⬢github Python · 40.5K ★ +20 since we first saw it · pushed 17 d ago · Apache-2.0
OpenBMB/VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
VoxCPM is a tokenizer-free, open-source text-to-speech system from OpenBMB that generates speech with a diffusion autoregressive architecture. The VoxCPM2 release is a 2B-parameter model trained on 2M+ hours of audio, supporting 30 languages, voice design from text descriptions, controllable voice cloning, and 48kHz output.
Why now: The major VoxCPM2 release adds multilingual synthesis, voice design, controllable cloning, and 48kHz audio, drawing wide attention (40k+ stars) alongside live demos and a technical report.
Who it is for: Developers and researchers building speech synthesis, voice cloning, or audio content applications.
audiodeeplearningminicpmmultilingualpythonpytorchspeechspeech-synthesistext-to-speechtts
Stars over our 35 snapshots: 40.5K to 40.5K, since 8 h ago.
Where people talked about it
- ⬢github OpenBMB/VoxCPM 17 h ago
API: https://socialmediatrends-api.osmike.com/v1/repos/OpenBMB/VoxCPM