diff --git a/backend/app/core/config.py b/backend/app/core/config.py
index 735692a..809655e 100644
--- a/backend/app/core/config.py
+++ b/backend/app/core/config.py
@@ -222,7 +222,7 @@ class Settings(BaseSettings):
     # Gemini TTS Model Options
     gemini_tts_models: dict[str, str] = {
         "flash": "gemini-3.1-flash-tts-preview",  # Fast, cost-efficient
-        "pro": "gemini-2.5-pro-preview-tts",      # Higher quality
+        "pro": "gemini-3.1-pro-tts-preview",       # Higher quality
     }
 
     # Gemini TTS Style Presets - prompts prepended to text for style control
diff --git a/backend/app/services/gemini.py b/backend/app/services/gemini.py
index fbb42a1..20aaa10 100644
--- a/backend/app/services/gemini.py
+++ b/backend/app/services/gemini.py
@@ -45,7 +45,7 @@ async def _record_gemini_usage(
 
 class GeminiService:
     def __init__(self):
-        self.model_name = 'gemini-3-pro-preview'  # Gemini 3 Pro preview model
+        self.model_name = 'gemini-3.1-pro-preview'
         self.prompts_dir = Path(__file__).parent.parent / "prompts"
 
     def _load_prompt(self, prompt_file: str) -> str:
diff --git a/backend/app/tasks/tts_synthesis.py b/backend/app/tasks/tts_synthesis.py
index 0f97320..bd76b4f 100644
--- a/backend/app/tasks/tts_synthesis.py
+++ b/backend/app/tasks/tts_synthesis.py
@@ -32,7 +32,7 @@ _TTS_PROVIDER_MODEL_MAP = {
 
 _TTS_MODEL_STRINGS = {
     "flash": "gemini-3.1-flash-tts-preview",
-    "pro": "gemini-2.5-pro-preview-tts",
+    "pro": "gemini-3.1-pro-tts-preview",
     "standard": "standard",
     "wavenet": "wavenet",
     "neural2": "neural2",