{"name":"Ming-3.0-tts","repo":"inclusionAI/Ming-3.0-tts","url":"https://midorreal.com/project/inclusionai-ming-3-0-tts","repository":"https://github.com/inclusionAI/Ming-3.0-tts","description":"Ming-3.0-tts is an open-source TTS model family with 0.5B dense and 7.9B-A1.3B MoE variants, supporting multilingual speech, voice cloning, voice design, and natural-language control.","facts":{"license":{"value":"MIT","source":"https://github.com/inclusionAI/Ming-3.0-tts","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/inclusionAI/Ming-3.0-tts","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/inclusionAI/Ming-3.0-tts/releases","checked":"21 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/inclusionAI/Ming-3.0-tts/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/inclusionAI/Ming-3.0-tts","checked":"22 Nov 2026"}},"stars":618.0,"writeup":{"what_it_is":"Ming-3.0-tts is an open-source speech synthesis model family with two variants: a 0.5b dense model and a tiny MoE model (7.9B total, 1.3B active). It provides multilingual speech generation with voice cloning, voice design, and natural-language and paralinguistic control.","audience":"Developers and researchers building or using text-to-speech systems","claims":[{"kind":"specific","claim":"Ranks 1st among open-weights models on Controlled Voice on Artificial Analysis","excerpt":"ranks **1st among open-weights models on Controlled Voice**","status":"not_checked"},{"kind":"specific","claim":"Achieves 93.2% on the Pronunciation Robustness measure, ranked 1st overall","excerpt":"| 93.2% | **1st overall** |","status":"not_checked"},{"kind":"specific","claim":"Supports 14 inline tags for paralinguistic expressions in Chinese or English","excerpt":"insert 14 inline tags for laughter, sighs, and other vocal expressions in Chinese or English","status":"not_checked"},{"kind":"specific","claim":"Synthesizes Chinese, English, German, Spanish, French, Korean and Japanese, plus Sichuanese and Cantonese","excerpt":"synthesize Chinese, English, German, Spanish, French, Korean and Japanese, plus Sichuanese and Cantonese","status":"not_checked"},{"kind":"broad","claim":"Is described as providing a powerful, accurate speech generation experience","excerpt":"Multilingual speech synthesis with free-form and paralinguistic control.","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-22"},"why_now":null,"owner_supplied":null,"score":{"verdict":"too_early","hype":58,"reality":23,"gap":35,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":{"estimate":true,"lean":"too_close","gap_low":-2,"gap_high":39,"rule":"early-2.0"},"changes":[{"date":"2026-10-19T07:03:25+00:00","text":"Repository created","source":"https://github.com/inclusionAI/Ming-3.0-tts"}],"cite":"Ming-3.0-tts is a GitHub project at https://github.com/inclusionAI/Ming-3.0-tts written mainly in Python, described there as \"Ming-3.0-tts is an open-source TTS model family with 0.5B dense and 7.9B-A1.3B MoE variants, supporting multilingual speech, voice cloning, voice design, and natural-language control\".","attribution":"Data from Mid or Real, https://midorreal.com/project/inclusionai-ming-3-0-tts, checked 22 November 2026. Attribution with a link is required.","still_real":null}