Hands-on Test of Local Voice Cloning with Ant Ling Ming-3.0-tts-0.5B
Ant Ling reposted a test by user @ItsmeAjayKV: Ming-3.0-tts-0.5B runs locally on an RTX 3090 and completed cloning using only a 5-second sample of the user's own voice, even though the recording contained fan noise. The user also said the model uses about 3.3 GB of VRAM, takes up less than 3 GB of disk space, and generates speech faster than real time.
View original postTested voice cloning with Ming-3.0-tts-0.5B by @AntLingAGI and it is even more insane. For a model of this size, voice cloning happens really well, i tested my own voice, half drunk, in a room full of noise (fan noise mostly) and it instantly cloned it. It needed just a 5-second sample of my voice, and it speaks faster than real time: about 4 seconds of speech in 2–3 seconds. All running locally on my RTX 3090. Ming takes about 3.3 GB of VRAM, and the whole model is under 3 GB on disk. Great time for Local AI.
View original
Tested voice cloning with Ming-3.0-tts-0.5B by @AntLingAGI and it is even more insane. For a model of this size, voice cloning happens really well, i tested my own voice, half drunk, in a room full of noise (fan noise mostly) and it instantly cloned it. It needed just a 5-second sample of my voice, and it speaks faster than real time: about 4 seconds of speech in 2–3 seconds. All running locally on my RTX 3090. Ming takes about 3.3 GB of VRAM, and the whole model is under 3 GB on disk. Great time for Local AI.
Body
Great to see Ming-3.0-tts-0.5B running locally on an RTX 3090! In @ItsmeAjayKV’s test, a 5-second sample of his own voice was enough for cloning—even with fan noise in the recording. 🫶 Thanks for sharing, AJ! We’d love to see what you build next.