feat(server): improve transcript error handle (#11293)

2026-08-02 09:59:55 +08:00 · 2025-03-31 09:30:32 +00:00
parent 6a66bf53a8
commit b37182ceb7
5 changed files with 146 additions and 97 deletions
@@ -364,6 +364,7 @@ The output should be a JSON array, with each element containing:

 - Ensure the accurate differentiation of speakers even if multiple speakers overlap slightly or switch rapidly.
 - Maintain a consistent speaker labeling system throughout the transcription.
+- If the provided audio or data does not contain valid talk, you should return an empty JSON array.
 `,
      },
    ],