Text-to-Speech
Safetensors
GGUF
qwen2
audio
speech
speech-language-models
conversational

Voice Supports?

#2
by ApurvCodiste - opened
  1. Can anyone tell me how many voices it have supported?
  2. Can we use the voice cloning with this model?
  3. RealTime Streaming is possible or not?
  1. It supports voice cloning so unlimited basically
  2. Yes, it’s prefix based voice cloning
  3. Also yes, I’m not sure code for it is out yet but you can probably just detokenize every 50 tokens generated into 1 second of audio.
harryjulian changed discussion status to closed

Sign up or log in to comment