tts/generate.py

@@ -31,6 +31,16 @@ def main() -> None:
     parser.add_argument("--reference", required=True, help="Reference audio path")
     parser.add_argument("--output", required=True, help="Output wav path")
     parser.add_argument("--language", default="English", help="Language tag")
+    parser.add_argument(
+        "--instruction", default=None,
+        help='Style/delivery instruction (e.g. "Change the emotion to excited."). '
+        "Undocumented MOSS-TTS field for this checkpoint - confirmed to work for "
+        "emotion in testing, passed through as-is.",
+    )
+    parser.add_argument(
+        "--seed", type=int, default=None,
+        help="Random seed for reproducibility. Unset = nondeterministic.",
+    )
     parser.add_argument("--audio_temperature", type=float, default=1.7)
     parser.add_argument("--audio_top_p", type=float, default=0.8)
     parser.add_argument("--audio_top_k", type=int, default=25)
@@ -41,6 +51,11 @@ def main() -> None:
     device = "cuda" if torch.cuda.is_available() else "cpu"
     dtype = torch.bfloat16 if device == "cuda" else torch.float32
 
+    if args.seed is not None:
+        torch.manual_seed(args.seed)
+        if device == "cuda":
+            torch.cuda.manual_seed_all(args.seed)
+
     torch.backends.cuda.enable_cudnn_sdp(False)
     torch.backends.cuda.enable_flash_sdp(True)
     torch.backends.cuda.enable_mem_efficient_sdp(True)
@@ -65,6 +80,7 @@ def main() -> None:
             text=args.text,
             language=args.language,
             reference=[args.reference],
+            instruction=args.instruction,
         )
     ]