diff --git a/funclip/videoclipper.py b/funclip/videoclipper.py
index 8655940..fc28368 100644
--- a/funclip/videoclipper.py
+++ b/funclip/videoclipper.py
@@ -221,6 +221,7 @@ def clip(self, dest_text, start_ost, end_ost, state, dest_spk=None, output_dir=N
         ts = all_ts
         # ts.sort()
         srt_index = 0
+        time_acc_ost = 0.0
         clip_srt = ""
         if len(ts):
             start, end = ts[0]
@@ -228,16 +229,30 @@ def clip(self, dest_text, start_ost, end_ost, state, dest_spk=None, output_dir=N
             end = min(max(0, end+end_ost*16), len(data))
             res_audio = data[start:end]
             start_end_info = "from {} to {}".format(start/16000, end/16000)
-            srt_clip, _, srt_index = generate_srt_clip(sentences, start/16000.0, end/16000.0, begin_index=srt_index)
+            srt_clip, _, srt_index = generate_srt_clip(
+                sentences,
+                start/16000.0,
+                end/16000.0,
+                begin_index=srt_index,
+                time_acc_ost=time_acc_ost,
+            )
             clip_srt += srt_clip
+            time_acc_ost += (end - start) / 16000.0
             for _ts in ts[1:]:  # multiple sentence input or multiple output matched
                 start, end = _ts
                 start = min(max(0, start+start_ost*16), len(data))
                 end = min(max(0, end+end_ost*16), len(data))
                 start_end_info += ", from {} to {}".format(start, end)
                 res_audio = np.concatenate([res_audio, data[start:end]], -1)
-                srt_clip, _, srt_index = generate_srt_clip(sentences, start/16000.0, end/16000.0, begin_index=srt_index-1)
+                srt_clip, _, srt_index = generate_srt_clip(
+                    sentences,
+                    start/16000.0,
+                    end/16000.0,
+                    begin_index=srt_index-1,
+                    time_acc_ost=time_acc_ost,
+                )
                 clip_srt += srt_clip
+                time_acc_ost += (end - start) / 16000.0
         if len(ts):
             message = "{} periods found in the speech: ".format(len(ts)) + start_end_info + log_append
         else:
@@ -284,8 +299,8 @@ def video_clip(self,
                    state, 
                    font_size=32, 
                    font_color='white', 
-                   add_sub=False, 
-                   dest_spk=None, 
+                   add_sub=False,
+                   dest_spk=None,
                    output_dir=None,
                    timestamp_list=None):
         # get from state
@@ -567,4 +582,4 @@ def main(cmd=None):
 
 
 if __name__ == '__main__':
-    main()
+    main()
\ No newline at end of file
diff --git a/tests/test_audio_clip_srt_timeline.py b/tests/test_audio_clip_srt_timeline.py
new file mode 100644
index 0000000..f38d332
--- /dev/null
+++ b/tests/test_audio_clip_srt_timeline.py
@@ -0,0 +1,48 @@
+import copy
+import sys
+from pathlib import Path
+
+import numpy as np
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "funclip"))
+
+from videoclipper import VideoClipper
+
+
+def _state():
+    sentences = [
+        {"text": "hello", "timestamp": [[1000, 2000]], "spk": 0},
+        {"text": "world", "timestamp": [[4000, 5000]], "spk": 0},
+    ]
+    return {
+        "audio_input": (16000, np.zeros(96000)),
+        "recog_res_raw": "hello world",
+        "timestamp": [[1000, 2000], [4000, 5000]],
+        "sentences": sentences,
+        "sd_sentences": copy.deepcopy(sentences),
+    }
+
+
+def test_concatenated_audio_subtitles_accumulate_output_time():
+    clipper = VideoClipper(None)
+
+    (rate, audio), _, subtitles = clipper.clip(
+        "hello#world", 0, 0, copy.deepcopy(_state())
+    )
+
+    assert rate == 16000
+    assert len(audio) == 32000
+    assert "00:00:00,000 --> 00:00:01,000" in subtitles
+    assert "00:00:01,000 --> 00:00:02,000" in subtitles
+
+
+def test_explicit_timestamp_list_uses_same_accumulated_timeline():
+    clipper = VideoClipper(None)
+
+    (_, audio), _, subtitles = clipper.clip(
+        "", 0, 0, copy.deepcopy(_state()),
+        timestamp_list=[[16000, 32000], [64000, 80000]],
+    )
+
+    assert len(audio) == 32000
+    assert "00:00:01,000 --> 00:00:02,000" in subtitles