{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreidpkuif5bvixwfrmfhbqb5xaat5m3coete6hibwp3f4an6c5sxj5e",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmrtd2746g72"
},
"path": "/t/realtime-api-audio-response-unexpectedly-repeated-an-unrelated-personal-sentence-multiple-times-mid-conversation/1381793#post_2",
"publishedAt": "2026-05-26T19:53:09.000Z",
"site": "https://community.openai.com",
"tags": [
"@techiesingh"
],
"textContent": "Welcome to the community @techiesingh!\n\nThat’s definitely unsettling, especially since the response was completely unrelated to your conversation context. The repeated emotional playback part also makes this seem more like a realtime/session issue than normal model behavior.\n\nTo help narrow it down, could you share a few details from the session?\n\n * Request ID(s)\n * Approximate timestamp(s) when it happened\n * Model used\n * Realtime session configuration if relevant\n * Snapshot/export of the realtime event log\n * Whether the repeated audio also had repeated transcript events, or if it was only the audio playback repeating\n * Whether interruption/turn detection was active\n * Anything else unusual right before it started looping\n\n\n\nThose details can help identify whether this came from transcript generation, audio playback state, buffering, or a session-level mix-up.\n\nA few folks have reported odd realtime/audio edge cases recently, so having the event timeline is especially useful here.\n\n-Mark G.",
"title": "Realtime API audio response unexpectedly repeated an unrelated personal sentence multiple times mid-conversation"
}