Inclusion AI (Ant Group) · Open TTS
Ming-3.0-tts
An open-weight text-to-speech family from Ant Group's Inclusion AI with voice design from a text description, voice cloning, director-style line instructions and inline tags for laughs, sighs and coughs. It speaks seven languages plus Sichuanese and Cantonese. Two models: a 0.5B dense model on Qwen2.5-0.5B, and a tiny MoE with 7.9B total and 1.3B active parameters that adds long-form podcast generation. On Artificial Analysis in October 2026, the 0.5B ranks first among open-weight models for Controlled Voice (1069 Elo) and ties first overall for pronunciation (93.2%). MIT licence; about 200 GitHub stars. Follows Ming-omni-tts-0.5B covered in week 8.
Open the source ↗Similar Audio & Speech releases
- Audio8-TTS-Realistic 0.6B
Audio8 (edge0-ai) · Compact multilingual TTS · Week 45, 2026
- KittenTTS 2
KittenML (Stellon Labs) · Voice Cloning TTS · Week 43, 2026
- Fish Audio Drama 3
Fish Audio · Directable TTS · Week 43, 2026
- VoiceStudio v0.5.6
debpalash · Local Voice Studio · Week 42, 2026
- Bhojpuri F5-TTS
gentleman101 · Bhojpuri Voice Cloning · Week 41, 2026
- Gemini 3.8 Flash TTS
Google · Expressive Gemini TTS · Week 40, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.