BASE MODEL · SPEECH-TO-SPEECH

OpenVoice V2

Instant voice cloning with control over emotion, accent and rhythm.

Voices built on OpenVoice V2

Technical details

Architecture
Base speaker TTS + tone color converter
Type
Speech-to-speech
Size
0.3 GB
Runs on
~2 GB VRAM
Languages
English, Spanish, French, Chinese, Japanese, Korean
Recommended settings
tau=0.3
Version
v2 · updated 1 yr ago
Source
Hugging Face
License
MIT · Commercial OK

OpenVoice V2 is developed and owned by its original authors. timbre only indexes it.

COMPARE Compare