feat: 视频调速引擎（快进/慢放） (#294)

apps/worker/video_processing/unified_render_service.py

@@ -45,6 +45,7 @@ from video_processing.pip_engine import PiPConfig, PiPEngine, PiPLayerConfig
 from video_processing.render_audio import RenderContext, merge_audio_video, mix_audio
 from video_processing.render_subtitles import generate_ass_subtitles
 from video_processing.reverse_engine import ReverseConfig, ReverseEngine
+from video_processing.speed_engine import SpeedConfig, SpeedEngine
 from video_processing.sticker_engine import StickerEngine, parse_stickers_from_config
 from video_processing.subtitle_generator import generate_ass_from_timeline
 from video_processing.transition_engine import TransitionEngine
@@ -73,6 +74,7 @@ class ResolvedClip:
     duration: float = 0.0  # 0 表示使用素材完整时长
     transition_effect: str = "cut"
     transition_duration: float = 0.0  # 0 表示使用全局默认值
+    playback_speed: float = 1.0  # 0 或 1.0 表示原速
     config: dict[str, Any] = field(default_factory=dict)
 
     # 运行时填充
@@ -186,6 +188,7 @@ class UnifiedRenderService:
         self.asr_service = asr_service
         self.bgm_path = bgm_path
         self._transition_engine = TransitionEngine(default_duration=transition_duration)
+        self._speed_engine = SpeedEngine()
 
     def render(self) -> RenderResult:
         """执行渲染，返回 RenderResult.
@@ -493,7 +496,7 @@ class UnifiedRenderService:
         if not main_layer or not main_layer.clips:
             return 0.0
 
-        total = sum(UnifiedRenderService._clip_effective_duration(c) for c in main_layer.clips)
+        total = sum(UnifiedRenderService._clip_adjusted_duration(c) for c in main_layer.clips)
 
         # 减去转场重叠时间（粗略估算）
         n_clips = len(main_layer.clips)
@@ -1197,6 +1200,7 @@ class UnifiedRenderService:
                 duration=final_duration,
                 transition_effect=clip.transition_effect or "cut",
                 transition_duration=getattr(clip, "transition_duration", 0.0) or 0.0,
+                playback_speed=getattr(clip, "playback_speed", 1.0) or 1.0,
                 config=clip_config,
                 actual_duration=actual_duration,
                 trim_config=effective_trim,
@@ -1294,6 +1298,11 @@ class UnifiedRenderService:
                     filters.append(f"trim=duration={effective_duration:.3f}")
                 filters.append("setpts=PTS-STARTPTS")
 
+            # 调速 — 基于 setpts 改变播放速度
+            speed = UnifiedRenderService._clip_speed(clip)
+            if abs(speed - 1.0) >= 1e-6:
+                filters.append(f"setpts=PTS/{speed:.4f}")
+
             # 倒放滤镜（在 trim 之后、scale 之前应用）
             reverse_config = ReverseConfig.from_dict(clip.config.get("reverse"))
             if reverse_config.enabled and reverse_config.reverse_video:
@@ -1351,8 +1360,8 @@ class UnifiedRenderService:
         for layer in layers:
             layer_clip_indices = [all_clips.index(c) for c in layer.clips]
             layer_labels = [preprocessed_labels[i] for i in layer_clip_indices]
-            # 使用 trim 后的有效时长，与 Step 1 的 trim=duration 保持一致
-            layer_durations = [UnifiedRenderService._clip_effective_duration(all_clips[i]) for i in layer_clip_indices]
+            # 使用调速后的实际时长，与 Step 1 的调速处理保持一致
+            layer_durations = [UnifiedRenderService._clip_adjusted_duration(all_clips[i]) for i in layer_clip_indices]
             layer_transitions = [all_clips[i].transition_effect for i in layer_clip_indices]
             layer_transition_durations = [all_clips[i].transition_duration for i in layer_clip_indices]
 
@@ -1597,7 +1606,7 @@ class UnifiedRenderService:
 
     @staticmethod
     def _clip_effective_duration(clip: ResolvedClip) -> float:
-        """计算 clip 的有效时长."""
+        """计算 clip 的有效时长（原速 trim 后时长）."""
         if clip.duration > 0:
             return min(clip.duration, clip.actual_duration) if clip.actual_duration > 0 else clip.duration
         return clip.actual_duration if clip.actual_duration > 0 else 0.0
@@ -1694,3 +1703,20 @@ class UnifiedRenderService:
         )
 
         return new_filter, new_input_args
+
+    @staticmethod
+    def _clip_speed(clip: ResolvedClip) -> float:
+        """获取 clip 的播放速度，无效值回退到 1.0."""
+        speed = getattr(clip, "playback_speed", 1.0)
+        if not isinstance(speed, (int, float)) or speed <= 0:
+            return 1.0
+        return float(speed)
+
+    @staticmethod
+    def _clip_adjusted_duration(clip: ResolvedClip) -> float:
+        """计算调速后的 clip 实际时长（用于拼接计算）."""
+        base = UnifiedRenderService._clip_effective_duration(clip)
+        speed = UnifiedRenderService._clip_speed(clip)
+        if abs(speed - 1.0) < 1e-6:
+            return base
+        return base / speed