Launching today
KugelAudio
Real-time text-to-speech model you can self-host
48 followers
Real-time text-to-speech model you can self-host
48 followers
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.
KugelAudio
Congratulations on the launch guys! Few questions:
1. Websites list languages like Hindi to be supported but can not find any voice related to that on playground.
2. I checked the websocket streaming API for TTS.. is it possible to have multi context support (just like elevenlabs) in the streaming API? is that part of plan in future?
Cheers!
KugelAudio
@ashishkingdom Currently we don't have stable support for Hindi, but feel free to try it with a voice sample for cloning. Our main focus are currently European languages and we gather many different voices and accents right now. Regarding your second question, we are compatible with elevenlabs sdk and offer a multi context endpoint that is currently used in the Livekit integration.
@alexnetz super!! will check that out
mailX by mailwarm
How does it handle long numbers and addresses in mixed language contexts, like German with English product names?
KugelAudio
@thamibenjelloun Just tried it out and it works:)
Dont this support nepali language?
KugelAudio
@manish_regmi1Hey, not yet.
Pushary
Sensational for German TTS
Congrats on the launch guys!