{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibt6xntgszfyj4m5ngl5fkbdqolcdbitema7kjjbjevs5idlxbkji",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3ml5cc7f7kwx2"
},
"path": "/t/tts-with-a-question-the-audio-back-has-the-answer/1377233#post_7",
"publishedAt": "2026-05-05T22:26:53.000Z",
"site": "https://community.openai.com",
"tags": [
"@OpenAI_Support",
"TTS usage",
"deprecations",
"here"
],
"textContent": "OpenAI_Support:\n\n> Meanwhile, we suggest you all try using gpt-realtime-1.5 for TTS usage.\n\n@OpenAI_Support The suggested model `gpt-realtime-1.5` does not appear to be a valid model for TTS usage.\n\nIt also seems to be incorrectly listed in the deprecations documentation as a valid replacement. Additionally, it was already reported here that `gpt-4o-mini-tts-2025-12-15` has unresolved issues, so it may not be a suitable replacement either.\n\nIf possible, I’d be grateful if this could be forwarded to the team. For now, `gpt-4o-mini-tts-2025-03-20` would still be a useful model for the developer community.",
"title": "TTS with a question... the audio back has the answer"
}