diff --git a/comfy_api/latest/_input_impl/video_types.py b/comfy_api/latest/_input_impl/video_types.py
index 9f498a6bb..09db94198 100644
--- a/comfy_api/latest/_input_impl/video_types.py
+++ b/comfy_api/latest/_input_impl/video_types.py
@@ -707,13 +707,17 @@ class VideoFromFile(VideoInput):
 
                 elif packet.stream == audio_stream and not audio_done:
                     for resampled in itertools.chain.from_iterable(map(resampler.resample, packet.decode())):
+                        frame_start = None
+                        if resampled.pts is not None:
+                            # passthrough frames keep the source stream's time base
+                            tb = resampled.time_base if resampled.time_base else audio_time_base
+                            frame_start = float(resampled.pts * tb)
+                            if duration and not audio_started and frame_start >= start_time + duration:
+                                audio_done = True
+                                break
                         if not audio_started:
-                            if resampled.pts is None:
+                            if frame_start is None:
                                 frame_start = 0.0
-                            else:
-                                # passthrough frames keep the source stream's time base
-                                tb = resampled.time_base if resampled.time_base else audio_time_base
-                                frame_start = float(resampled.pts * tb)
                             to_skip = max(0, int((start_time - frame_start) * sample_rate))
                             if to_skip >= resampled.samples:
                                 continue
diff --git a/tests-unit/comfy_api_test/video_types_test.py b/tests-unit/comfy_api_test/video_types_test.py
index 9d78b28b3..3dc7055f6 100644
--- a/tests-unit/comfy_api_test/video_types_test.py
+++ b/tests-unit/comfy_api_test/video_types_test.py
@@ -481,6 +481,12 @@ def test_save_to_transcode_learns_unprobed_audio_params():
     assert result["audio_codecs"] == ["aac"]
     assert result["audio_seconds"] == pytest.approx(1.0, abs=0.1)
 
+    buffer.seek(0)
+    trimmed_before_audio = transcode_and_probe(VideoFromFile(buffer, duration=1))
+    assert trimmed_before_audio["frames"] == fps
+    assert trimmed_before_audio["audio_codecs"] == []
+    assert trimmed_before_audio["audio_seconds"] is None
+
 
 def test_save_to_transcode_trimmed_fragmented_mp4_keeps_audio():
     """Fragmented mp4 (MediaRecorder, DASH/HLS-derived files) delivers audio well behind