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 + GPT-5.1 + Turbo v2.5

Cascade

Rank on Roark score

#275of 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 price45 / 100544 of 655LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Coda71 / 100
Task completion91%397 of 656LeaderLinden-1 (own VAD) + GPT-6.1 Sol + TTS-1 HD99%
Tool usen/aLeaderUniversal-3.6 Pro + GPT-6.1 Sol + TTS-1 HD90%
Time to first word1.0 s353 of 656LeaderUniversal-3.5 Pro + GPT-6.1 Sol + Flash v2.50.5 s
Response time3.7 s346 of 655LeaderGrok Voice 3.01.9 s
Barge-in handling100%209 of 342LeaderWhisper-1 + GPT-6.1 Sol + v4 Turbo100%
Turn budget3.7 s312 of 596LeaderLinden-1 (own VAD) + GPT-4o mini + Flash v2.52.1 s
Cost per task$1.13638 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
91%Completed

#402 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
4.0/ 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.

16 barge-ins
100%Handled correctly(16/16 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
1.19%avg

p50

0.00%

p95

5.13%

#1 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.

27 calls
0.59per callavg

p50

1.00 per call

p95

1.00 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
1.46%avg

p50

0.68%

p95

4.64%

#465 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
2.73%avg

p50

1.95%

p95

6.61%

#293 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
78.5%avg

p50

83.8%

p95

100%

#425 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
6.58%avg

p50

3.28%

p95

15.7%

#387 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
3.3/ 5avg

med

3

#571 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.

151 turns
3.86savg

p50

3.75s

p95

6.23s

#348 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
2.15savg

p50

1.02s

p95

11.4s

#356 of 662 on the board · best 0.45 s

Latency spikes

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

20 calls
6.30per callavg

p50

6.00 per call

p95

11.1 per call

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

By industry

IndustryTask completionLatency P50Barge-in handling
Healthcare91%4.02 s—
Home services79%4.01 s—
Insurance100%3.39 s—
Customer support93%3.42 s—

By caller

CallerTask completionLatency P50Barge-in handling
US English, quiet line94%4.14 s—
Spanish-accented English, city street83%3.49 s—
Indian English, busy café95%3.38 s—
Southern US, flustered, crying baby98%4.13 s—
Fast and interrupting, construction outside82%3.73 s100%

The calls behind the numbers

Customer support

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

CUSTOMERHi, Alex. My internet has been down for about two hours now. I work from home, so. It's a bit urgent. There's a road crew digging up the street outside, and since then the connection dropped. I already rebooted the gateway twice and checked every cable. The internet light is blinking orange. Can you check if the road work is causing this? My account number is BW883017. Sorry, last digit is one.

AGENTI’ve got your

CUSTOMERHello?

CUSTOMERAha. Go ahead.

AGENTThanks for hanging on, and thanks for the correction earlier—your account number is BW8830171. Here’s what I see on my side:

- No area outage at your address, so it’s not a known neighborhood-wide issue. - I ran a line test to your Brightwave BX7 gateway. The signal to your home looks good, but the gateway had fallen out of registration.

CUSTOMERAll right. So it's not the road crew then. The gateway light is still blinking orange. Like I said, I already rebooted it twice and checked all the cables. What should I do next?

AGENTI pushed a remote reset

CUSTOMEROkay, let me check the gateway now.

AGENTSounds good—I’ll stay with you. The reset I sent shows your gateway as “registered and online” on my side now, but your lights may take up to about 2 minutes to settle and your devices may need another minute to reconnect. While you’re checking:

- The internet light should go to solid (not blinking orange). - On a computer/phone, try loading a website or a speed test once the light is solid. Tell me

1) Has the internet light changed from blinking orange yet? 2) Can any device actually get online now?

CUSTOMERYes, the internet light just went solid white. How long until my devices will reconnect? Should I try now or wait a bit longer?

AGENTGood—that solid white light means the connection is back. You can start trying devices now:

1. On one device (laptop or phone), turn Wi‑Fi off and back

CUSTOMERAll right, I can do that. But before I try, can I also get a credit for the downtime? I lost two hours of work due to this outage.

AGENTYes, I can do that. I’ve applied a $10.00 service credit on your account BW8830171 for about two hours of downtime. It will show on your next bill as a service interruption credit. You’re fine to start reconnecting devices now:

- Toggle Wi‑Fi off/on on a laptop or phone, reconnect to your Brightwave network, and try a couple of sites. If anything still doesn’t come up or is very slow, tell me what device and whether it’s on Wi‑Fi or ethernet, and we’ll tune it from there.

CUSTOMERGot it. But I lost two hours of work. Can you make the credit? More than that.

AGENTI understand why you’re asking, especially if you were in the middle of work. I do have to stay within what I’m allowed to grant directly, and $10 is the maximum credit I can apply for a short interruption like this (about two hours) when it’s resolved remotely without an outage or repair visit. What I’ve already added:

- AccountBW8830171 - Credit: $10.00 - When you’ll see it: On your next bill, as a service interruption credit If you’d like to pursue a larger adjustment, the next step is to contact our billing team directly (they can review longer history, prior issues, etc.). I can’t override their limits from here, but you can ask them to review the impact on your work and see if anything more is possible. In the meantime, let’s make sure your connection is fully stable so this doesn’t keep interrupting your day. Are your devices all back online and working normally now?

CUSTOMERYes. Everything is back online now. Thank you for your help with this, Alex. Goodbye.

AGENTYou’re welcome—I’m

AGENTglad everything’s back up and running. Quick recap before you go: - Account: BW8830171 - Credit applied: $10.00 service interruption credit (will appear on your next bill)

If this happens again or you notice anything unstable, contact us right away. Take care, and have a good rest of your day.

Healthcare

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

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

AGENTI can help with that. To look up your appointment, I need to verify your account. Please provide:

- Your full name as listed with the clinic (first, middle if any, and last), and - Your date of birth (YYYY-MM-DD).

CUSTOMERJordan. Ellis. Sorry, I don't have a middle name. March 17th, 1948. Sorry. No. 1984. March 17th, 1984.

AGENTI’ve found your appointment—Jordan Ellis, date of birth 1984-03-17—with dermatology (Dr. Okafor) next Wednesday at 09:15, Main Campus, Building B. You mentioned you can only come after 3 p.m. and want to move that appointment. With Dr. Okafor, the next available late-day options I see are:

- Tuesday at 1545 - Thursday at 16:10 Friday’s opening is at 11:30, which is before 3 p.m., so that doesn’t meet your constraint. Which of these would you like me to move your appointment to: Tuesday at 15:45 or Thursday at 16:10?

CUSTOMERTuesdays don't work, after all. Since I pick up my daughter. What about Friday? Is there anything after 3 p.m.? If not, I'll take Thursday at 4:10 p.m..

AGENTThere’s nothing with Dr. Okafor after 3 p.m. on Friday—only an 11:30 a.m. slot—so I’ve gone ahead and moved you to Thursday at 4:10 p.m. like you requested. Here are your updated details:

- NameJordan Ellis - Date of birth: 1984-03-17 - Provider: Dr. Okafor (Dermatology) - New day and time: Thursday at 16:10 (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. Would you like me to send these details to you by email or text as well?

CUSTOMERNo need to send it by email or text. Thanks. Is there a fee for changing the appointment? And where should I park from? Main campus building B. Also, does Doctor Okafor accept Aetna insurance?

AGENTHere’s the info you asked about:

1) Fee for changing the appointment Clinic policy is- Changes made more than 24 hours before the appointment are free. - Changes less than 24 hours before carry a $40 fee. Your move to Thursday at 4:10 p.m. was done ahead of time, so there is no change fee. 2) Parking for Main Campus, Building B - Patient parking is free. - Use Lot C, with the entrance on River Road. From Lot C, follow the signs for Building B; the main entrance is clearly marked once you’re near the building. 3) Aetna insurance I don’t have access

CUSTOMEROkay.

CUSTOMERGot it. So Doctor Okafor does not accept Aetna insurance. Is there another provider in dermatology at Riverbend who does.

AGENTI didn’t say that Dr. Okafor does not accept Aetna—only that I don’t have access to our insurance-network details in this system, so I can’t confirm either way here. To find a dermatologist at Riverbend who’s in-network with Aetna (including whether Dr. Okafor is covered), you have two good options:

1) Call our front desk / billing - Ask them to check dermatology providers who are in-network with Aetna under your specific plan. - They can confirm Dr. Okafor’s status and/or suggest another dermatologist in-network and help move your appointment if needed. 2) Check Aetna’s provider directory - Go to Aetna’s member website or app. - Search for “Riverbend Health Clinic” and filter by specialty “Dermatology.” - That list will show which Riverbend dermatologists are in-network for your exact plan. If you’d like, once you know which in-network dermatologist you prefer, I can help you reschedule your appointment to that provider’s next available time that works after 3 p.m.

CUSTOMERAha. That makes sense. I'll check with Billing or Aetna directly then call back if I need to change my provider. Thanks for all the info and for moving my appointment. Goodbye.

Home services

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

CUSTOMERHey, I'm sorry. I'm kind of frazzled right now. I've got a pipe under my kitchen sink that just burst, and there's water spreading all over the floor. It's heading toward a power strip, and my baby's crying in the other room, so I really need help. Fast. What should I do first? Can y'all send someone out right away?

AGENTThanks for hanging in there; let’s get you safe first. 1. Stay safe around electricity - Do not touch the power strip or any plugs if water is near or on them. - If you can safely reach your main electrical panel without walking through water, flip off the breaker that controls the kitchen outlets. If you’re unsure which one that is and it’s safe to do so, you can switch off the main breaker. - If you’d have to step in water to reach the panel, don’t do it. Just keep everyone away from that area. 2. Shut off the water - Look under the kitchen sink for two small shutoff valves (usually on the pipes going to the faucet). Turn both of them clockwise until they stop. - If those valves are stuck or you can’t find them, do you know where your main water shutoff is? Common spots:

- In a basement or utility room along an outside wall - In a closet near the front of the house - In a box at the curb (for some homes)

- If you know where it is and can get to it safely, turn the main valve clockwise to shut off all water to the house. 3. Keep your baby safe - If you haven’t already, move your baby to a dry room away from the kitchen and any cords or outlets. You can leave towels on the floor by the kitchen to slow the spread, but only if you’re not near that power strip. While you’re doing that, I’ll get someone out as an emergency. I need a couple of quick answers so I can set this up

1. Is any water actually touching the power strip yet, or is it just getting close? 2. Have you been able to turn off either the under-sink valves or the main water yet? 3. What’s the address where this is happening? 4. What’s the best callback number for you? Once I have your address and phone, I’ll check our earliest emergency arrival window and the fee, read it back to you, and then get a plumber dispatched right away.

CUSTOMERYeah. I appreciate you walking me through all that. The water's not quite touching the power strip yet, but it's getting real close. I just turned both those under sink valves off, and the water's stopped now. Sorry. I know I'm talking fast. My address is 1480 Larkspur Avenue, and I'm in unit 4D, not four B. We just moved last month. My phone number is (503) 555-0139. No, sorry, 0193. Is that okay? Can you double check you got that right?

AGENTI’ve got you, and you’re doing the right things. First, to answer your question: I have your number as (503) 555-0193 — ending in 0193, not 0139. And your address as 1480 Larkspur Avenue, Unit 4D. That matches what you just told me. Since the water is stopped and hasn’t reached the power strip yet, keep everyone (and pets) out of the kitchen area, and don’t use that power strip. If you can safely unplug it from a dry spot, you can,

CUSTOMERI. Thank you. That helps a lot. I just really needed to hear that. I'll keep everybody clear, and I won't touch that strip unless it's totally dry. Is it alright if I ask how much is this emergency visit going to cost? And can anyone get here before 2 p.m.? I just want to make sure we get help as soon as possible.

AGENTI’ve already got you on the schedule as an emergency, and here’s what I can see on my end:

- Soonest available arrival windowtoday, 2:00 PM to 4:00 PM There’s nothing earlier showing in our system, so I can’t move you sooner than 2 PM, but you are in the earliest emergency slot we have today. - Emergency visit cost for you: you’re listed as a Copperline Care member, so the emergency callout fee is $99. That covers getting the plumber out there and diagnosis; any

CUSTOMERHorny. I really appreciate you checking $99. Right? That's okay, as long as I know up front. So, uh, who's coming out? Do y'all know which plumbers are signed? And how will I know when they're on their way? I. Just need to be sure I'll recognize them when they get here. And could you give me the ticket number for this? So I've got it handy.

AGENTYes, the emergency callout for you is $99 as a Copperline Care member. Here’s what I can tell you about the visit:

- Arrival windowToday between 2:00 PM and 4:00 PM - Ticket number: CPL-58210 - Service address on the ticket: 1480 Larkspur Avenue, Unit 4D - Callback number on the ticket: (503) 555-0193

For who’s coming and how you’ll recognize them

- Our system doesn’t show me personal

CUSTOMERI. Okay, that's. All right. I just wanted to double check. As long as you've got the ticket set up and everything matches. I feel a bit better. Uh, so the ticket number is CPL58210, right? Is there anything else I need to do before they get here? Thank you again. I really appreciate all your help. Goodbye.

AGENTYes, you’ve got it exactly right: your ticket number is CPL-58210. Before the plumber gets there, here’s all you really need to do:

1. Keep the area safe - Keep your baby and anyone else out of the kitchen. - Don’t use that power strip; don’t touch it if there’s any chance it’s damp. 2. Contain the water if you can do it safely - Lay down towels around the edges of the water to keep it from spreading further. - If you have a bucket or bowl, you can set it under the pipe area in case anything starts dripping again. 3. Have a quick path cleared - If possible, clear out the area under the sink and a small path so the plumber can get right to the cabinet when they arrive. Just to read everything back one last time so you know it’s all correct

- Service address1480 Larkspur Avenue, Unit 4D - Ticket number: CPL-58210 - Arrival window: Today, 2:00 PM to 4:00 PM - Callback number: (503) 555-0193 Emergency callout fee: $99 (Copperline Care member rate)

You’ve already done the most important part by stopping the water and keeping everyone safe. If anything changes before we arrive—like the water starts again or it does reach that power strip—step away from the area and call us back

CUSTOMEROkay. Thank you. That really helps. I'll keep an eye out and do exactly what you said. I'm sorry for all the questions. I just get nervous when stuff like this happens. I appreciate your patience. Goodbye.

Insurance

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

CUSTOMERYes, I'm in a cafe right now. I am safe. Nobody is hurt. I just need help with my car. Please.

AGENTI’m glad you’re safe and that no one is hurt. I’ll help you with your car and get a claim started. First, I need to pull up your policy. - What’s your auto policy number? - And the policyholder’s last name?

CUSTOMERSure. The policy number is NG4471903. No, sorry, last one is two. The last name is Mehta.

AGENTThank you, Ms. Mehta. I’ve found your policy ending in 1902 for the 2021 Honda CR‑V. Let’s get the details of what happened so I can open your claim and help with the car:

1. When did the accident happen? 2. Where did it happen? 3.

CUSTOMERYeah. That's right. The accident happened about 20 minutes ago. I was stopped at a red light at SW fifth Avenue and Alder Street.

AGENTThanks, I’ve got that: about 20 minutes ago at SW Fifth Avenue and Alder

CUSTOMERJust to clarify, it was S. S Fifth Avenue and Alder Street, not SW. Is that okay?

AGENTThanks for clarifying—that’s helpful. I’ll note it as:

- LocationS Fifth Avenue and Alder Street - Time: About 20 minutes ago

I still need a few details to open the claim

1. Can you tell me what happened, in your own words? 2. Do you have the other driver’s name, their insurance company, and their license plate? 3. Did the police come to the scene, and if so, is there a report number? 4. Is your Honda CR‑V drivable, or does it feel unsafe to drive?

CUSTOMERSure. So I was stopped at a red light. Another car hit the back of my Honda CRV. The back bumper is crushed and the rear wheel is rubbing. I cannot drive it. The other driver is Kevin Lund, insured with Pacific Shore. His license plate is 7KX, like X-ray R 214. Police did not come, so there is no report number and my car is not drivable. It feels unsafe to drive.

AGENTI’ve got everything I need, and I’m going to walk you through what’s happening now. First, let me read key details back to you:

- Policy numberNG4471902 - Other driver’s license plate: 7KXR214 - Location: S Fifth Avenue and Alder Street - No injuries, no police at the scene, rear-end impact, your Honda CR‑V not drivable. If anything there isn’t right, tell me and I’ll fix it. Now what I’ve done for you:

1. Your claim is open - Claim numberNGM-904417 - Assigned adjuster: Priya Shah She will contact you within one business day. 2. Tow truck is on the way - Tow company: Eastside Towing - ETA: about 45 minutes to S Fifth Avenue and Alder Street - They’re

CUSTOMEROkay, that is correct. Just a small correction. The other driver's plate is 7KX, like X-ray r 214, not 2114. Rest is all right. So can you tell me how much do I have to pay? Will I get a rental car? And is my premium going to go up? Also, where will the car be taken? And I got the claim number NGM904417.

AGENTThanks, I’ve updated that plate number. - Other driver’s license plate: 7KXR214 - Your claim number: NGM-904417

CUSTOMERYeah that's right. And about my questions, will I have to pay anything out of pocket? Do I get a rental car? Is my premium going to increase and where will the car be taken?

AGENTI’ll go through each of those for you, based only on what I can see on your policy. First, confirming details I have correct now: - Policy number: NG4471902 - Other driver’s license plate: 7KXR214 - Claim number: NGM-904417 1) What you may have to pay out of pocket From your coverage: - Collision deductible: $500 Because this is damage to your own vehicle, if your collision coverage is used, you would be responsible for the first $500 of covered repairs. - If Pacific Shore (the other driver’s insurer) accepts full liability and pays for your damage directly, you may not end up paying that deductible. - If we handle it under your collision coverage first,

CUSTOMERBut he hit me. So I should not have to pay that. Right?

AGENTFrom what you’ve told me, you were stopped and were hit from behind, so it sounds like the other driver is at fault. But I can’t decide fault or guarantee who pays—that’s something your adjuster and the other insurance company will determine. Here’s how it usually works in a rear‑end situation:

1. If the other insurer accepts full fault - Their company (Pacific Shore) would typically pay for your repairs and you would not owe your $500 collision deductible to us. - Sometimes they may also handle your rental directly. 2. If we fix your car first under your collision coverage - You have a $500 collision deductible on your policy. - You’d be responsible for that amount up front on covered repairs. - If we later recover the money from Pacific Shore, we may be able to get your deductible reimbursed, depending on the outcome. Your adjuster, Priya Shah, will- Contact Pacific Shore and investigate fault, - Explain whether your claim will go through your collision coverage or directly through the other driver’s insurance, and - Tell you clearly if and when your deductible applies. On your other questions:

- Rental carYour policy includes rental reimbursement of $40 per day for up to 30 days, starting from when the claim is opened, if the loss is covered. The adjuster will help you set that up and explain how to book it. - Tow / where the car is going: The tow I arranged is set to take your Honda CR‑V to a Northgate partner repair shop at 9th and Morrison. If you prefer a different shop, tell the adjuster and they can help redirect or coordinate. - Premium increase: I don’t have access to rating or pricing, so I can’t say if your premium will go up. That depends on the final fault decision, state rules, and your overall record. Your adjuster or your agent can discuss that once the investigation is further along. Next step: once Priya reaches you, tell her clearly that you were stopped at the light and were rear‑ended, and that there were no injuries. She’ll walk you through the fault decision, deductible, rental setup, and repairs.

CUSTOMEROkay, understood. So I will wait for Priyesh Shah to contact me. I got the claim number NGM904417. Thank you for your help. Goodbye.

AGENTYou’re very

AGENTwelcome, and just to confirm before you go:

- Claim numberNGM-904417 - Adjuster: Priya Shah (she’ll contact you within one business day) - Policy number: NG4471902 - Other driver’s plate: 7KXR214 The tow is already arranged to the partner shop at 9th and Morrison. Take care, and call us back if you need anything else. Goodbye.

How these numbers are measured →