InclusionAI · Text-to-Speech
Ming-omni-tts-0.5B
Unified 0.5B audio model generating speech, music, and sound in one channel. Custom 12.5Hz tokenizer + Patch-by-Patch compression yields 3.1Hz inference. 93% Cantonese accuracy and SOTA emotion control.
Open the source ↗Similar Audio & Speech releases
- UniAudio 2.0
Research · Text-to-Speech · Week 7, 2026
- MOSS-TTS
OpenMOSS · Text-to-Speech · Week 7, 2026
- AudioStory
Tencent ARC · Text-to-Speech · Week 32, 2025
- Audio8-TTS-Realistic 0.6B
Audio8 (edge0-ai) · Compact multilingual TTS · Week 45, 2026
- Paradee-8M-v1.2
Sahil Mahendrakar · Tiny multi-voice TTS · Week 45, 2026
- Ming-3.0-tts
Inclusion AI (Ant Group) · Open TTS · Week 44, 2026
More from InclusionAI
- UI-Venus-1.5-2B
InclusionAI · Web Agents · Week 10, 2026
- LLaDA 2.1-mini
InclusionAI · MoE Architecture · Week 7, 2026
- Ring-1T
InclusionAI · Reasoning · Week 42, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.