Fetching metadata from the HF Docker repository... 2 days ago
-
Fill a take: 800 chars is ~54s, just under the frame cap, instead of stopping at 600 Running
VoiceClimax
-
Split a take into start (GPU, charged to the caller's IP) and stream (direct)
VoiceClimax
-
History turns may carry audio instead of codes, for backends that cannot export frames
VoiceClimax
-
Add /speech: chunked take with a context token, and emit the sampled codes
VoiceClimax
-
Point the preset at the clip we ship; skip missing presets instead of failing startup
VoiceClimax
-
Streaming speech service on ZeroGPU
VoiceClimax