GLM-TTS is an advanced text-to-speech synthesis system built on large language model technologies that focuses on producing high-quality, expressive, and controllable spoken output, including features like emotion modulation and zero-shot voice cloning. It uses a two-stage architecture where a generative LLM first converts text into intermediate speech token sequences and then a Flow-based neural model converts those tokens into natural audio waveforms, enabling rich prosody and voice character even for unseen speakers. The system introduces a multi-reward reinforcement learning framework that jointly optimizes for voice similarity, emotional expressiveness, pronunciation, and intelligibility, yielding output that can rival commercial options in naturalness and expressiveness. GLM-TTS also supports phoneme-level control and hybrid text + phoneme input, giving developers precise control over pronunciation critical for multilingual or polyphone-rich languages.
Features
- Zero-shot voice cloning from short prompt audio
- Multi-reward reinforcement learning for expressive prosody
- Two-stage LLM + Flow-based audio generation pipeline
- Support for phoneme-level control and hybrid inputs
- High-quality synthesis comparable with commercial TTS
- Streaming real-time speech synthesis
Project Samples
