fix(backend): count the S3TokenizerV2 repo in the Chatterbox MLX cache check; register the backend with PyInstaller

Review follow-ups: mlx-audio's Model.from_pretrained fetches the S3
speech tokenizer from mlx-community/S3TokenizerV2 (~470 MB) separately
from the chatterbox checkout, so _is_model_cached now requires both
repos (same shape as the Hume backend's codec check) and the config's
size_mb reflects the real footprint. backend.backends.chatterbox_mlx_backend
is a function-level import that PyInstaller's graph will not see, so it
is added to the Apple Silicon hidden-import list in build_binary.py and
voicebox-server.spec next to mlx_backend.

backend/backends/__init__.py

@@ -297,7 +297,8 @@ def _get_non_qwen_tts_configs() -> list[ModelConfig]:
     on_mlx = get_backend_type() == "mlx"
     if on_mlx:
         chatterbox_repo = "mlx-community/chatterbox-multilingual-v3"
-        chatterbox_size_mb = 2600
+        # 2.5 GB of weights plus the separately fetched S3TokenizerV2 (~470 MB)
+        chatterbox_size_mb = 3000
     else:
         chatterbox_repo = "ResembleAI/chatterbox"
         chatterbox_size_mb = 3200