✦
Summary
Ming-3.0-TTS is an open-weight speech-generation family for narration, audio stories, podcasts, and conversational products. A lightweight dense model and a mixture-of-experts variant provide different deployment options, with natural-language direction and expressive speech controls.
About Ming-3.0-TTS
Developers can create character voices and localized narration while choosing a model size suited to their serving environment. Core capabilities include Voice design, Reference-voice cloning, Director-style instructions, and Paralinguistic tags.
Public code or model weights are linked from the project, with setup instructions for running or adapting the system. Additional characteristics include Seven languages and two dialects, A 0.5B dense model, A 7.9B-total MoE variant, and Podcast generation in the tiny variant.