Build voice agents you can trust. Roark tracks call metrics, runs evaluations, and stress-tests your agent with simulated callers across accents, languages, and speaking styles. Failed calls become tests - giving you visibility and continuous improvement.
When we first built voice agents, we ran into the same problems every team faces:
Testing was manual - we literally called agents over and over just to check if they followed instructions.
Monitoring was missing - we didn’t know when failures happened, and even when they did, we had no idea which levers to pull to make the agent better.
Fixes didn’t stick - regressions kept popping back up without us noticing.
So we built Roark - a platform that brings reliability and visibility to Voice AI.
Here’s what Roark does today:
🔹 Monitoring & Evaluation
Capture 40+ built-in call metrics and events (latency, instruction-following, repetition detections, sentiment, etc.) - plus define your own custom ones.
Support for calls with up to 15 speakers, with automatic speaker identification.
Analyze audio with models for emotion, vocal cues, and even fine-tuned transcriptions based on your use case.
Build dashboards, schedule reports, set up alerts, and trigger webhooks so your team is always in the loop.
Evaluate calls with best-in-class evaluators you can run on demand or automate via SDK/API.
🔹 Simulations & Personas
Run end-to-end simulations for both inbound and outbound agents, over the phone or WebSocket - so you’re testing the same paths real customers take.
Define tests as conversations - a sequence of turns between customer and agent, using a graph-based approach. This makes it easy to branch into edge cases or test variants, so your coverage reflects real-world complexity, not just happy paths.
Configure personas by gender, language, accent, background noise, and speech profile (pace, clarity, disfluencies).
Layer on behavior profiles like base emotion, intent clarity, confirmation style, memory reliability - even a backstory.
Stress-test across real-world variables and automatically generate test cases from live calls (failed calls → repeatable tests).
🔹 Developer-first Integrations
First-class SDKs in Node & Python + REST API.
Native support for LiveKit, Pipecat, VAPI, Retell, and Voiceflow.
Easiest integrations on the market - nothing bolted together overnight.
👉 In the past 6 months, Roark has already processed over 10M minutes of calls for companies like Radiant Graph, Podium, Aircall and BrainCX - helping them evaluate agents and run simulations at scale.
The result? A full lifecycle platform that closes the loop: monitor your live calls → spot failures → turn them into tests → improve continuously.
Think of Roark as the QA + Observability layer for Voice AI - robust, deeply thought-out, and built to last.
Love that Roark auto-generates repeatable tests from failed calls — would've stopped so many regressions in our voice agents. Amazing work @zammitjames & @danielgauci
Roark helps you build voice agents that actually earn trust. It tracks call metrics, runs smart evaluations, and stress-tests across accents, languages, and speaking styles. Every failed call becomes a test, so your agent gets sharper with every interaction.
Finally, a way to build AI voice agents that don't just work, but work well. Roark provides the crucial trust and visibility needed to deploy with confidence.
One of Origami's fastest growing customers for a reason - hearing really good things on the utility of your product from your customers.
Congrats on the launch!
It’s great to see a product dedicated to testing voice agents, it’s definitely a much needed tool as voice agents become increasingly popular across industries. I already know a couple of people working with voice agents and will be sure to let them know about this product!
Roark is absolutely an awesome product - voice is really hard to build, and roark gave us the info we needed for rapid iteration. The team was extremely helpful even outside of voice, they really care!
Congratulations on the launch @zammitjames and @danielgauci ! Roark is truly a game-changing product for teams working in Voice AI! Truly excited to see how to product continues to evolve. Go Go Go!
this is really cool James! how do you guys tackle improving the voice agents?
We had such a good experience with Roark at LumaLink. James and David worked so closely with us that it felt like an extension of our own team. The product is rock solid, but honestly, the partnership was just as valuable — we even ended up being their customer reference for investors.
Can I use this to practice calling humans? I would rather drink bleach than make a phone call.
👋 Hey Product Hunt!
We’re @zammitjames & @danielgauci, co-founders of Roark (YC W25).
When we first built voice agents, we ran into the same problems every team faces:
Testing was manual - we literally called agents over and over just to check if they followed instructions.
Monitoring was missing - we didn’t know when failures happened, and even when they did, we had no idea which levers to pull to make the agent better.
Fixes didn’t stick - regressions kept popping back up without us noticing.
So we built Roark - a platform that brings reliability and visibility to Voice AI.
Here’s what Roark does today:
🔹 Monitoring & Evaluation
Capture 40+ built-in call metrics and events (latency, instruction-following, repetition detections, sentiment, etc.) - plus define your own custom ones.
Support for calls with up to 15 speakers, with automatic speaker identification.
Analyze audio with models for emotion, vocal cues, and even fine-tuned transcriptions based on your use case.
Build dashboards, schedule reports, set up alerts, and trigger webhooks so your team is always in the loop.
Evaluate calls with best-in-class evaluators you can run on demand or automate via SDK/API.
🔹 Simulations & Personas
Run end-to-end simulations for both inbound and outbound agents, over the phone or WebSocket - so you’re testing the same paths real customers take.
Define tests as conversations - a sequence of turns between customer and agent, using a graph-based approach. This makes it easy to branch into edge cases or test variants, so your coverage reflects real-world complexity, not just happy paths.
Configure personas by gender, language, accent, background noise, and speech profile (pace, clarity, disfluencies).
Layer on behavior profiles like base emotion, intent clarity, confirmation style, memory reliability - even a backstory.
Stress-test across real-world variables and automatically generate test cases from live calls (failed calls → repeatable tests).
🔹 Developer-first Integrations
First-class SDKs in Node & Python + REST API.
Native support for LiveKit, Pipecat, VAPI, Retell, and Voiceflow.
Easiest integrations on the market - nothing bolted together overnight.
👉 In the past 6 months, Roark has already processed over 10M minutes of calls for companies like Radiant Graph, Podium, Aircall and BrainCX - helping them evaluate agents and run simulations at scale.
The result? A full lifecycle platform that closes the loop: monitor your live calls → spot failures → turn them into tests → improve continuously.
Think of Roark as the QA + Observability layer for Voice AI - robust, deeply thought-out, and built to last.
If you’re building voice agents, you can sign up today for 50% off with our PH discount, book a demo here if you’d like a walkthrough, or just drop me a note at [email protected] - we’d love to help.
- James & Daniel