Add Stable Audio 3 Small-SFX to sound effects tab, with model toggle and save-to-library

Runs entirely on CPU (no VRAM contention with ComfyUI), and sounds
noticeably better than MOSS-SoundEffect per listening test, so it is now
the default model. Toggle keeps MOSS-SoundEffect available as a fallback.
Saved clips land in the-service-station/sfx_library/ on disk, no db/
metadata system per explicit scope.

Co-Authored-By: Claude Sonnet 5 <[email protected]>

sfx-stable-audio-3/generate.py

@@ -0,0 +1,32 @@
+"""
+Stable Audio 3 Small-SFX CLI: generate a sound effect/ambience clip from a
+text description. Runs on CPU by design - this checkpoint is the
+"lightweight, no GPU required" model in Stable Audio 3's lineup, so it
+never contends with ComfyUI/other models for VRAM (unlike generate_sfx.py's
+MOSS-SoundEffect, which needs the 3090 and ComfyUI's memory freed first).
+"""
+
+import argparse
+
+import torchaudio
+from stable_audio_3 import StableAudioModel
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Stable Audio 3 Small-SFX text-to-sound-effect")
+    parser.add_argument("--text", required=True, help="Description of the sound effect/ambience")
+    parser.add_argument("--output", required=True, help="Output wav path")
+    parser.add_argument("--duration", type=float, default=10.0, help="Clip duration in seconds (max 120)")
+    parser.add_argument("--seed", type=int, default=-1, help="Random seed, or -1 for random")
+    args = parser.parse_args()
+
+    model = StableAudioModel.from_pretrained("small-sfx", device="cpu")
+    sample_rate = model.model.sample_rate
+
+    audio = model.generate(prompt=args.text, duration=args.duration, seed=args.seed)
+    torchaudio.save(args.output, audio[0].cpu(), sample_rate)
+    print(f"[INFO] Saved {args.output}")
+
+
+if __name__ == "__main__":
+    main()