GPT-SoVITS

Can do

• Voice cloningYes. YesSpeaks in a voice copied from a short reference clip.
• Voice designNo. NoBuilds a new voice from a written description.
• Emotion controlNo. NoTakes graded emotion from a clip, a vector or text.
• Preset voicesNo. NoShips fixed voices; no reference clip needed.

Languages

Runs on

• Remote api_v2 server

  Remote serverCUDACPU

  VoiceStudio is the client; the model runs on the server you configure.

  Engine doc

Hardware

Supported Needs a build Experimental

Licence

Code

MIT

VoiceStudio is AGPL-3.0 and doesn't relicense model weights. Licence guide

Related

• CosyVoice 3Multilingual zero-shot cloning with instructed speech, installed in its own Python environment.
• IndexTTS 2.5Multilingual cloning with emotion control from a reference clip, a vector or text. Made for dubbing.