# GLM-TTS Technical Report

arXiv: https://arxiv.org/abs/2512.14291 · HTML: https://mlsanity.com/paper/2512.14291/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2025.

## Built on by (most cited first, 9 of 9)

- [OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models](https://mlsanity.com/paper/2604.00688/) (2026)
- [MM-Sonate: Multimodal Controllable Audio-Video Generation with Zero-Shot Voice Cloning](https://mlsanity.com/paper/2601.01568/) (2026)
- [UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions](https://mlsanity.com/paper/2604.22209/) (2026)
- [FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation](https://mlsanity.com/paper/2606.09141/) (2026)
- [Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS](https://mlsanity.com/paper/2606.25672/) (2026)
- [HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech](https://mlsanity.com/paper/2606.28249/) (2026)
- [VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion](https://mlsanity.com/paper/2607.11706/) (2026)
- [Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue](https://mlsanity.com/paper/2609.04250/) (2026)
- [GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability](https://mlsanity.com/paper/2610.15082/) (2026)

## Abstract (arXiv)

This work proposes GLM-TTS, a production-level TTS system designed for efficiency, controllability, and high-fidelity speech generation. GLM-TTS follows a two-stage architecture, consisting of a text-to-token autoregressive model and a token-to-waveform diffusion model. With only 100k hours of training data, GLM-TTS achieves state-of-the-art performance on multiple open-source benchmarks. To meet production requirements, GLM-TTS improves speech quality through an optimized speech tokenizer with fundamental frequency constraints and a GRPO-based multi-reward reinforcement learning framework that jointly optimizes pronunciation, speaker similarity, and expressive prosody. In parallel, the system enables efficient and controllable deployment via parameter-efficient LoRA-based voice customization and a hybrid phoneme-text input scheme that provides precise pronunciation control. Our code is available at https://github.com/zai-org/GLM-TTS. Real-time speech synthesis demos are provided via Z.ai (audio.z.ai), the Zhipu Qingyan app/web (chatglm.cn).