132 likes
Multilingual 0.5B TTS model clones voices and adds breath tags
What is Ming-3.0-tts-0.5B?
Ming-3.0-tts is a 0.5 billion-parameter text-to-speech model that can generate speech in Chinese, English, German, Spanish, French, Korean and Japanese, plus Sichuanese and Cantonese dialects. It offers zero-shot voice cloning, natural-language speaker description, and inline tags for breaths, coughs, sighs, laughter and other delivery cues.
Who it is for
If you build voice assistants, podcasts, or educational audio, you can create custom multilingual voices on the fly without gathering large recordings.