{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigfsgydoejppfurap5f3hfme5fahy5k3h2jbczt544bemeseniqoi",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mm5hpu6ecaq2"
  },
  "path": "/t/realtime-sip-caller-hangup-still-drops-final-input-transcription-events/1380663#post_6",
  "publishedAt": "2026-05-18T17:56:38.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@Toshi"
  ],
  "textContent": "@Toshi, your read is likely right: in SIP Realtime sessions, the WebSocket can close fast after BYE / hangup. If VAD hasn’t committed the final audio yet, the transcription events may never fire.\n\nRight now, final transcription is not guaranteed when someone talks continuously and hangs up immediately.\n\nA few things worth logging:\n\n  * `speech_started`\n  * `speech_stopped`\n  * `input_audio_buffer.committed`\n\n\n\nIf you see `speech_started` but no `committed` before disconnect, that points to the final audio never becoming a conversation item.\n\nBest workaround for now is to save transcription deltas as they arrive, and use the Twilio recording as fallback for the caller’s last utterance in these quick-hangup cases.\n\n-Mark G.",
  "title": "Realtime SIP caller hangup still drops final input transcription events"
}