feat: 水印 + 片头片尾引擎（视频包装能力） (#298)

apps/worker/video_processing/render_audio.py

@@ -175,6 +175,7 @@ def concat_main_audio(
         # 单 clip，直接提取音频，截断到 min(clip有效时长, 视频总时长)
         clip = clips[0]
         effective_duration = clip_effective_duration(clip)
+        trim_start = getattr(clip, "start_time", 0) or 0
         # 最终时长：取 clip 有效时长和视频总时长的较小值
         # （视频总时长由主图层决定，但单 clip 场景下两者应该一致，仍做保护）
         final_duration = effective_duration
@@ -192,6 +193,8 @@ def concat_main_audio(
             "-b:a",
             "128k",
         ]
+        if trim_start > 0:
+            command.extend(["-ss", f"{trim_start:.3f}"])
         if final_duration > 0:
             command.extend(["-t", f"{final_duration:.3f}"])
         command.append(str(output_path))
@@ -205,8 +208,11 @@ def concat_main_audio(
     for i, clip in enumerate(clips):
         input_args.extend(["-i", str(clip.local_path)])
         effective_duration = clip_effective_duration(clip)
+        trim_start = getattr(clip, "start_time", 0) or 0
         if effective_duration > 0:
-            filter_parts.append(f"[{i}:a]atrim=0:{effective_duration:.3f},asetpts=PTS-STARTPTS[a{i}]")
+            filter_parts.append(
+                f"[{i}:a]atrim=start={trim_start:.3f}:duration={effective_duration:.3f}," f"asetpts=PTS-STARTPTS[a{i}]"
+            )
         else:
             filter_parts.append(f"[{i}:a]asetpts=PTS-STARTPTS[a{i}]")
 
@@ -266,9 +272,11 @@ def mix_with_independent_audio(
         for clip in main_clips:
             input_args.extend(["-i", str(clip.local_path)])
             effective_duration = clip_effective_duration(clip)
+            trim_start = getattr(clip, "start_time", 0) or 0
             if effective_duration > 0:
                 filter_parts.append(
-                    f"[{input_idx}:a]atrim=0:{effective_duration:.3f},asetpts=PTS-STARTPTS[ma{input_idx}]"
+                    f"[{input_idx}:a]atrim=start={trim_start:.3f}:duration={effective_duration:.3f},"
+                    f"asetpts=PTS-STARTPTS[ma{input_idx}]"
                 )
             else:
                 filter_parts.append(f"[{input_idx}:a]asetpts=PTS-STARTPTS[ma{input_idx}]")
@@ -285,11 +293,12 @@ def mix_with_independent_audio(
     for j, clip in enumerate(audio_clips):
         input_args.extend(["-i", str(clip.local_path)])
         effective_duration = clip_effective_duration(clip)
+        trim_start = getattr(clip, "start_time", 0) or 0
         volume = clip.config.get("volume", 1.0) if clip.config else 1.0
         label = f"ia{j}"
         filters = []
         if effective_duration > 0:
-            filters.append(f"atrim=0:{effective_duration:.3f}")
+            filters.append(f"atrim=start={trim_start:.3f}:duration={effective_duration:.3f}")
         filters.append("asetpts=PTS-STARTPTS")
         if volume != 1.0:
             filters.append(f"volume={volume}")