Add tts/text output schema

api/app/routers/assistants.py

@@ -21,6 +21,7 @@ def _resolve_runtime_metadata(db: Session, assistant: Assistant) -> dict:
     metadata = {
         "systemPrompt": assistant.prompt or "",
         "greeting": assistant.opener or "",
+        "output": {"mode": "audio" if assistant.voice_output_enabled else "text"},
         "services": {},
     }
     warnings = []
@@ -49,11 +50,14 @@ def _resolve_runtime_metadata(db: Session, assistant: Assistant) -> dict:
         else:
             warnings.append(f"ASR model not found: {assistant.asr_model_id}")
 
-    if assistant.voice:
+    if not assistant.voice_output_enabled:
+        metadata["services"]["tts"] = {"enabled": False}
+    elif assistant.voice:
         voice = db.query(Voice).filter(Voice.id == assistant.voice).first()
         if voice:
             tts_provider = "siliconflow" if _is_siliconflow_vendor(voice.vendor) else "edge"
             metadata["services"]["tts"] = {
+                "enabled": True,
                 "provider": tts_provider,
                 "model": voice.model,
                 "apiKey": voice.api_key if tts_provider == "siliconflow" else None,
@@ -63,6 +67,7 @@ def _resolve_runtime_metadata(db: Session, assistant: Assistant) -> dict:
         else:
             # Keep assistant.voice as direct voice identifier fallback
             metadata["services"]["tts"] = {
+                "enabled": True,
                 "voice": assistant.voice,
                 "speed": assistant.speed or 1.0,
             }
@@ -98,6 +103,7 @@ def assistant_to_dict(assistant: Assistant) -> dict:
         "prompt": assistant.prompt or "",
         "knowledgeBaseId": assistant.knowledge_base_id,
         "language": assistant.language,
+        "voiceOutputEnabled": assistant.voice_output_enabled,
         "voice": assistant.voice,
         "speed": assistant.speed,
         "hotwords": assistant.hotwords or [],
@@ -120,6 +126,7 @@ def _apply_assistant_update(assistant: Assistant, update_data: dict) -> None:
         "knowledgeBaseId": "knowledge_base_id",
         "interruptionSensitivity": "interruption_sensitivity",
         "configMode": "config_mode",
+        "voiceOutputEnabled": "voice_output_enabled",
         "apiUrl": "api_url",
         "apiKey": "api_key",
         "llmModelId": "llm_model_id",
@@ -180,6 +187,7 @@ def create_assistant(data: AssistantCreate, db: Session = Depends(get_db)):
         prompt=data.prompt,
         knowledge_base_id=data.knowledgeBaseId,
         language=data.language,
+        voice_output_enabled=data.voiceOutputEnabled,
         voice=data.voice,
         speed=data.speed,
         hotwords=data.hotwords,