Skip to content

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

fix(audio_mixer): drop dangling speech_dup pad in full_mix ducking

0xDevNinjafebc9244d3bb
diff --git a/tests/tools/test_audio_mixer_ducking.py b/tests/tools/test_audio_mixer_ducking.py
new file mode 100644
index 00000000..ec060e81
--- /dev/null
+++ b/tests/tools/test_audio_mixer_ducking.py
@@ -0,0 +1,89 @@
+"""Regression tests for audio_mixer full_mix ducking filtergraph.
+
+The ducking branch built an `acopy[speech_dup]` filter whose output pad was
+never consumed, leaving the FFmpeg filtergraph with a dangling output. FFmpeg
+rejects that, so `full_mix` with the most common shape — a single narration
+track plus one music bed, with ducking enabled (the default) — always failed.
+"""
+
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
+sys.path.insert(0, str(PROJECT_ROOT))
+
+from tools.audio.audio_mixer import AudioMixer # noqa: E402
+
+pytestmark = pytest.mark.skipif(
+ shutil.which("ffmpeg") is None, reason="ffmpeg required for full_mix"
+)
+
+
+def _sine(path: Path, freq: int, dur: int) -> None:
+ subprocess.run(
+ ["ffmpeg", "-y", "-f", "lavfi", "-i", f"sine=frequency={freq}:duration={dur}", str(path)],
+ capture_output=True,
+ check=True,
+ timeout=30,
+ )
+
+
+def _has_audio(path: Path) -> bool:
+ out = subprocess.run(
+ ["ffprobe", "-v", "error", "-select_streams", "a",
+ "-show_entries", "stream=codec_type", "-of", "csv=p=0", str(path)],
+ capture_output=True, text=True, timeout=30,
+ )
+ return "audio" in out.stdout
+
+
+def test_full_mix_single_narration_plus_music_with_ducking(tmp_path):
+ speech = tmp_path / "speech.wav"
+ music = tmp_path / "music.wav"
+ _sine(speech, 440, 2)
+ _sine(music, 220, 3)
+ out = tmp_path / "mixed.wav"
+
+ result = AudioMixer().execute(
+ {
+ "operation": "full_mix",
+ "tracks": [
+ {"path": str(speech), "role": "speech"},
+ {"path": str(music), "role": "music"},
+ ],
+ "ducking": {"enabled": True},
+ "output_path": str(out),
+ }
+ )
+
+ assert result.success is True, result.error
+ assert out.exists() and _has_audio(out)
+
+
+def test_full_mix_multi_narration_plus_music_with_ducking(tmp_path):
+ s1, s2 = tmp_path / "s1.wav", tmp_path / "s2.wav"
+ music = tmp_path / "music.wav"
+ _sine(s1, 440, 2)
+ _sine(s2, 330, 2)
+ _sine(music, 220, 3)
+ out = tmp_path / "mixed_multi.wav"
+
+ result = AudioMixer().execute(
+ {
+ "operation": "full_mix",
+ "tracks": [
+ {"path": str(s1), "role": "speech"},
+ {"path": str(s2), "role": "speech"},
+ {"path": str(music), "role": "music"},
+ ],
+ "ducking": {"enabled": True},
+ "output_path": str(out),
+ }
+ )
+
+ assert result.success is True, result.error
+ assert out.exists() and _has_audio(out)
diff --git a/tools/audio/audio_mixer.py b/tools/audio/audio_mixer.py
index dba08b0b..44f29499 100644
--- a/tools/audio/audio_mixer.py
+++ b/tools/audio/audio_mixer.py
@@ -530,20 +530,13 @@ class AudioMixer(BaseTool):
f"[ducked_music]volume={music_vol * 3}[music_out]"
)
- # Duplicate speech for final mix (sidechain consumes it as key)
- filter_parts.append(
- f"{speech_out}acopy[speech_dup]" if speech_out.startswith("[a") else ""
- )
- # Re-mix speech path: we need speech audio in the output too
- # Simpler approach: use amix on original speech and ducked music
- # Reset: use a cleaner approach — amerge the speech mix and ducked music
- # Actually, let's rebuild. The sidechain approach above uses speech as
- # the key signal but doesn't consume it from the output chain.
- # FFmpeg sidechaincompress: input 0 = audio to compress, input 1 = key signal
- # So music is compressed, speech signal is the key. We need to mix them.
- # Remove the last filter_part (the acopy that may be empty)
- if filter_parts and filter_parts[-1] == "":
- filter_parts.pop()
+ # sidechaincompress uses the speech signal only as the ducking key —
+ # it does not emit speech to the output. Re-derive the speech stream
+ # for the final mix below. (An earlier version also appended an
+ # `acopy[speech_dup]` here, but that pad was never consumed and left
+ # the filtergraph with a dangling output, which ffmpeg rejects — so
+ # single-narration + music full_mix always failed. FFmpeg auto-splits
+ # the reused input label, so no explicit duplicate is needed.)
# Build speech mix for output separately
if len(speech_tracks) > 1: