{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreieijsdbopw3nadlhxk33ssqyfctar4kfy2liiaxzrz3dzj4zuzt34",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmcpkdxjjtf2"
},
"path": "/t/realtime-api-poor-portuguese-call-quality-with-gpt-realtime-mini-gpt-realtime/1381375#post_2",
"publishedAt": "2026-05-20T19:37:08.000Z",
"site": "https://community.openai.com",
"tags": [
"Realtime transcription"
],
"textContent": "About your problem with noises and background interference, I would consider a implementation of a filter (band-pass filter, spectral denoise, noise reduction, etc.), there is a lot kind of filters try some to check which one fits better for you case. Is important to know that the API supports `noise_reduction` filter as parameter. Check Realtime transcription.\n\nAbout the recognition accuracy, it can be related with the noises. I would first try to implement the filters. If it doesn’t resolve, try another models. But, I would say that the gpt realtime models are already good. I have some projects using Gemini speech-to-text and live API and they’re good too.\n\nAnother approach is to implement a second turn that pass along the transcribed text and improve it, but probably it is not worth for real-time cases due to the delay.",
"title": "Realtime API: Poor Portuguese call quality with gpt-realtime-mini / gpt-realtime"
}