Roark
Test, monitor, and improve your voice agents
537 followers
Test, monitor, and improve your voice agents
537 followers
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.
Roark
👋 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 james@roark.ai - we’d love to help.
- James & Daniel
@zammitjames @danielgauci
A few years ago I spent months building voice AI startup... We failed miserably 😅
One of the main reason: reliability!
It's something to build cool proto !
It's highly different and more complicated to have something robust you can have trust in !
What you guys do is allowing millions of dev to have the confidence to ship !
A super noble mission and a crucial one for the entire ecosystem!
👊 Keep pushing the Voice AI industry needs you to get too millions of devices and robots 🖤
Roark
@thibaulttbot Thank you for your support T-Bot - glad this resonated!!
Roark
@imnikhill10 Appreciate you Nikhil 🚀 thanks for the upvote!
@zammitjames @danielgauci Congratulations!!
Roark
@maria_q Thanks Maria!
@zammitjames @danielgauci Congrats on the launch! Amazing product - we use it daily!
Roark
@cornelius_schramm1 Thanks Cornelius - appreciate your support!
AngelList
Let's go @zammitjames and team!
Roark
@thibqut Thank you for the support Thibaut!
Agnes AI
Cool, voice agents are getting more and more popular and your product seems to be a doctor for them! BTW - will you give any improvement suggestion for voice agents?
Roark
@cruise_chen Thanks Cruise! 🙏 Exactly, we don’t just flag failures, we also help teams understand why they happened and what to try next. For example, we’ll surface insights like whether you should test different TTS engines, adjust prompts, or tweak how your agent handles specific scenarios.
The idea is to make it really clear what “levers” you can pull to improve reliability - so you’re not just staring at metrics, but actually iterating faster.
Can I use this to practice calling humans? I would rather drink bleach than make a phone call.
Roark
@a_e_1 Haha love it - yes, you can spin up practice calls with any persona you like!
Akiflow
Congrats on the launch @danielgauci 🔥
Roark
Thanks @nunziomartinello!
Tylify
Congrats on the launch @danielgauci @zammitjames ! 🎉
Putting 🇲🇹 on the map!
Roark
@webdevluca thank you Luca! Appreciate the support 🙏
Roark
Thank you @webdevluca!
A01
Congrats on the launch! Love how you’re tackling the messy parts of testing and monitoring voice agents. it feels like a much-needed reliability layer. Curious, which part do teams usually get the biggest “aha” moment from first: monitoring, simulations, or integrations?
Roark
@shengkun_ye Thanks for the support! There's definitely a special "aha" moment we get from customers when testing out both our simulations product and being able to see their agent improving over time.
Triforce Todos
Huge congrats on the launch, James & Daniel 👏 This is exactly the kind of backbone voice AI teams need.
Roark
@abod_rehman thank you!