release aidev NEEDS REVIEW SIG 1/5

Z.ai publishes GLM-TTS: zero-shot voice cloning with flow matching

Z.ai published GLM-TTS on Hugging Face, a text-to-speech model (arxiv:2512.14291) with zero-shot voice cloning, reinforcement learning, and flow matching. The repository uses the glm-tts library and carries an MIT license. No benchmark results are provided in the repository listing.

PUBLISHED2025-12-10
OBSERVED2026-08-11
AGE8mo
SOURCES1

Model published on Hugging Face under zai-org organisation.

  • Pipeline: text-to-speech
  • Library: glm-tts
  • Tags: tts, zero-shot, voice-cloning, reinforcement-learning, flow-matching, zh, en, arxiv:2512.14291
  • License: MIT
model-supportcapability

COMMUNITY

No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.