All posts
Research
How streaming state space models keep voice fast
A look at why we build our speech models on streaming sequence architectures, and what that means for live conversation.
Ivo Petrak
7 min read
Live conversation is unforgiving. A pause that would be fine in a podcast feels awkward on a phone call, so our research starts from one question: how fast can a model start speaking without giving up quality?
Streaming by design
State space layers keep a compact memory of everything they have heard so far. That lets a model process audio as it arrives instead of waiting for a full sentence, which keeps the first word of every reply close to instant.
Quality without the wait
We pair those layers with careful training on conversational speech, so voices keep their warmth and rhythm even when they are generated piece by piece.
What is next
We are now exploring hierarchical models that read raw audio directly. Expect more research notes on this blog as that work matures.
More from the blog
News
Introducing Halvora Agents
Halvora Agents brings our speech models together into one platform for building phone agents that answer, route and resolve calls.
Mara Ellison
Product
Designing voices callers trust
What we learned while designing the default voice library, from pacing and warmth to how a voice should sound when it apologizes.
Lena Okafor
Engineering
Measuring turn-taking in live calls
How our team evaluates when an agent should speak, wait or yield, and the tools we use to test it before launch.
Sam Reyes
Get started today
Talk to an expert.
Meet someone from our team and see how Halvora can power voice experiences your callers will remember.
Start building.
Spin up a voice agent or call our models from the API, and go live the same day.
We’re hiring!
Help build voice that feels human