- Home
- Text-to-speech tools
- GLM-TTS
On the recordRead 13 Oct 202622 facts
GLM-TTS
On the record
- Deployment hardware
- The repository provides separate setup instructions for GPU and NPU environments.github.com · read 13 Oct 2026
- Emotion control
- Its multi-reward reinforcement learning framework supports emotional expression and prosody control.github.com · read 13 Oct 2026
- Export formats
- WAVgithub.com · read 20 Sep 2026
- Hardware and setup
- The setup instructions cover GPU and Ascend NPU environments and specify Python 3.10–3.12.github.com · read 12 Oct 2026
- Inference
- The repository provides command-line and shell-script inference, plus an interactive web interface launched with Gradio.github.com · read 12 Oct 2026
- Inference options
- It supports phoneme-level text-to-speech, multiple sampling strategies, and multiple inference modes.github.com · read 13 Oct 2026
- Integrations
- The project acknowledges CosyVoice for frontend processing and vocoding, Llama as its language-model architecture, and Vocos as a vocoder.github.com · read 12 Oct 2026
- Languages
- It primarily supports Chinese and also supports English mixed text.github.com · read 13 Oct 2026
- License
- The repository identifies its license as Apache-2.0.github.com · read 13 Oct 2026
- Model architecture
- The system uses an LLM to generate speech token sequences and a Flow model to convert tokens into audio waveforms.github.com · read 13 Oct 2026
- Model downloads
- The complete model weights can be downloaded from Hugging Face or ModelScope.github.com · read 13 Oct 2026
- Product
- GLM-TTS is a large-language-model-based text-to-speech system that supports zero-shot voice cloning and streaming inference.github.com · read 12 Oct 2026
- Pronunciation
- Phoneme-in supports hybrid phoneme and text input to control pronunciation of specific words, including polyphones and rare characters.github.com · read 12 Oct 2026
- Purpose
- GLM-TTS is a text-to-speech synthesis system based on large language models.github.com · read 13 Oct 2026
- Requirements
- The quick-start instructions specify Python 3.10 through 3.12.github.com · read 13 Oct 2026
- Security
- The repository page does not state security certifications or compliance claims.github.com · read 12 Oct 2026
- Streaming
- It supports real-time streaming audio generation for interactive applications.github.com · read 13 Oct 2026
- 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.github.com · read 12 Oct 2026
