Implement StepFun Realtime service and enhance AssistantConfig

- Add new fields to AssistantConfig for realtime interface configuration, including types, values, and secrets.
- Introduce StepFunRealtimeService to handle speech-to-speech processing via WebSocket, integrating STT, LLM, and TTS functionalities.
- Refactor pipeline execution to support a new realtime mode, allowing direct text input processing and immediate responses.
- Update model resource testing to include validation for StepFun Realtime connections.
- Enhance service factory to create realtime services based on configuration settings.
- Modify README documentation to reflect new realtime capabilities and usage instructions.

backend/services/interface_catalog.py

@@ -78,6 +78,25 @@ INTERFACE_DEFINITIONS: list[dict] = [
         "capability": "Realtime",
         "fields": OPENAI_COMMON + [field("voice", "Voice")],
     },
+    {
+        "interface_type": "stepfun-realtime",
+        "name": "StepFun StepAudio Realtime",
+        "capability": "Realtime",
+        "fields": OPENAI_COMMON
+        + [
+            field("voice", "Voice", required=True, default="linjiajiejie"),
+            field("inputSampleRate", "Input Sample Rate", type_="number", default=24000),
+            field("outputSampleRate", "Output Sample Rate", type_="number", default=24000),
+            field("prefixPaddingMs", "VAD Prefix Padding (ms)", type_="number", default=500),
+            field("silenceDurationMs", "VAD Silence Duration (ms)", type_="number", default=300),
+            field(
+                "energyAwakenessThreshold",
+                "VAD Energy Threshold",
+                type_="number",
+                default=2500,
+            ),
+        ],
+    },
     {
         "interface_type": "xfyun-asr",
         "name": "Xfyun Streaming ASR",