{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreia4fnrplhdg4qk45pxrja6j3lmi2tkj2svbk34qkiz3jkaavcix6u",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlri7454jqg2"
  },
  "path": "/t/realtime-regression-in-non-english-production-voice-agents-gpt-realtime-mini-vs-gpt-realtime-mini-2025-10-06/1380643#post_10",
  "publishedAt": "2026-05-13T23:17:16.000Z",
  "site": "https://community.openai.com",
  "textContent": "Interesting topic. I’m going to test `gpt-realtime-mini-2025-10-06` in Portuguese as well.\n\nWe are currently using `gpt-realtime-mini`, but the quality has been quite poor for Portuguese voice agents. We are seeing issues with context loss, weaker understanding, and overall lower reliability in real customer scenarios.\n\nThis is directly affecting our ability to expand the project to more customers and use cases. The standard `gpt-realtime` model performs better, but it is too expensive for our use case and not economically viable at scale.\n\nIt would be very helpful to understand whether `gpt-realtime-mini-2025-10-06` is expected to improve non-English voice quality, especially for Portuguese, or if there are recommended settings to reduce these issues.",
  "title": "Realtime regression in non-English production voice agents: gpt-realtime-mini vs gpt-realtime-mini-2025-10-06"
}