Ant Open-Sources Ming-3.0 Audio Family: TTS with Voice Cloning & Emotion Control, MIT Licensed
Promptmethus · x · 2026-11-05
Ant Group has open-sourced the Ming-3.0 audio model family under the MIT license, free for commercial use with one-click deployment. It consists of three core models:
- Ming-3.0-tts: text-to-speech with voice cloning/design and control over emotion, emphasis, and tone; natively supports multi-voice concurrency for one-click multi-speaker podcast generation. The poster, after hands-on testing, calls it director-grade speech synthesis
- Ming-3.0-audio: a 126B-parameter MoE audio reasoning model that understands environmental sounds and speaker identity; combined with the TTS model it forms a simultaneous-interpretation workflow
- Ming-3.0-asr: a lightweight, high-accuracy transcription model for local meeting notes or real-time voice input
The poster also built a visual demo page showcasing the TTS capabilities.
More from Multimodal
- Atmee v2 live-generates a Taipei alley, pointing toward an agentic world model — flngr · 2026-11-05
- Local demo of Ming-3.0-audio-flash: transcription, sounds and vocal emotion — truecakesnake · 2026-11-05
- New hyper-realistic Glif AI video of a man collecting chestnuts in the rain is nearly indistinguishable from reality — ainsoph00 · 2026-11-05
- VideoMemBench: new benchmark exposes major gaps in MLLMs' in-context video memory — Zhengdong Hu · 2026-11-05
- CCORE releases final 4B model that generates 3D assets as Three.js scenes with GLB export, weights on Hugging Face — ConfidentDinner6648 · 2026-11-05
- 14-run same-seed test: Regenerate 2K's detail comes from the refiner LoRA, but it changes real people's faces — ReferenceFluffy6159 · 2026-11-05