

KugelAudio
Real-time text-to-speech model you can self-host
什麼是 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.
截圖
?
還沒有評論,來搶沙發吧!
X 上關於 KugelAudio 的真實討論
去 X 發文





