Skip to content
SPECIFICTION
Get listed

GLM-TTS

github.com

WebLinuxSelf-hosted
Visit github.com
Spec score 7.6 #151 of 223 in Text-to-Speech Software

Spec sheet

Purpose
GLM-TTS is a text-to-speech synthesis system based on large language models.Read 13 Oct 2026 · github.com
Product
GLM-TTS is a large-language-model-based text-to-speech system that supports zero-shot voice cloning and streaming inference.Read 12 Oct 2026 · github.com
Platforms
web,self_hostedRead 20 Sep 2026 · github.com
Integrations
The project acknowledges CosyVoice for frontend processing and vocoding, Llama as its language-model architecture, and Vocos as a vocoder.Read 12 Oct 2026 · github.com
Security
The repository page does not state security certifications or compliance claims.Read 12 Oct 2026 · github.com
Support
The project links to a technical report, Hugging Face, ModelScope, and an Audio.Z.AI site; the repository page does not specify a support service.Read 12 Oct 2026 · github.com
License
The repository identifies its license as Apache-2.0.Read 13 Oct 2026 · github.com
Deployment hardware
The repository provides separate setup instructions for GPU and NPU environments.Read 13 Oct 2026 · github.com
Emotion control
Its multi-reward reinforcement learning framework supports emotional expression and prosody control.Read 13 Oct 2026 · github.com
Export formats
WAVRead 20 Sep 2026 · github.com
Hardware and setup
The setup instructions cover GPU and Ascend NPU environments and specify Python 3.10–3.12.Read 12 Oct 2026 · github.com
Inference
The repository provides command-line and shell-script inference, plus an interactive web interface launched with Gradio.Read 12 Oct 2026 · github.com
Inference options
It supports phoneme-level text-to-speech, multiple sampling strategies, and multiple inference modes.Read 13 Oct 2026 · github.com
Languages
It primarily supports Chinese and also supports English mixed text.Read 13 Oct 2026 · github.com
Model architecture
The system uses an LLM to generate speech token sequences and a Flow model to convert tokens into audio waveforms.Read 13 Oct 2026 · github.com
Model downloads
The complete model weights can be downloaded from Hugging Face or ModelScope.Read 13 Oct 2026 · github.com
Pronunciation
Phoneme-in supports hybrid phoneme and text input to control pronunciation of specific words, including polyphones and rare characters.Read 12 Oct 2026 · github.com
Requirements
The quick-start instructions specify Python 3.10 through 3.12.Read 13 Oct 2026 · github.com
Streaming
It supports real-time streaming audio generation for interactive applications.Read 13 Oct 2026 · github.com
Upcoming work
The README lists a 2D Vocos vocoder update and reinforcement-learning-optimized model weights as coming soon.Read 13 Oct 2026 · github.com
Voice cloning
It supports zero-shot voice cloning from 3–10 seconds of prompt audio.Read 13 Oct 2026 · github.com
Web interface
The repository includes instructions for running an interactive web interface with Gradio.Read 13 Oct 2026 · github.com

Where Specifiction places it

Alternatives to GLM-TTSAll alternatives →