

KugelAudio
Real-time text-to-speech model you can self-host
¿Qué es KugelAudio?
Most natural real-time TTS with voice cloning and sub-60ms latency, 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. Adapters for LiveKit, Pipecat, and Vapi. Built by 4 in Berlin.
Capturas de pantalla
?
Aún no hay comentarios. ¡Sé el primero!
Conversaciones reales sobre KugelAudio en X
Publicar en X





