All models
voice-cloning

GLM-TTS

MIT

English and Chinese reference-conditioned speech

Evaluate English and Chinese voice-conditioned speech. Supplied example prompt audio has separate research-only terms. Bring an authorized reference; do not use those examples as commercial presets. Hardware and quality remain unmeasured here.

Hear GLM-TTS

Standardized samples are pending for this release. See the official sources below for the author’s demo.

GLM-TTS · Samples pending · Same three scripts across the directory.

Best for: Evaluate English and Chinese voice-conditioned speech.

Permissive model license: Supplied example prompt audio has separate research-only terms. Bring an authorized reference; do not use those examples as commercial presets. Hardware and quality remain unmeasured here.

Code: MIT. Weights: MIT. License sources checked 2026-09-20. Source 1Source 2

Before you choose: Supplied example prompt audio has separate research-only terms. Bring an authorized reference; do not use those examples as commercial presets. Hardware and quality remain unmeasured here. Streaming support was not verified in the cited repository.

No OpenSpeech hardware benchmark yet; follow the checkpoint documentation.

Details reviewed 2026-09-20. Hardware figures are estimates unless a benchmark is linked.

No samples yet

Every model in this directory is read against the same three scripts so voices can be compared honestly — GLM-TTS’s samples just haven’t been generated yet.

Contribute samples on GitHub →

Run GLM-TTS

git clone https://github.com/zai-org/GLM-TTS.git

GLM-TTS FAQ

Do I need a GPU to run GLM-TTS?

We have not verified a hardware requirement for this release. Follow the official setup instructions.

Can GLM-TTS clone voices?

Yes — GLM-TTS supports voice cloning from reference audio.

What license is GLM-TTS released under?

GLM-TTS is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does GLM-TTS support?

GLM-TTS supports English, Chinese.

Is there a hosted GLM-TTS API?

OpenSpeech Cloud is accepting production-access interest for GLM-TTS, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.