Cekura Bench
Cekura Bench offers verified benchmarks for voice AI models acting as realtime voice agents. It tests various speech-to-speech AI models across scenarios to evaluate reliability, task success, data accuracy, response time, and cost with publicly available call transcripts. It helps developers and teams choose the best voice AI model for phone-based conversational agents.
Ratings & Reviews
Write a reviewBe the first to share a thoughtful review.
Information
Website checks
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 18, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 68 out of 100, Needs improvement
- Accessibility
- 100 out of 100, Good
- Best Practices
- 100 out of 100, Good
- SEO
- 100 out of 100, Good
Website checks are queued. Results will appear here when complete.
Around the Web
Terrific testing tools for voice AI applications, including complicated features like subagents.
kwindla · Review on Product Hunt
Every speech-to-speech model sounds great in a demo, so we put them all through the same real phone calls with real tool use and scored what actually happened. Excited to see how the rankings shift as new models drop 🚀
dileepchagam · Imported from Product Hunt
Publishing the call transcripts alongside the scores is the part I like here. Being able to look at what actually happened on a failed call makes the ranking much easier to judge. Congrats to the team!
oleksii_sekundant · Imported from Product Hunt