sonilo-cli 0.8.2__tar.gz → 0.9.0__tar.gz

{sonilo_cli-0.8.2 → sonilo_cli-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sonilo-cli
-Version: 0.8.2
+Version: 0.9.0
 Summary: Command-line interface for the Sonilo API: generate music and sound effects from text or video
 Project-URL: Repository, https://github.com/sonilo-ai/sonilo-python
 Author: Sonilo AI
@@ -146,8 +146,10 @@ they differ only in what comes back: `video-to-sound` writes the mixed **audio**
 - `--segments` places individual effects on the timeline, in the SFX shape `{start, end, prompt}` —
   see [Segments](#segments).
 - `--preserve-speech` keeps speech from the source video in the mix.
-- **Ducking is on by default** (music dips under speech). Pass `--no-ducking` to opt out — omitting
-  the flag leaves the server default untouched.
+- **Ducking is off by default.** Pass `--ducking` to bring the source video's own speech into the
+  mix with the generated bed dipped under it — without it the result is the generated music and
+  effects alone. Omitting both flags leaves the server default untouched; `--no-ducking` still
+  works and now just states that default explicitly.
 - `--stem` is repeatable (`music`, `music_processed`, `sfx`) and saves the individual layers next to
   the combined output, so you can re-balance the mix yourself. With `--output soundtrack.wav`, the
   music stem lands at `soundtrack.music.m4a`. `music_processed` exists only when `--preserve-speech`

{sonilo_cli-0.8.2 → sonilo_cli-0.9.0}/README.md

@@ -130,8 +130,10 @@ they differ only in what comes back: `video-to-sound` writes the mixed **audio**
 - `--segments` places individual effects on the timeline, in the SFX shape `{start, end, prompt}` —
   see [Segments](#segments).
 - `--preserve-speech` keeps speech from the source video in the mix.
-- **Ducking is on by default** (music dips under speech). Pass `--no-ducking` to opt out — omitting
-  the flag leaves the server default untouched.
+- **Ducking is off by default.** Pass `--ducking` to bring the source video's own speech into the
+  mix with the generated bed dipped under it — without it the result is the generated music and
+  effects alone. Omitting both flags leaves the server default untouched; `--no-ducking` still
+  works and now just states that default explicitly.
 - `--stem` is repeatable (`music`, `music_processed`, `sfx`) and saves the individual layers next to
   the combined output, so you can re-balance the mix yourself. With `--output soundtrack.wav`, the
   music stem lands at `soundtrack.music.m4a`. `music_processed` exists only when `--preserve-speech`

{sonilo_cli-0.8.2 → sonilo_cli-0.9.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "sonilo-cli"
-version = "0.8.2"
+version = "0.9.0"
 description = "Command-line interface for the Sonilo API: generate music and sound effects from text or video"
 readme = "README.md"
 license = "MIT"

{sonilo_cli-0.8.2 → sonilo_cli-0.9.0}/src/sonilo_cli/__init__.py

@@ -1,3 +1,3 @@
-__version__ = "0.8.0"
+__version__ = "0.9.0"
 
 __all__ = ["__version__"]

{sonilo_cli-0.8.2 → sonilo_cli-0.9.0}/src/sonilo_cli/__main__.py

@@ -167,6 +167,30 @@ def parse_segments(
     return value
 
 
+def _ducking(args: argparse.Namespace) -> Optional[bool]:
+    """Resolve --ducking / --no-ducking, or None to let the server default win.
+
+    `ducking` used to be default-ON server-side, so the only direction worth
+    expressing was turning it off and --no-ducking was the only flag. It is now
+    default-OFF, which makes --ducking the useful one. --no-ducking is kept
+    because dropping it would turn every script that passes it into a hard
+    argparse error; it now sends the explicit False the server would have
+    applied anyway.
+
+    Passing both is a contradiction with no sensible winner, so it exits rather
+    than silently picking one.
+    """
+    on = getattr(args, "ducking", False)
+    off = getattr(args, "no_ducking", False)
+    if on and off:
+        raise SystemExit("pass at most one of --ducking or --no-ducking")
+    if on:
+        return True
+    if off:
+        return False
+    return None
+
+
 def _segments(args: argparse.Namespace) -> Optional[List[Dict[str, Any]]]:
     """parse_segments() for whichever subcommand is running."""
     return parse_segments(args.segments, args.segments_shape, args.command)
@@ -345,7 +369,7 @@ def _run_sound(client: Sonilo, args: argparse.Namespace, resource: Any, default_
         sfx_prompt=args.sfx_prompt,
         segments=_segments(args),
         preserve_speech=True if args.preserve_speech else None,
-        ducking=False if args.no_ducking else None,
+        ducking=_ducking(args),
         variants_num=args.variants,
         **extra,
     )
@@ -403,12 +427,11 @@ def cmd_video_to_video_music(client: Sonilo, args: argparse.Namespace) -> None:
         client.video_to_video_music,
         prompt=args.prompt,
         # Unset flags forward None, not False, so the server default stands —
-        # same reasoning as --no-ducking on the sound commands. The two
-        # defaults run opposite ways: ducking is default-ON server-side and
-        # keep_original_sound default-OFF, so each is only ever sent to change
-        # the default, never to restate it.
+        # same reasoning as --ducking on the sound commands. Both ducking and
+        # keep_original_sound are default-OFF server-side, so each is only ever
+        # sent to change the default, never to restate it.
         keep_original_sound=True if args.keep_original_sound else None,
-        ducking=False if args.no_ducking else None,
+        ducking=_ducking(args),
         preserve_speech=True if args.preserve_speech else None,
         isolate_vocals=True if args.isolate_vocals else None,
         variants_num=args.variants,
@@ -611,8 +634,14 @@ def build_parser() -> argparse.ArgumentParser:
     _add_segments(p_v2sd, SFX_SHAPE)
     p_v2sd.add_argument("--preserve-speech", dest="preserve_speech", action="store_true",
                         help="Keep source speech in the mix.")
+    p_v2sd.add_argument("--ducking", dest="ducking", action="store_true",
+                        help="Bring the source video's own speech into the mix and duck "
+                             "the generated bed under it. Off by default, so by default "
+                             "the result is the generated music and effects alone and "
+                             "there is no music_processed stem.")
     p_v2sd.add_argument("--no-ducking", dest="no_ducking", action="store_true",
-                        help="Disable automatic ducking (on by default server-side).")
+                        help="Explicit opt-out. Same as the default; kept so existing "
+                             "scripts keep working.")
     p_v2sd.add_argument("--stem", dest="stems", action="append", choices=_SOUND_STEMS,
                         default=None, help="Also save an individual stem. Repeatable.")
     p_v2sd.add_argument("--output", default=None, help="Where to save the combined audio.")
@@ -631,10 +660,13 @@ def build_parser() -> argparse.ArgumentParser:
                              "generated music under it. Off by default, so by default "
                              "the result's audio is the generated music alone. "
                              "Supersedes --preserve-speech.")
+    p_v2vm.add_argument("--ducking", dest="ducking", action="store_true",
+                        help="Duck the music under the voice instead of mixing it in at "
+                             "a static level. No effect without --keep-original-sound "
+                             "or --preserve-speech.")
     p_v2vm.add_argument("--no-ducking", dest="no_ducking", action="store_true",
-                        help="Combine the voice and the music as a static mix instead "
-                             "of a dynamic duck. No effect without "
-                             "--keep-original-sound or --preserve-speech.")
+                        help="Explicit opt-out. Same as the default; kept so existing "
+                             "scripts keep working.")
     p_v2vm.add_argument("--preserve-speech", dest="preserve_speech", action="store_true",
                         help="Keep only the source's isolated speech in the mix.")
     # Same aliasing as video-to-music, and here the endpoint collapses the two
@@ -676,10 +708,13 @@ def build_parser() -> argparse.ArgumentParser:
                               "--preserve-speech. This command only.")
     p_v2vsd.add_argument("--preserve-speech", dest="preserve_speech", action="store_true",
                          help="Keep only the source's isolated speech in the mix.")
-    p_v2vsd.add_argument("--no-ducking", dest="no_ducking", action="store_true",
-                         help="Combine the voice and the generated bed as a static mix "
-                              "instead of a dynamic duck. No effect without "
+    p_v2vsd.add_argument("--ducking", dest="ducking", action="store_true",
+                         help="Duck the generated bed under the voice instead of mixing "
+                              "it in at a static level. No effect without "
                               "--keep-original-sound or --preserve-speech.")
+    p_v2vsd.add_argument("--no-ducking", dest="no_ducking", action="store_true",
+                         help="Explicit opt-out. Same as the default; kept so existing "
+                              "scripts keep working.")
     p_v2vsd.add_argument("--stem", dest="stems", action="append", choices=_SOUND_STEMS,
                          default=None, help="Also save an individual stem. Repeatable.")
     p_v2vsd.add_argument("--output", default=None, help="Where to save the combined video.")

{sonilo_cli-0.8.2 → sonilo_cli-0.9.0}/tests/test_cli.py

@@ -369,15 +369,25 @@ def test_video_to_sound_ducking_absent_omits_field(tmp_path):
     )
     run(["video-to-sound", "--video-url", "http://x/y.mp4",
          "--output", str(tmp_path / "s.wav")])
-    # ducking is default-ON server-side: an unset --no-ducking must forward
-    # `None`, not `False`, so the field must be entirely absent from the
-    # form-encoded body (per build_v2s_parts).
+    # ducking is default-OFF server-side, and neither flag was passed, so the
+    # CLI must forward `None`, not `False` — the field has to be absent from
+    # the form-encoded body (per build_v2s_parts) and let the server decide.
     body = route.calls.last.request.content.decode()
     assert "ducking=" not in body
 
 
 @respx.mock
-def test_video_to_sound_no_ducking_sets_false(tmp_path):
+@pytest.mark.parametrize(
+    "flag, wire",
+    [
+        # --ducking is the direction that does something now that the server
+        # default is off; --no-ducking predates the flip, still parses so
+        # existing scripts do not break, and states the default explicitly.
+        ("--ducking", "ducking=true"),
+        ("--no-ducking", "ducking=false"),
+    ],
+)
+def test_video_to_sound_ducking_flags(tmp_path, flag, wire):
     route = respx.post(f"{BASE}/v1/video-to-sound").mock(
         return_value=httpx.Response(200, json={"task_id": "sd4", "status": "processing"})
     )
@@ -388,9 +398,15 @@ def test_video_to_sound_no_ducking_sets_false(tmp_path):
         return_value=httpx.Response(200, content=b"MIXED")
     )
     run(["video-to-sound", "--video-url", "http://x/y.mp4",
-         "--output", str(tmp_path / "s.wav"), "--no-ducking"])
+         "--output", str(tmp_path / "s.wav"), flag])
     body = route.calls.last.request.content.decode()
-    assert "ducking=false" in body
+    assert wire in body
+
+
+def test_video_to_sound_rejects_both_ducking_flags(tmp_path):
+    with pytest.raises(SystemExit):
+        run(["video-to-sound", "--video-url", "http://x/y.mp4",
+             "--output", str(tmp_path / "s.wav"), "--ducking", "--no-ducking"])
 
 
 @respx.mock