fix: pipe language out of Voice Design into Generate

Voice Design now outputs (instruct, language) — wire language directly
into Generate to avoid setting it in two places. Generate's language
input is now a STRING (accepts the connection or manual 'auto').

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

nodes/generator.py

@@ -62,18 +62,13 @@ class OmniVoiceGenerate:
                     "default": "",
                     "tooltip": "Transcription of ref_audio. Connect a Whisper (or other STT) node for best results.",
                 }),
-                "language": (
-                    ["auto", "English", "Chinese"],
-                    {
-                        "default": "auto",
-                        "tooltip": (
-                            "Used in voice_design mode to select the instruct vocabulary.\n"
-                            "'English' uses English instruct items (male, female, british accent …)\n"
-                            "'Chinese' uses Chinese dialect items (男, 女, 四川话, 东北话 …)\n"
-                            "Has no effect in voice_cloning mode (language is inferred from text)."
-                        ),
-                    },
-                ),
+                "language": ("STRING", {
+                    "default": "auto",
+                    "tooltip": (
+                        "Connect the 'language' output from OmniVoice Voice Design — it sets this automatically.\n"
+                        "Only needed in voice_design/auto_voice mode. Leave 'auto' for voice_cloning."
+                    ),
+                }),
                 "instruct": ("STRING", {
                     "default": "",
                     "tooltip": (

nodes/voice_design.py

@@ -39,7 +39,7 @@ class OmniVoiceVoiceDesign:
                     ["English", "Chinese"],
                     {
                         "default": "English",
-                        "tooltip": "Selects the instruct vocabulary. Must match the language set in OmniVoice Generate.",
+                        "tooltip": "Selects the instruct vocabulary. The language output wires directly into Generate — no need to set it there too.",
                     },
                 ),
                 "gender": (cls.GENDERS, {"default": "female",
@@ -59,8 +59,8 @@ class OmniVoiceVoiceDesign:
             },
         }
 
-    RETURN_TYPES  = ("STRING",)
-    RETURN_NAMES  = ("instruct",)
+    RETURN_TYPES  = ("STRING", "STRING")
+    RETURN_NAMES  = ("instruct", "language")
     FUNCTION      = "compose"
     CATEGORY      = "OmniVoice"
 
@@ -68,7 +68,7 @@ class OmniVoiceVoiceDesign:
                 zh_gender="none", zh_age="none", zh_pitch="none", zh_dialect="none"):
         if language == "Chinese":
             parts = [v for v in [zh_gender, zh_age, zh_pitch, zh_dialect] if v != "none"]
-            return ("，".join(parts),)
+            return ("，".join(parts), "Chinese")
         else:
             parts = [v for v in [gender, age, pitch, accent] if v != "none"]
-            return (", ".join(parts),)
+            return (", ".join(parts), "English")