Add audio chat API support (gpt-4o-audio-preview, gpt-audio-1.5)

[BugorBN]

What

Adds audio support through the existing ChatQuery surface rather than a parallel API:

• gpt-audio-1.5, gpt-audio and gpt-audio-mini model constants
• gpt-4o-audio-preview marked deprecated (shut down 7 May 2026) and dropped from allModels(satisfying:), as other deprecated constants are
• a README section, "Audio input and output with Chat Completions", built on ChatQuery.modalities and ChatQuery.audioOptions — audio in and out, text in with audio out, streaming, multi-turn via the audio id, and audio token usage
• coding tests for input_audio content parts, assistant messages referencing a previous audio response, and decoding message.audio and the streaming delta.audio

Why

The first version of this PR added AudioChatQuery, AudioChatResult, AudioChatStreamResult, audioChats/audioChatsStream and an AudioConversationManager. Per review, that was a second way to call /chat/completions with a smaller surface (6 voices against 11, fewer parameters), added four protocol requirements that the API-breakage gate flags, and put conversation state management inside the SDK. All of it is removed, so the library keeps one way to make a chat completion.

What remains is what the library was actually missing: the current audio model constants, and documentation for audio over Chat Completions, which the README did not cover at all.

Affected Areas

• Sources/OpenAI/Public/Models/Models/Models.swift — three new constants, one deprecation
• README.md — new section under Audio
• Tests/OpenAITests/ — audio cases added to the existing ChatQuery, ChatResult and ChatStreamResult test files

No API breakage: swift package diagnose-api-breaking-changes against 0.5.1 reports none, so no allowlist entry is needed. The branch is rebased on main and all 218 tests pass.

[Krivoblotsky]

Thank you for the work here, and apologies for the wait. It merges cleanly with main, builds, and all 217 tests pass. I want to be upfront about the direction, because it affects most of the diff.

ChatQuery already covers audio chat. On main today: ChatQuery.modalities, ChatQuery.audioOptions (11 voices including ash, ballad, coral, sage, verse; formats mp3, opus, flac, wav, pcm16), ContentPartAudioParam for input_audio, ChatResult.Choice.Message.audio (id, expiresAt, data, transcript) and the same on the streaming delta. AudioChatQuery, AudioChatResult and AudioChatStreamResult are a second way to call /chat/completions with a smaller surface (6 voices, fewer parameters), and audioChats / audioChatsStream add four protocol requirements, which the new API-breakage gate flags. The library should have one way to do a chat completion.

AudioConversationManager is conversation state management, which belongs in the app (or the Demo), not in the SDK.

What we would like to take from this PR:

• the gpt-audio-1.5 constant (plus gpt-audio and gpt-audio-mini), with gpt-4o-audio-preview marked deprecated since it was shut down on 7 May 2026;
• a README section "Audio input and output with Chat Completions" built on ChatQuery, which the README lacks entirely today; your examples adapt almost one to one;
• the coding tests, adapted to ChatQuery where they add coverage we do not have.

If you are up for reshaping the PR along those lines, that would be great and it would land quickly. If not, we can open a smaller PR that carries those pieces with you credited as co-author. Either way, thank you for pushing on audio support.

[BugorBN]

Thank you for the work here, and apologies for the wait. It merges cleanly with main, builds, and all 217 tests pass. I want to be upfront about the direction, because it affects most of the diff.

ChatQuery already covers audio chat. On main today: ChatQuery.modalities, ChatQuery.audioOptions (11 voices including ash, ballad, coral, sage, verse; formats mp3, opus, flac, wav, pcm16), ContentPartAudioParam for input_audio, ChatResult.Choice.Message.audio (id, expiresAt, data, transcript) and the same on the streaming delta. AudioChatQuery, AudioChatResult and AudioChatStreamResult are a second way to call /chat/completions with a smaller surface (6 voices, fewer parameters), and audioChats / audioChatsStream add four protocol requirements, which the new API-breakage gate flags. The library should have one way to do a chat completion.

AudioConversationManager is conversation state management, which belongs in the app (or the Demo), not in the SDK.

What we would like to take from this PR:

• the gpt-audio-1.5 constant (plus gpt-audio and gpt-audio-mini), with gpt-4o-audio-preview marked deprecated since it was shut down on 7 May 2026;
• a README section "Audio input and output with Chat Completions" built on ChatQuery, which the README lacks entirely today; your examples adapt almost one to one;
• the coding tests, adapted to ChatQuery where they add coverage we do not have.

If you are up for reshaping the PR along those lines, that would be great and it would land quickly. If not, we can open a smaller PR that carries those pieces with you credited as co-author. Either way, thank you for pushing on audio support.

Hey, thanks for the feedback, I'll reshape it in the next couple days

[BugorBN]

@Krivoblotsky done, let me know if I can help with anything else