GiaoGiao屋
GiaoGiao屋
New Qwen3-TTS 1.7B voice synthesis model added, supporting 10 languages, voice cloning from 3-second audio samples, GPU-accelerated inference.
Based on open source AI technology, supports quick voice cloning from audio samples, all processing completed locally.
Open source audio AI aggregation station officially launched, curating the best open source audio AI tools worldwide, all free, ready to use.