Industry
We open-sourced Gepard 1.0 - a 555M streaming TTS that starts talking as text arrives. ~50ms to TTFA, ~20x RTF on 1 RTX 5090. Voice cloning …
We open-sourced Gepard 1.0 - a 555M streaming TTS that starts talking as text arrives. ~50ms to TTFA, ~20x RTF on 1 RTX 5090. Voice cloning from seconds of audio. vLLM native. Apache 2.0. Demo + weigh
We open-sourced Gepard 1.0 - a 555M streaming TTS that starts talking as text arrives. ~50ms to TTFA, ~20x RTF on 1 RTX 5090. Voice cloning from seconds of audio. vLLM native. Apache 2.0. Demo + weights: https://huggingface.co/nineninesix/gepard-1.0
Source: Clem Delangue (X) | 2026-07-07