diff --git a/README.md b/README.md
index 87edd1d..a1773bd 100644
--- a/README.md
+++ b/README.md
@@ -8,11 +8,12 @@
- 
+
+ 
# MOSS-TTSD 🪐
@@ -24,7 +25,7 @@
MOSS-TTSD (text to spoken dialogue) is an open-source bilingual spoken dialogue synthesis model that supports both Chinese and English.
It can transform dialogue scripts between two speakers into natural, expressive conversational speech.
MOSS-TTSD supports voice cloning and long single-session speech generation, making it ideal for AI podcast production, interviews, and chats.
- For detailed information about the model and demos, please refer to our [Blog-en](https://www.open-moss.com/en/moss-ttsd/) and [中文博客](https://www.open-moss.com/cn/moss-ttsd/). You can also find the model on [Hugging Face](https://huggingface.co/fnlp/MOSS-TTSD-v0.5) and try it out in the [Spaces demo](https://huggingface.co/spaces/fnlp/MOSS-TTSD).
+ For detailed information about the model and demos, please refer to our [Blog-en](https://www.open-moss.com/en/moss-ttsd/) and [中文博客](https://www.open-moss.com/cn/moss-ttsd/). You can also find the model on [Hugging Face](https://huggingface.co/fnlp/MOSS-TTSD-v0.7) and try it out in the [Spaces demo](https://huggingface.co/spaces/fnlp/MOSS-TTSD).
## Highlights
@@ -36,7 +37,7 @@ MOSS-TTSD supports voice cloning and long single-session speech generation, maki
## News 🚀
- - **[2025-11-01]** MOSS-TTSD v0.7 is released! v0.7 significantly improves audio quality, voice cloning capability, and stability, adds support for 32 kHz high‑quality output, greatly extends single‑pass generation length (960s→1700s), and more reliably generates speech events following speaker tags. We recommend using the v0.7 model by default.
+ - **[2025-11-01]** MOSS-TTSD v0.7 is released! v0.7 significantly improves audio quality, voice cloning capability, and stability, adds support for 32 kHz high‑quality output, greatly extends single‑pass generation length (960s→1700s). We recommend using the v0.7 model by default. [MOSS-TTSD v0.7 Model Address](https://huggingface.co/fnlp/MOSS-TTSD-v0.7)
- **[2025-09-09]** We supported SGLang inference engine to accelerate model inference by up to **16x**.
- **[2025-08-25]** We released the 32khz version of XY-Tokenizer.
- **[2025-08-12]** We add support for streaming inference in MOSS-TTSD v0.5.
@@ -59,7 +60,7 @@ pip install flash-attn
### Download XY-Tokenizer
-You also need to download the XY Tokenizer model weights. You can find the weights in the [XY_Tokenizer repository](https://huggingface.co/fnlp/XY_Tokenizer_TTSD_V0_32k).
+You also need to download the XY Tokenizer model weights. You can find the weights in the [XY-Tokenizer-TTSD version repository](https://huggingface.co/fnlp/MOSS_TTSD_tokenizer).
```bash
mkdir -p XY_Tokenizer/weights
diff --git a/README_zh.md b/README_zh.md
index ecf5c79..d01b568 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -8,11 +8,12 @@
- 
+
+
# MOSS-TTSD 🪐
@@ -22,7 +23,7 @@
## 概述
MOSS-TTSD（text to spoken dialogue）是一个开源的中英双语口语对话合成模型，可以将包含两位说话人的对话脚本转换为自然、富有表现力的对话语音。MOSS-TTSD支持双说话人零样本音色克隆与长时间单段语音生成，非常适合播客，访谈，聊天等对话场景。
-详细模型介绍与演示请见我们的[中文博客](https://www.open-moss.com/cn/moss-ttsd/)和[Blog-en](https://www.open-moss.com/en/moss-ttsd/)。模型权重在 [Hugging Face](https://huggingface.co/fnlp/MOSS-TTSD-v0.5) 提供，并可在 [Spaces 演示](https://huggingface.co/spaces/fnlp/MOSS-TTSD) 在线体验。
+详细模型介绍与演示请见我们的[中文博客](https://www.open-moss.com/cn/moss-ttsd/)和[Blog-en](https://www.open-moss.com/en/moss-ttsd/)。模型权重在 [Hugging Face](https://huggingface.co/fnlp/MOSS-TTSD-v0.7) 提供，并可在 [Spaces 演示](https://huggingface.co/spaces/fnlp/MOSS-TTSD) 在线体验。
## 亮点
@@ -34,7 +35,7 @@ MOSS-TTSD（text to spoken dialogue）是一个开源的中英双语口语对话
## 最新动态 🚀
-- **[2025-11-01]** 我们发布了 MOSS-TTSD v0.7：显著提升了音质、声音克隆能力与稳定性，支持32khz高音质输出，并大幅拓展了单次生成长度（960s->1700s），更够比较稳定地根据说话人标签生成语音事件。
+- **[2025-11-01]** 我们发布了 MOSS-TTSD v0.7：显著提升了音质、声音克隆能力与稳定性，支持32khz高音质输出，并大幅拓展了单次生成长度（960s->1700s）。我们推荐默认使用MOSS-TTSD v0.7版本。[MOSS-TTSD v0.7 模型地址](https://huggingface.co/fnlp/MOSS-TTSD-v0.7)
- **[2025-09-09]** 我们支持了 SGLang 推理引擎加速模型推理，最高可加速**16倍**。
- **[2025-08-25]** 我们发布了 32khz XY-Tokenizer。
- **[2025-08-12]** 我们支持了 MOSS-TTSD v0.5 的流式推理。
@@ -57,7 +58,7 @@ pip install flash-attn
### 下载 XY-Tokenizer 权重
-首先需要下载 XY-Tokenizer 的Codec模型权重，见 [XY_Tokenizer仓库](https://huggingface.co/fnlp/XY_Tokenizer_TTSD_V0_32k)。
+首先需要下载 XY-Tokenizer 的Codec模型权重，见[XY-Tokenizer-TTSD版本仓库](https://huggingface.co/fnlp/MOSS_TTSD_tokenizer)。
```bash
mkdir -p XY_Tokenizer/weights