{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiccljccs3tiqiepwr4lbprd6vcvnjmhfhufak2s6oaop7abnby2y4",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmwaayqksur2"
},
"path": "/t/gpt-realtime-2-splits-acknowledgment-next-step-into-separate-turns-causing-5-20s-caller-silence-rollback-to-gpt-realtime-1-5-confirmed-as-a-b-fix/1381276#post_4",
"publishedAt": "2026-05-28T13:31:02.000Z",
"site": "https://community.openai.com",
"textContent": "I have just discovered that this seems to be a case of false positive content_filter. From what I can find, the new model is highly sensitive and bad at this for other languages than English…\nYou can detect it via the response.done event:\n“”\"\nresponse done: namespace(type=‘response.done’, event_id=‘…’, response=namespace(object=‘realtime.response’, id=‘…’, status=‘incomplete’, status_details=namespace(type=‘incomplete’, reason=‘content_filter’), output=[namespace(id=‘…’, type=‘message’, status=‘incomplete’, role=‘assistant’, content=[namespace(type=‘output_audio’, transcript=‘Hej, dejligt at fortsætte efter vores korte introduktion. Sig endelig’)], phase=‘final_answer’)], conversation_id=‘…’, output_modalities=[‘audio’], max_output_tokens=‘inf’, audio=namespace(output=namespace(format=namespace(type=‘audio/pcm’, rate=24000), voice=‘marin’)), usage=namespace(total_tokens=1462, input_tokens=1312, output_tokens=150, input_token_details=namespace(text_tokens=1312, audio_tokens=0, image_tokens=0, cached_tokens=0, cached_tokens_details=namespace(text_tokens=0, audio_tokens=0, image_tokens=0)), output_token_details=namespace(text_tokens=75, audio_tokens=75)), metadata=None))\n“”\"",
"title": "Gpt-realtime-2 splits acknowledgment + next-step into separate turns, causing 5-20s caller silence (rollback to gpt-realtime-1.5 confirmed as A/B fix)"
}