Latest / Kana & Mari's SoundRepos (English)

tetsuo-ai/voice_clone_lab | GitHub
Voice Clone Lab is a local tool for fine-tuning Qwen3-TTS on a speaker’s voice and generating speech from text. It provides a CLI and Gradio web UI for audio preparation, transcription and transcript review, training, and speech generation, including zero-shot voice cloning; it emphasizes consent and keeps voice data on the user’s machine. Related: tetsuo-ai/voice_clone_lab / GitHub
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.