Avartha

The Real-time AI Agent Factory

[Avartha @AvarthaAI]

Introducing Avartha.

We're building the infrastructure to bring frontier-grade intelligence to real-time applications. Our first release, Ava Zero, is a voice agent entirely running open models using our inference infrastructure and ranks #1 on Sierra's tau-voice benchmark with highest task completion rate and generation quality and just costs $2.5 per hour.

Open models are now at the frontier of voice AI.

[Avartha @AvarthaAI]

Voice is poised to be the dominant interaction surface for all of computing in the future. So far voice ai have been held back by chunky models, but when you plug in models like @Zai_org's GLM 5.3 in the loop, possibilities become endless.

Here is a snippet of what our team has been cooking with Ava, our voice agent. Happy Halloween! 🎃

[Avartha @AvarthaAI]

@olegzanx @alsched Hi Oleg, this is the orginal version of the benchmark: https://t.co/dgDE35DZam

[Ujjwal Singh @ujjjwalll]

Had the chance to validate Ava Zero early, and it delivers.

The thing most voice agent builders miss is real-world conditions: background noise, crosstalk, messy audio. Ava Zero handles all of it without giving up speed, and inference stays lightning fast.

Kudos 🚀

[Avartha @AvarthaAI]

Read more: https://t.co/1UFfJYK7FR

[Avartha @AvarthaAI]

Introducing Avartha.

We're building the infrastructure to bring frontier-grade intelligence to real-time applications. Our first release, Ava Zero, is a voice agent entirely running open models using our inference infrastructure and ranks #1 on Sierra's tau-voice benchmark with highest task completion rate and generation quality and just costs $2.5 per hour.

Open models are now at the frontier of voice AI.

[Avartha @AvarthaAI]

We're a 10-person team that spun out of Georgia Tech's Systems for AI Lab. We co-created chunked prefills, ray, kv-cache parallelism, and chunked pipeline parallelism among others.

We believe that “One Size Fits All” is an idea whose time has come and gone. The next generation of inference infrastructure is going to be hyperspecialized by workload, and we are on a mission to build the best systems for real-time applications.