SYLIN

VibeVoice

Family · 4 entries

VibeVoice, side by side

NameWhat to knowPrice or memoryRanks
VibeVoice-ASRModelSupports over 50 languages natively; finetuning code and vLLM inference are available~1.6 GB
VibeVoice-TTSModelpromising Small, MIT-licensed speech model from Microsoft, but meant for research only~1.6 GB
VibeVoice-ASR-StreamingModelUnified streaming ASR continuously transcribes who said what as speech arrives, with custom hotwords and 10 languages
VibeVoice-RealtimeModelAdded experimental speakers: multilingual voices in nine languages and 11 English style voices