Local text-to-speech models
9 current open-weight models from 6 labs. Latest version of each family only.
Models
ModelLabParamsYour deviceScore
AuKTencent——IndexTTS 2.5Bilibili IndexTeam——Higgs TTS 3Boson AI4.65B—Chatterbox FlashResemble AI——MOSS TTS v1.5OpenMOSS8.49B—Supertonic 3Supertone——Chatterbox MultilingualResemble AI——DramaboxResemble AI——Chatterbox NanoResemble AI——Newest first.
Min memory is the smallest listed option. ● stated by the publisher · ◇ estimate from file size, an 8K-token context and 0.5 GB for the runtime. — means no figure is available.