diff --git a/en/basic/admin-panel/ai-setting.mdx b/en/basic/admin-panel/ai-setting.mdx
index f0d88f4..82c8cf2 100644
--- a/en/basic/admin-panel/ai-setting.mdx
+++ b/en/basic/admin-panel/ai-setting.mdx
@@ -20,9 +20,10 @@ You only need one Vercel account to complete the setup.
 | Requirement | Required? | Notes |
 |------|------|------|
 | **Vercel account** | Required | You need a working Vercel account |
-| **Vercel API key** | Required | Used for **AI Chat Runtime** |
+| **Vercel API Token** | Required | Used for **AI Chat Runtime** |
 | **Team / Project** | Required | You need a usable Team and Project. If needed, you can create them in the page |
 | **AI Gateway API key** | When using AI Gateway | Only needed if you choose **AI Gateway** as your model provider |
+| **OpenAI Realtime API Key** | Optional | Only needed if you want to enable **Voice input** in AI Chat |
 | **Public access** | Required | Your **Teable instance** and **object storage (MinIO / S3)** must be publicly accessible |
 
 Vercel-related costs usually have two parts:
@@ -86,13 +87,19 @@ This step sets the default model for sidebar **AI Chat**. The model must come fr
 
 You should choose a stable model that supports tool calling and has already been tested. Otherwise, Agent capability will be noticeably limited.
 
+### Optional. Configure Voice input
+
+**Voice input** lets users enter messages in AI Chat with a microphone.
+
+You can adjust **Max session duration (seconds)** and **Session creates per minute per user**. After voice input is enabled and saved, users will see the microphone button in the AI Chat input box.
+
 ### 4. Configure the runtime and App Builder
 
 Complete **AI Chat Runtime** first, then complete **App Builder**.
 
 <Steps>
   <Step title="Finish AI Chat Runtime">
-    In **AI Chat Runtime**, enter and verify the **Vercel API key**, then select **Team** and **Project**, and finally click **Test Connection**. After the test succeeds, the matching item in the **Pending configuration** panel will turn green.
+    In **AI Chat Runtime**, enter and verify the **Vercel API Token**, select **Team** and **Project**, click **Save**, then click **Test Connection**. After the connection test succeeds, the matching item in the **Pending configuration** panel will turn green.
   </Step>
   <Step title="Finish the basic App Builder setup">
     In **App Builder**, enter the **Vercel access token** under **Vercel Deploy**. This is the core setting required to publish apps.
@@ -139,11 +146,11 @@ Check the **Pending configuration** panel first to see which item is still missi
 
 This usually means **AI Chat Runtime** is not fully configured yet. Make sure all three items below are completed:
 
-- **Vercel API key**
+- **Vercel API Token**
 - **Team**
 - **Project**
 
-Entering only the token is not enough.
+Entering only the token is not enough. After choosing **Team** and **Project**, save the selection before testing the connection.
 </Accordion>
 
 <Accordion title="I get a credit exceeded error">
diff --git a/en/basic/ai/ai-chat.mdx b/en/basic/ai/ai-chat.mdx
index 8edf192..2d3244d 100644
--- a/en/basic/ai/ai-chat.mdx
+++ b/en/basic/ai/ai-chat.mdx
@@ -26,6 +26,13 @@ Files can also be pasted or dropped directly into the input box. They appear as
 
 When you paste a long block of plain text, Teable converts it to a Markdown attachment so the message input stays easy to read. You can preview text and Markdown attachments from their attachment chips.
 
+## Input Controls
+
+- **Voice input**: Click the microphone button in the input box, allow microphone access, start real-time transcription, then choose **Finish voice input** or **Discard voice input**.
+- **Model**: Use the model menu to choose the model for the conversation. Use a lighter model for simple queries, cleanup, or rewriting, and a stronger model for complex planning, cross-table analysis, and app building.
+- **Intelligence**: Choose the **Intelligence** level separately in the model menu. It controls thinking depth; higher levels produce more thorough reasoning.
+- **Queued messages**: If you send another message while AI is still working, the message is queued. Queued items show the same table, view, attachment, and selection chips as the chat input. Use **Edit** to move a queued item back into the input, **Stop & send now** to interrupt the current run and send that item, or **Remove** to delete it from the queue.
+
 ## Common Uses
 
 <CardGroup cols={2}>
@@ -111,4 +118,5 @@ After uploading files, AI can answer questions using both file content and table
 - **Use `@` to select nodes**: When AI needs to reference tables, views, apps, automations, or folders, type `@` and select them directly.
 - **Confirm before execution**: For tasks that modify data, create tables, create apps, or enable automations, ask AI to describe the changes before running them.
 - **Choose the model by task**: If the space supports model selection, use a lighter model for simple queries, cleanup, or rewriting, and a stronger model for complex planning, cross-table analysis, and app building.
+- **Adjust the Intelligence level**: **Intelligence** controls thinking depth; higher levels produce more thorough reasoning.
 - **Start a new chat when the topic changes**: A new chat is recommended when the topic changes, the conversation becomes too long, or context usage should be reduced.
diff --git a/en/basic/view/grid.mdx b/en/basic/view/grid.mdx
index e4e2c26..1a2789d 100644
--- a/en/basic/view/grid.mdx
+++ b/en/basic/view/grid.mdx
@@ -43,7 +43,7 @@ If you want to ensure your preferred row height configuration isn't accidentally
 
 ### Selection Statistics
 
-When you select cells in grid view, Teable shows **Average**, **Count**, and **Sum** for the selected numeric cells.
+When you select a range in grid view, Teable shows **Average**, **Filled**, and **Sum** for numeric field values in the selected range.
 
 ### Hiding Fields in Grid View
 
diff --git a/zh/basic/admin-panel/ai-setting.mdx b/zh/basic/admin-panel/ai-setting.mdx
index f851c31..6654a0b 100644
--- a/zh/basic/admin-panel/ai-setting.mdx
+++ b/zh/basic/admin-panel/ai-setting.mdx
@@ -23,6 +23,7 @@ description: "为私有化部署实例配置 AI Chat、AI 字段、AI 自动化
 | **Vercel API 密钥** | 必需 | 用于 **AI 聊天运行环境** |
 | **Team / Project** | 必需 | 需要一个可用的 Team 和 Project；如果还没有，也可以在 Vercel 中创建 |
 | **AI Gateway API 密钥** | 使用 AI Gateway 时 | 只在选择 **AI Gateway** 作为模型服务商时需要 |
+| **OpenAI Realtime API Key** | 可选 | 只有需要在 AI 对话中启用 **语音输入** 时才需要 |
 | **公网访问** | 必需 | **Teable 实例** 和 **对象存储（MinIO / S3）** 需要被公网访问 |
 
 Vercel 相关费用主要分成两部分：
@@ -85,13 +86,19 @@ Vercel 相关费用主要分成两部分：
 
 这里应选择支持工具调用、并且已经过测试的稳定模型，否则 Agent 能力会明显受限。
 
+### 可选：配置语音输入
+
+**语音输入** 可以让用户在 AI 对话中用麦克风输入消息。
+
+你可以调整 **单次最长时长（秒）** 和 **每用户每分钟签发次数**。启用并保存语音输入后，用户会在 AI 对话输入框中看到麦克风按钮。
+
 ### 4. 配置运行环境与应用构建器
 
 先完成 **AI 聊天运行环境**，再完成 **应用构建器**。
 
 <Steps>
   <Step title="完成 AI 聊天运行环境">
-    在 **AI 聊天运行环境** 中，先填写并验证 **Vercel API 密钥**，再选择 **Team** 和 **Project**，最后点击 **测试连接**。测试通过后，右侧对应的待配置项会变绿。
+    在 **AI 聊天运行环境** 中，先填写并验证 **Vercel API 密钥**，再选择 **Team** 和 **Project**，点击 **保存**，然后点击 **测试连接**。配置测试通过后，右侧对应的待配置项会变绿。
   </Step>
   <Step title="完成应用构建器基础配置">
     在 **应用构建器** 中的 **Vercel 部署** 填写 **Vercel 访问令牌**。这是发布应用所需的核心配置。
@@ -142,7 +149,7 @@ Vercel 相关费用主要分成两部分：
 - **Team**
 - **Project**
 
-只填写 Token 还不够。
+只填写 Token 还不够。选择 **Team** 和 **Project** 后，需要先保存，再测试连接。
 </Accordion>
 
 <Accordion title="出现 credit exceeded 报错">
diff --git a/zh/basic/ai/ai-chat.mdx b/zh/basic/ai/ai-chat.mdx
index d349e04..d0371ab 100644
--- a/zh/basic/ai/ai-chat.mdx
+++ b/zh/basic/ai/ai-chat.mdx
@@ -26,6 +26,13 @@ AI 会优先参考你当前页面中的信息：
 
 较长的纯文本粘贴会转成 Markdown 附件，避免输入框被大段文本占满。文本和 Markdown 附件可从附件标签中打开预览。
 
+## 输入框控制项
+
+- **语音输入**：点击输入框中的麦克风按钮，允许使用麦克风后开始实时转写，再选择结束或丢弃本次语音输入。
+- **模型**：在模型菜单中选择本次对话使用的模型。简单查询、整理、改写可以选择较轻量的模型；复杂规划、跨表分析和应用构建适合选择更强的模型。
+- **智能**：在模型菜单中单独选择 **智能** 级别，用于控制 AI 的思考强度；级别越高，推理越深入。
+- **排队消息**：如果 AI 仍在工作时继续发送消息，新消息会进入队列。排队项会像输入框一样显示表格、视图、附件和选区标签。可以点击 **编辑** 把排队项移回输入框，点击 **中断并立即发送** 停止当前任务并发送该项，或点击 **移除** 从队列删除。
+
 ## 常见用法
 
 <CardGroup cols={2}>
@@ -110,5 +117,6 @@ AI 可以根据已经查询到的数据生成一次性的 HTML 预览，适合
 - **提供多样本示例**：需要固定格式输出时，可以提供 3-5 组输入 -> 期望输出示例。
 - **用 `@` 选择节点**：需要参考表格、视图、应用、自动化或文件夹时，直接输入 `@` 选择节点。
 - **先确认再执行**：会修改数据、创建表格、创建应用或启用自动化时，建议先让 AI 说明将要做哪些改动。
-- **按任务选择模型**：如果你的空间支持选择模型，简单查询、整理、改写可用较轻量的模型；复杂规划、跨表分析、应用构建再使用更强模型。
+- **按任务选择模型**：如果你的空间支持选择模型，简单查询、整理、改写可以使用较轻量的模型；复杂规划、跨表分析、应用构建再使用更强模型。
+- **调整智能级别**：**智能** 级别会影响 AI 的思考强度；级别越高，推理越深入。
 - **换主题时新开对话**：话题变化、对话太长，或想减少上下文消耗时，建议新开一个对话。
diff --git a/zh/basic/view/grid.mdx b/zh/basic/view/grid.mdx
index 520a618..0db92b3 100644
--- a/zh/basic/view/grid.mdx
+++ b/zh/basic/view/grid.mdx
@@ -31,7 +31,7 @@ description: "表格视图是 Teable 中的一种数据展示方式，它以表
 
 ### 3. 选区统计
 
-选区时，Teable 会显示数值的 **平均值**、**计数** 和 **总和**。
+选区时，Teable 会显示数值字段的 **平均值**、**已填写** 和 **求和**。
 
 ## 三、 交互