{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiakx5i7ktggzujkuqwuev2dyvt6jdsxe7zpxv74hmr7iy3sq7qvuu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mixiqt2s33g2"
  },
  "path": "/t/best-solution-for-whisper-diarization-speaker-labeling/505922?page=2#post_24",
  "publishedAt": "2026-04-08T03:48:22.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "developers.openai.com",
    "GPT-4o Transcribe Diarize Model | OpenAI API"
  ],
  "textContent": "Hi Dears\n\nI think there is a model that will be available soon.. **GPT-4o Transcribe Diarize**\n\nWell, it looks like it is released, but from the SDK we are using (.NET) it became available just now. (couple of days ago)\n\ndevelopers.openai.com\n\n### GPT-4o Transcribe Diarize Model | OpenAI API\n\nWe are testing this right now as we speak.\n\nCurrently when clients select openAI for transcription, we are diarizing via the prompt itself. (We tell the prompt to detect the speakers and diarize). It somewhat works okay. People use it.\n\nThis is why we need to get this working **GPT-4o Transcribe Diarize** so we can remove this workaround from the system prompt.",
  "title": "Best solution for Whisper diarization/speaker labeling?"
}