-0193 about 30 minutes before the plumber arrives. Here’s your visit info,

AGENTall together:

- Service address1480 Larkspur Avenue, Unit 4D - Arrival window: Today, 2:00 PM–4:00 PM - Ticket number: CPL-58210 Stay clear of that power strip and any wet outlets until we’ve been out there. If anything changes or the water starts again, call us right away and mention ticket CPL-58210.

Insurance

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

CUSTOMERRight.

AGENTIs anyone injured, or is anyone in any danger right now? If anyone is hurt or might be hurt, please hang up and call 911 first, then you can call us back.

CUSTOMERNo. Nobody's hurt.

CUSTOMERWe're both fine.

CUSTOMERJust need help with the claim. All right.

CUSTOMERThe rear bumper is crushed and the wheel rubs, so I can't drive it.

CUSTOMERCan we move ahead quickly?

AGENTWe can move ahead now. Since the wheel is rubbing, don’t

CUSTOMEROkay.

AGENTThanks. Let’s get

CUSTOMERYeah.

AGENTFirst I’ll

CUSTOMERRight. Let's just get started.

AGENTUnderstood,

CUSTOMEROkay.

AGENTWe’ll get this started now. First, I need to verify your policy.

CUSTOMERRight.

AGENTWe’ll get this started now. First, I need to find your policy. 1) What’s your auto policy number? 2) And the policyholder’s last name? Also, since you mentioned the wheel is rubbing: where is the car right now (street address or nearest intersection and city)? Once we have your policy pulled up, I can also arrange a tow if needed.

CUSTOMERYep. Let's move.

CUSTOMERFast. Policy number is NG4471903. Wait, sorry, last one is two.

CUSTOMERLast name is Brooks.

CUSTOMERThe car is at SW fifth Avenue and Alder Street in Portland.

CUSTOMERI do need a tow, so please arrange that.

AGENTThanks, I’ve got what I need to get moving. Let me read back what I have so far:

- Policy numberNG4471902 - Policyholder last name:

CUSTOMERYeah. That's fine.

CUSTOMERCan you tell me how much I have to pay?

CUSTOMERDo I get a rental car?

AGENTHere’s what your policy shows:

- Your policy numberNG4471902 - Collision deductible: $500

CUSTOMERRight. Got

AGENTYou’ll be responsible

CUSTOMERit. Is there. A deductible? Since he

CUSTOMERhit. But

AGENTYes, there is a deductible on your policy. From your coverage, you have:

- Collision deductible$500

How it

CUSTOMERhe. Hit me!

AGENTYou do have a deductible on the policy, but whether you actually end up paying it depends on who’s found at fault and how the claim is handled. From your coverage:

- Collision deductible$500

How that usually works

- If we pay for your car under your collision coverage, we apply your $500 deductible. That

CUSTOMERRight.

AGENTYou’re covered, and I understand he hit you. I’ll explain how that usually

CUSTOMEROkay.

AGENTSince he hit

CUSTOMERYeah, I know.

AGENTYou’re all set on

CUSTOMERYeah.

AGENTI hear you — he hit you. Whether you actually pay that

CUSTOMERYeah.

AGENTSince

CUSTOMERGot.

CUSTOMERIt. So, what. About a rental car? Is my. Premium going to go up because of

AGENTOn your policy:

- Collision deductible$500 - Rental coverage: $40 per day, up to 30 days, starting from the day the claim is opened So yes, you do have rental coverage. Once I open the claim, we can set you up with a rental through one of our partners, or you can rent on your own and get

CUSTOMERthis? Got it.

CUSTOMERYeah.

AGENTYou do have rental

CUSTOMERAll right.

AGENTYou do have

CUSTOMERGot it.

AGENTrental

AGENTYou do

CUSTOMERYeah. Got it.

CUSTOMERAll right. Just need to

AGENTGood—that’s all

CUSTOMERknow. Where the car will be. Taken after it's towed. Can

CUSTOMERyou. Perfect. That's fine. Can you give me the claim number, please?

AGENTset

AGENTYour tow is already set up. Here’s what I have on it:

- Tow companyEastside Towing - ETA: About 45 minutes - Destination: A Northgate partner repair shop at 9th and Morrison in Portland That’s where your car will be taken after it’s towed.

CUSTOMERHello?

AGENTThanks for waiting, and sorry for the silence there. I’ve opened your claim. Here are the key details:

- Policy numberNG4471902 - Claim number: NGM-904417

CUSTOMEROkay.

CUSTOMERYeah. That's right.

CUSTOMERWhat's the claim number?

AGENTYour claim number is NGM-904417.

How these numbers are measured →