Wire diarization spans through MediaProcessor

app/services/media_service.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import json
 import os
 import time
 from collections.abc import Awaitable, Callable, Sequence
@@ -106,8 +107,26 @@ class MediaProcessor:
             ),
             temperature=self._float(params.get("temperature"), 0.0, 0.0, 1.0),
             caption_mode=str(params.get("caption_mode", "segment")),
+            diarization=self._diarization(params.get("diarization")),
         )
 
+    @staticmethod
+    def _diarization(value: Any) -> list[dict[str, Any]] | None:
+        if value is None or value == "":
+            return None
+        if isinstance(value, str):
+            try:
+                value = json.loads(value)
+            except json.JSONDecodeError as exc:
+                from app.core.exceptions import InputError
+
+                raise InputError("diarization must be valid JSON") from exc
+        if not isinstance(value, list):
+            from app.core.exceptions import InputError
+
+            raise InputError("diarization must be a JSON array of speaker spans")
+        return value
+
     async def run_ytdlp(self, resolved: ResolvedRequest) -> SuccessResponse:
         started = time.monotonic()
         params = resolved.params