{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibgvyimwtz6nraayynelwqhulpzmxar2njaonwfhf3asvysu4sipm",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mibojlbsof72"
  },
  "path": "/t/transcription-models-available-question-on-gpt-4o-transcribe-gpt-4o-mini-transcribe-gpt-4o-transcribe-diarize/1378134#post_4",
  "publishedAt": "2026-03-30T11:56:31.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@vb",
    "GPT-4o Transcribe Diarize Model | OpenAI API",
    "https://github.com/openai/openai-dotnet/issues/869",
    "github.com/openai/openai-dotnet",
    "[Audio] Add support for diarized audio transcription (#1008#event-23660087929)",
    "ShivangiReja",
    "+3171\n-622",
    "…"
  ],
  "textContent": "@vb\n\nAbout this “gpt-4o-transcribe-diarize” GPT-4o Transcribe Diarize Model | OpenAI API\n\nThe problem is that the API doesn’t allow setting response format to “ddiarized_json” which is needed for this model.\nThere’s an open issue about this here https://github.com/openai/openai-dotnet/issues/869\n\nSeems like the required “chunking_strategy” is not currently supported by the SDK and we get HTTP 400 (invalid_request_error: invalid_value)\nParameter: chunking_strategy\nchunking_strategy is required for diarization models\n\nThis shows that there is active work ongoing.\n\ngithub.com/openai/openai-dotnet\n\n####  [Audio] Add support for diarized audio transcription (#1008#event-23660087929)\n\n`main` ← `ShivangiReja:Shreja_DiarizedAudioTranscription`\n\nopened 11:38PM - 05 Mar 26 UTC\n\n\n\n            ShivangiReja\n          \n\n\n+3171\n-622\n\n\n## Summary Adds client support for the diarized audio transcription. ## Ch…anges ### New API surface - **`AudioClient.TranscribeAudioDiarized` / `TranscribeAudioDiarizedAsync`** — four new method overloads (sync/async × `Stream`/file path) that return `DiarizedAudioTranscription` - **`DiarizedAudioTranscription`** — response model containing `Text`, `Duration`, `Segments`, and `Usage` - **`DiarizedTranscriptionSegment`** — segment model with `Speaker`, `Text`, `StartTime`, `EndTime`, and `Logprob` - **`TranscriptionUsage`** — base usage type with discriminated subtypes: - `TranscriptionTokenUsage` (with `InputTokens`, `OutputTokens`, `TotalTokens`, `InputTokenDetails`) - `TranscriptionDurationUsage` (with `Seconds`) - **`TranscriptionUsageKind`** — extensible enum (`Tokens`, `Duration`) - **`TranscriptionInputTokenDetails`** — `TextTokens`, `AudioTokens` - **`AudioTranscriptionFormat.DiarizedJson`** — now public - **`AudioTranscriptionOptions.KnownSpeakerNames`** and **`KnownSpeakerReferences`** — now public ### Tests & examples - Five new tests: `DiarizedTranscriptionWorks`, `DiarizedTranscriptionWithKnownSpeakersWorks`, `DiarizedTranscriptionHasUsage`, `DiarizedTranscriptionSegmentsAreOrdered`, `TranscriptionUsageWorks` - Two new examples: `Example05_DiarizedTranscription` (sync and async) - New test model entry: `gpt-4o-transcribe-diarize` Fixes: https://github.com/openai/openai-dotnet/issues/916\n\nGuess I will wait and watch… If you happen to have any additional news, do not hesitate and let me know.\n\nThanks so much Dears",
  "title": "Transcription models available - Question on gpt-4o-transcribe gpt-4o-mini-transcribe gpt-4o-transcribe-diarize"
}