Someone built a LOCAL ELEVENLABS that clones ANY voice from 3 seconds of audio and generates speech

someone built a LOCAL ELEVENLABS that clones ANY voice from 3 seconds of audio and generates speech in 10 languages  its called voicebox, runs ENTIRELY on your laptop, costs $0 FOREVER, no cloud, no subscription, your voice data never leaves your machine  you record or upload a few seconds of anyones voice, voicebox creates a voice profile and from that point you can make it say anything in that voice, natural prosody, emotion, cadence. not robotic TTS, actual human-sounding speech  powered by qwen3-TTS, same class of model the big paid services use, model downloads once, no internet needed after that, mac gets native Metal GPU acceleration, near real-time generation. windows needs NVIDIA but CUDA works out of box  it also has a full DAW-style timeline editor, multi-track, multi-voice. you can build entire podcasts with different cloned voices, arrange clips, mix conversations, this is a production tool  a professional voice actor charges $250-500 per FINISHED MINUTE  ElevenLabs charges $22-99/month and keeps your voice data on their servers  this is one download and your data NEVER leaves your machine