GLM TTS
GLM-TTS is Zhipu AI’s speech synthesis model for customer service, audiobooks, interactive assistants and document narration. It uses context to infer emotion and intonation, with streaming support that lets speech play while text is still being generated. Summary written by AI Index from Zhipu AI’s own pages.
- Streaming
- Open weights
Prices
1 offering · prices as listedGLM-TTS| Conditions/ 10K characters | Character |
|---|---|
| Standard | ¥2.00 |
Prices from 智谱 BigModel:API 定价 (opens in a new tab) (checked Nov 9, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Model ID
Not stated on Zhipu AI’s pages: max input.
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers speech synthesis yet. We will cite one when its license allows.
Changes
All changes →No changes recorded yet.
Sources
- 智谱 BigModel:API 定价in Chinese (opens in a new tab) docs.bigmodel.cn · checked Nov 9, 2026
- 智谱:GLM-TTSin Chinese (opens in a new tab) docs.bigmodel.cn · checked Nov 9, 2026
- 智谱 BigModel:新品发布in Chinese (opens in a new tab) docs.bigmodel.cn · checked Nov 8, 2026
- zai-org/GLM-TTS model card (opens in a new tab) huggingface.co · checked Nov 9, 2026
- GitHub - zai-org/GLM-TTS: GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning · GitHub (opens in a new tab) github.com · checked Nov 6, 2026
Zhipu AI’s official policies: data use, privacy, terms →
Zhipu AI · China · z.ai
Related models
Snapshots, the same family and other models from this provider