diff --git a/xinference/model/audio/model_spec.json b/xinference/model/audio/model_spec.json
index 6762d84a18..bf51b3da3a 100644
--- a/xinference/model/audio/model_spec.json
+++ b/xinference/model/audio/model_spec.json
@@ -71,6 +71,14 @@
     "model_ability": "audio-to-text",
     "multilingual": true
   },
+  {
+    "model_name": "whisper-large-v3-turbo",
+    "model_family": "whisper",
+    "model_id": "openai/whisper-large-v3-turbo",
+    "model_revision": "41f01f3fe87f28c78e2fbf8b568835947dd65ed9",
+    "model_ability": "audio-to-text",
+    "multilingual": true
+  },
   {
     "model_name": "Belle-distilwhisper-large-v2-zh",
     "model_family": "whisper",
diff --git a/xinference/model/audio/model_spec_modelscope.json b/xinference/model/audio/model_spec_modelscope.json
index df0c2a3af8..e3f46f84bc 100644
--- a/xinference/model/audio/model_spec_modelscope.json
+++ b/xinference/model/audio/model_spec_modelscope.json
@@ -8,6 +8,15 @@
     "model_ability": "audio-to-text",
     "multilingual": true
   },
+  {
+    "model_name": "whisper-large-v3-turbo",
+    "model_family": "whisper",
+    "model_hub": "modelscope",
+    "model_id": "AI-ModelScope/whisper-large-v3-turbo",
+    "model_revision": "master",
+    "model_ability": "audio-to-text",
+    "multilingual": true
+  },
   {
     "model_name": "SenseVoiceSmall",
     "model_family": "funasr",