Add speaker-attributed meeting transcription

openrouter_client.py

@@ -363,6 +363,61 @@ async def transcribe(audio_path: str) -> str:
             pass
 
 
+async def transcribe_tracks(tracks: list[dict]) -> str:
+    """Transcribe per-speaker WAV files and return a speaker-labeled transcript.
+
+    ``tracks`` is a list of dicts shaped like the ``tracks.json`` manifest
+    entries: ``{"display_name": str, "path": str, ...}``. Each track is
+    transcribed independently, then prefixed with the speaker's display name so
+    the summary model can attribute who said what.
+
+    Tracks that produce no transcript (silence-only, decode failure) are
+    skipped. Raises RuntimeError only if NO track produced any text.
+    """
+    from helpers import build_transcript_block
+
+    blocks: list[str] = []
+    failures: list[str] = []
+
+    for track in tracks:
+        path = track.get("path")
+        display_name = track.get("display_name") or "Unknown User"
+        if not path or not os.path.exists(path):
+            failures.append(f"{display_name}: track file missing ({path})")
+            continue
+
+        try:
+            text = await transcribe(path)
+        except Exception as exc:  # noqa: BLE001 - per-track isolation is intentional
+            failures.append(f"{display_name}: {exc}")
+            logger.warning(
+                "Per-speaker transcription failed: display_name=%s path=%s error=%s",
+                display_name,
+                path,
+                exc,
+            )
+            continue
+
+        if text.strip():
+            blocks.append(build_transcript_block(display_name, text))
+            logger.info(
+                "Per-speaker transcription complete: display_name=%s transcript_chars=%s",
+                display_name,
+                len(text.strip()),
+            )
+
+    if not blocks:
+        raise RuntimeError(
+            "Speaker-track transcription produced no text"
+            + (": " + " | ".join(failures) if failures else "")
+        )
+
+    if failures:
+        logger.warning("Some speaker tracks failed to transcribe: %s", " | ".join(failures))
+
+    return "\n\n".join(blocks)
+
+
 def _extract_chat_content(data: Any, *, provider: str) -> str:
     try:
         content = data["choices"][0]["message"]["content"]