diff --git a/README.md b/README.md
index 8eaab35..9944f7b 100644
--- a/README.md
+++ b/README.md
@@ -13,6 +13,7 @@
- Custom Voice: Predefined speaker voices
- Voice Design: Create voices from natural language descriptions
- Voice Cloning: Clone voices from uploaded audio
+- Audiobook Generation: Upload EPUB files and generate multi-character audiobooks with LLM-powered character extraction and voice assignment
- Dual Backend Support: Switch between local model and Aliyun TTS API
- Multi-language Support: English, 简体中文, 繁體中文, 日本語, 한국어
- JWT auth, async tasks, voice cache, dark mode
@@ -33,6 +34,16 @@
+### Audiobook Generation
+
+
+
+
+  |
+  |
+
+
+
## Tech Stack
**Backend**: FastAPI + SQLAlchemy + PyTorch + JWT
diff --git a/README.zh.md b/README.zh.md
index f70ea7b..2b7e7d6 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -13,6 +13,7 @@
- 自定义语音:预定义说话人语音
- 语音设计:自然语言描述创建语音
- 语音克隆:上传音频克隆语音
+- 有声书生成:上传 EPUB 文件,通过 LLM 自动提取角色并分配语音,生成多角色有声书
- 双后端支持:支持本地模型和阿里云 TTS API 切换
- 多语言支持:English、简体中文、繁體中文、日本語、한국어
- JWT 认证、异步任务、语音缓存、暗黑模式
@@ -33,6 +34,16 @@
+### 有声书生成
+
+
+
+
+  |
+  |
+
+
+
## 技术栈
**后端**: FastAPI + SQLAlchemy + PyTorch + JWT
diff --git a/images/audiobook-chapters.png b/images/audiobook-chapters.png
new file mode 100644
index 0000000..dc1905e
Binary files /dev/null and b/images/audiobook-chapters.png differ
diff --git a/images/audiobook-characters.png b/images/audiobook-characters.png
new file mode 100644
index 0000000..5df4ec9
Binary files /dev/null and b/images/audiobook-characters.png differ
diff --git a/images/audiobook-overview.png b/images/audiobook-overview.png
new file mode 100644
index 0000000..5547cbd
Binary files /dev/null and b/images/audiobook-overview.png differ