GLM-TTS is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named GLM-TTS among their alternatives. The relationship is not symmetric — how GLM-TTS rates them is a separate judgement, made when GLM-TTS is analysed in its own right.
calls GLM-TTS “Choose when you need emotion-expressive zero-shot TTS via multi-reward reinforcement learning.”
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
calls GLM-TTS “choose for emotion-expressive zero-shot TTS trained with multi-reward reinforcement learning.”
Spark-TTS Inference Code
calls GLM-TTS “choose for controllable emotion-expressive zero-shot TTS via multi-reward RL, no speech editing.”
Zero-Shot Speech Editing and Text-to-Speech in the Wild
calls GLM-TTS “Choose for emotion-expressive zero-shot TTS with multi-reward RL if you need emotional TTS but not editing existing audio.”
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech