diff --git a/README.md b/README.md
index 9e0fa8b..001eea5 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 <div align="center">
 
-[![Version](https://img.shields.io/badge/version-3.0.1-blue.svg)](https://github.com/asyouplz/SpeechNote/releases)
+[![Version](https://img.shields.io/badge/version-3.0.4-blue.svg)](https://github.com/asyouplz/SpeechNote/releases)
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 [![Obsidian](https://img.shields.io/badge/obsidian-%3E%3D0.15.0-purple.svg)](https://obsidian.md)
 [![OpenAI](https://img.shields.io/badge/OpenAI-Whisper%20API-orange.svg)](https://platform.openai.com/docs/guides/speech-to-text)
@@ -473,7 +473,12 @@ If this project helped you:
 
 ## Recent Updates
 
-### 🚀 v3.0.1 (Latest) - Enterprise Architecture & Performance
+### 🚀 v3.0.4 (Latest) - Settings Stability & Deepgram Cleanup
+- 🛠️ **Settings Stability**: Improves plugin settings reliability
+- 🧹 **Deepgram Refactor**: Cleanup and refactor for provider integration
+- 🧩 **General Fixes**: Minor bug fixes and improvements
+
+### v3.0.1 - Enterprise Architecture & Performance
 - 🏗️ **Clean Architecture**: Domain-driven design with clear separation of concerns
 - 🎯 **Modular Structure**: Organized into application, core, domain, infrastructure layers
 - ⚡ **Performance Monitoring**: Built-in performance benchmarking and memory management
@@ -954,7 +959,12 @@ SpeechNote/
 
 ## 최근 업데이트
 
-### 🚀 v3.0.1 (최신) - 엔터프라이즈 아키텍처 및 성능
+### 🚀 v3.0.4 (최신) - 설정 안정화 및 Deepgram 정리
+- 🛠️ **설정 안정화**: 플러그인 설정 신뢰성 개선
+- 🧹 **Deepgram 리팩터링**: 공급자 통합 구조 정리
+- 🧩 **기타 수정**: 소소한 버그 수정 및 개선
+
+### v3.0.1 - 엔터프라이즈 아키텍처 및 성능
 - 🏗️ **클린 아키텍처**: 관심사 분리를 갖춘 도메인 주도 설계
 - 🎯 **모듈식 구조**: application, core, domain, infrastructure 레이어로 구성
 - ⚡ **성능 모니터링**: 내장 성능 벤치마킹 및 메모리 관리
diff --git a/manifest.json b/manifest.json
index 6f24129..d0fbe73 100644
--- a/manifest.json
+++ b/manifest.json
@@ -1,7 +1,7 @@
 {
 	"id": "speech-to-text",
 	"name": "Speech to Text",
-	"version": "3.0.3",
+	"version": "3.0.4",
 	"minAppVersion": "0.15.0",
 	"description": "Convert audio recordings to text using multiple AI providers (OpenAI Whisper, Deepgram)",
 	"author": "Taesun Lee",
diff --git a/package-lock.json b/package-lock.json
index 841a66a..a5383e2 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
 {
   "name": "obsidian-speech-to-text",
-  "version": "3.0.3",
+  "version": "3.0.4",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "obsidian-speech-to-text",
-      "version": "3.0.3",
+      "version": "3.0.4",
       "license": "MIT",
       "dependencies": {
         "@deepgram/sdk": "^3.9.0"
diff --git a/package.json b/package.json
index a4293f3..88d534c 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "obsidian-speech-to-text",
-  "version": "3.0.3",
+  "version": "3.0.4",
   "description": "Convert audio recordings to text in Obsidian using multiple AI providers (OpenAI Whisper, Deepgram)",
   "main": "main.js",
   "scripts": {
diff --git a/versions.json b/versions.json
index dbbb9c6..1901585 100644
--- a/versions.json
+++ b/versions.json
@@ -4,5 +4,6 @@
 	"3.0.0": "0.15.0",
 	"3.0.1": "0.15.0",
 	"3.0.2": "0.15.0",
-	"3.0.3": "0.15.0"
+	"3.0.3": "0.15.0",
+	"3.0.4": "0.15.0"
 }
\ No newline at end of file