GLM-TTS

### TL;DR

GLM-TTS is a high-quality text-to-speech (TTS) synthesis system based on large language models, supporting zero-shot voice cloning and streaming inference. It utilizes a two-stage architecture combining a language model for speech token generation and a Flow Matching model for waveform synthesis. By introducing a Multi-Reward Reinforcement Learning framework, GLM-TTS significantly improves the expressiveness of generated speech, achieving more natural emotional control compared to traditional TTS systems.

Key Insights & Metrics

Key Features

• Zero-shot Voice Cloning: Clone any speaker's voice with just 3-10 seconds of prompt audio.
• RL-enhanced Emotion Control: Utilizes a multi-reward reinforcement learning framework (GRPO) to optimize prosody and emotion.
• High-quality Synthesis: Generates speech comparable to commercial systems with reduced Character Error Rate (CER).
• Phoneme-level Control: Supports "Hybrid Phoneme + Text" input for precise pronunciation control (e.g., polyphones).
• Streaming Inference: Supports real-time audio generation suitable for interactive applications.

→ Related Releases

Discussion