add_audio_effect
Apply audio effects like scene sounds, tone modifications, or speech-to-song conversion to audio segments in video editing workflows.
Instructions
为音频片段添加特效
Args: audio_segment_id: 音频片段ID，通过add_audio_segment获得 effect_type: 特效类型，支持以下类型： - "AudioSceneEffectType": 场景音效（如雨声、风声等） - "ToneEffectType": 音调特效（如机器人、电音等） - "SpeechToSongType": 语音转歌声特效（如Lofi、流行等） effect_name: 特效名称，如 "雨声", "机器人", "Lofi", "电音", "回声" 等，可以使用find_effects_by_type工具，资源类型选择AudioSceneEffectType、ToneEffectType、SpeechToSongType，从而获取特效类型有哪些 params: 特效参数列表（可选），参数范围0-100，具体参数数量和含义取决于特效类型，一般不做修改
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| audio_segment_id | Yes | ||
| effect_type | Yes | ||
| effect_name | Yes | ||
| params | No |
Implementation Reference
- jianyingdraft/tool/audio_tool.py:103-205 (handler)Main MCP tool handler for 'add_audio_effect'. Decorated with @mcp.tool(), performs input validation, effect existence check using JianYingResourceManager, retrieves draft and track info from index_manager, and invokes the service layer.@mcp.tool() def add_audio_effect( audio_segment_id: str, effect_type: str, effect_name: str, params: Optional[List[Optional[float]]] = None ) -> ToolResponse: """ 为音频片段添加特效 Args: audio_segment_id: 音频片段ID，通过add_audio_segment获得 effect_type: 特效类型，支持以下类型： - "AudioSceneEffectType": 场景音效（如雨声、风声等） - "ToneEffectType": 音调特效（如机器人、电音等） - "SpeechToSongType": 语音转歌声特效（如Lofi、流行等） effect_name: 特效名称，如 "雨声", "机器人", "Lofi", "电音", "回声" 等，可以使用find_effects_by_type工具，资源类型选择AudioSceneEffectType、ToneEffectType、SpeechToSongType，从而获取特效类型有哪些 params: 特效参数列表（可选），参数范围0-100，具体参数数量和含义取决于特效类型，一般不做修改 """ # 参数验证 valid_types = ["AudioSceneEffectType", "ToneEffectType", "SpeechToSongType"] if effect_type not in valid_types: return ToolResponse( success=False, message=f"无效的特效类型 '{effect_type}'，支持的类型: {', '.join(valid_types)}" ) # 验证参数范围 if params: for i, param in enumerate(params): if param is not None and not (0.0 <= param <= 100.0): return ToolResponse( success=False, message=f"参数{i + 1}超出范围，必须在0-100之间，当前值: {param}" ) # 音频特效存在性验证（音频特效使用 name 字段） from jianyingdraft.utils.effect_manager import JianYingResourceManager manager = JianYingResourceManager() effects = manager.find_by_type( effect_type=effect_type, keyword=effect_name, limit=1 ) # 检查是否找到完全匹配的特效 exact_match = False if effects: for effect in effects: if effect.get('name') == effect_name: exact_match = True break if not effects or not exact_match: # 获取建议特效 effect_suggestions = manager.find_by_type(effect_type, keyword=effect_name) all_suggestions = [] for effect in effect_suggestions: if effect.get('name'): all_suggestions.append(effect.get('name')) return ToolResponse( success=False, message=f"在 {effect_type} 中未找到特效 '{effect_name}',请确认名称是否正确，或使用相关特效: {', '.join(all_suggestions)}", data={ "error_type": "effect_not_found", "effect_type": effect_type, "effect_name": effect_name, "suggestions": all_suggestions } ) # 通过audio_segment_id获取相关信息 draft_id = index_manager.get_draft_id_by_audio_segment_id(audio_segment_id) track_info = index_manager.get_track_info_by_audio_segment_id(audio_segment_id) if not draft_id: return ToolResponse( success=False, message=f"未找到音频片段ID对应的草稿: {audio_segment_id}" ) if not track_info: return ToolResponse( success=False, message=f"未找到音频片段ID对应的轨道信息: {audio_segment_id}" ) track_name = track_info.get("track_name") # 调用服务层处理业务逻辑 result = add_audio_effect_service( draft_id=draft_id, audio_segment_id=audio_segment_id, effect_type=effect_type, effect_name=effect_name, params=params, track_name=track_name ) return result
- Service layer helper function 'add_audio_effect_service' that creates an AudioSegment instance and calls its add_effect method to apply the specified audio effect to the segment.def add_audio_effect_service( draft_id: str, audio_segment_id: str, effect_type: str, effect_name: str, params: Optional[List[Optional[float]]] = None, track_name: Optional[str] = None ) -> ToolResponse: """ 音频特效添加服务 - 为音频片段添加特效 Args: draft_id: 草稿ID audio_segment_id: 音频片段ID effect_type: 特效类型，"AudioSceneEffectType"、"ToneEffectType"、"SpeechToSongType" effect_name: 特效名称，如 "雨声"、"机器人"、"Lofi" 等 params: 特效参数列表（可选），参数范围0-100 track_name: 轨道名称（可选） Returns: ToolResponse: 包含操作结果的响应对象 """ try: # 创建AudioSegment实例，传入audio_segment_id audio_segment = AudioSegment(draft_id, audio_segment_id=audio_segment_id, track_name=track_name) # 调用音频特效添加方法 result_data = audio_segment.add_effect( effect_type=effect_type, effect_name=effect_name, params=params ) # 构建返回数据 response_data = { "audio_segment_id": audio_segment_id, "draft_id": draft_id, "effect_type": effect_type, "effect_name": effect_name, "add_effect": result_data } # 添加可选参数到返回数据 if params: response_data["params"] = params if track_name: response_data["track_name"] = track_name return ToolResponse( success=True, message=f"音频特效添加成功: {effect_type}.{effect_name}", data=response_data )
- jianyingdraft/server.py:30-30 (registration)Registration of the audio tools module, which includes 'add_audio_effect', by calling audio_tools(mcp) in the main server setup.audio_tools(mcp)
- jianyingdraft/server.py:20-20 (registration)Import of audio_tools function used for registering the audio tools including 'add_audio_effect'.from jianyingdraft.tool.audio_tool import audio_tools