Ming-omni-tts:
Simple and Efficient Unified Generation of Speech, Music, and Sound with Precise Control

Ming-omni-tts is a high-performance unified audio generation model that achieves precise control over speech attributes and enables single-channel synthesis of speech, environmental sounds, and music. Powered by a custom 12.5Hz continuous tokenizer and Patch-by-Patch compression, it delivers competitive inference efficiency (3.1Hz). Additionally, the model features robust text normalization capabilities for the accurate and natural narration of complex mathematical and chemical expressions.

- 🔊 Fine-grained Vocal Control: Enables precise control over speech rate, pitch, volume, emotion, and dialects via simple instructions. It achieves 93% accuracy for Cantonese and 46.7% for emotional control, outperforming CosyVoice3.
- 🌌 Intelligent Voice Design: Features 100+ premium built-in voices and supports zero-shot voice design through natural language descriptions. Its performance on the Instruct-TTS-Eval-zh benchmark is on par with Qwen3-TTS.
- 🎶 Immersive Unified Generation: The industry’s first autoregressive model to jointly generate speech, ambient sound, and music in a single channel. Built on a custom 12.5Hz continuous tokenizer and a DiT head architecture, it delivers a seamless, "in-the-scene" auditory experience.
- ⚡ High-efficiency Inference: Introduces a "Patch-by-Patch" compression strategy that reduces the LLM inference frame rate to 3.1Hz. This significantly cuts latency and enables podcast-style audio generation while preserving naturalness and audio detail.
- 🧪 Professional Text Normalization: The model accurately parses and narrates complex formats, including mathematical expressions and chemical equations, ensuring natural-sounding output for specialized applications.