This page is maintained by the EarlyHound community.Work at KugelAudio? Claim this page
Real-time text-to-speech model you can self-host
Site up · checked 4 days ago
KugelAudio is a real-time text-to-speech model with voice cloning and under 60ms latency, available on-prem or via API. Grammar-aware normalization reads phone numbers, IBANs, addresses and medications naturally across 25+ languages, with word-level timestamps and IPA support. It ships adapters for LiveKit, Pipecat and Vapi, and is built by a team of four in Berlin.
No reviews yet. Be the first to say how this actually works.
