日本語のみで絞り込む
VoxCPM2 is the latest major release — a 2B parameter model trained on over 2 million hours of multilingual speech data, now supporting 30 languages, Voice ...
2025/9/29 -VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 ...
VoxCPM2 is a tokenizer-free Text-to-Speech model trained on over 2 million hours of multilingual speech data. Built on a MiniCPM-4 backbone with AudioVAE V2, it ...
Free, open-source TTS with voice cloning! Create controllable, expressive AI voices in 30+ languages and 48kHz studio-quality audio.
Open-source desktop voice-cloning studio for creators — clone a voice, script lines with emotion markers, synthesize on-device. Tauri + VoxCPM2, runs on macOS, ...
VoxCPM2 is an AI voice generation tool with three modes: Voice Design, Controllable Cloning, and Ultimate Cloning. Try the live demo free.
VoxCPM2 achieves state-of-the-art or competitive results on major zero-shot and controllable TTS benchmarks. See the GitHub repo for full benchmark tables ...
2026/6/5 -VoxCPM2 achieves state-of-the-art or competitive performance on public zero-shot and instruction-following TTS benchmarks. On our internal 30- ...
Hello everyone, welcome to the VoxCPM2 speech synthesis demo. Today I'll show you the effect of cross-lingual voice transfer in different languages. Chinese ...