.Net: {Azure}OpenAI add support for Audio Contents in Chat Completion models. #10493
Assignees
Labels
Build
Features planned for next Build conference
.NET
Issue or Pull requests regarding .NET code
sk team issue
A tag to denote issues that where created by the Semantic Kernel team (i.e., not the community)
Comments
markwallace-microsoft
added
.NET
RogerBarreto
added
the
sk team issue
markwallace-microsoft
added
Build
markwallace-microsoft
moved this from Backlog: Planned
to Sprint: In Review
in Semantic Kernel
github-merge-queue bot
pushed a commit
that referenced
this issue
Apr 2, 2025
…11279) ### Motivation and Context - Resolve #10493 --------- Co-authored-by: SergeyMenshykh <[email protected]>
glorious-beard
pushed a commit
to glorious-beard/semantic-kernel
that referenced
this issue
Apr 6, 2025
…icrosoft#11279) - Resolve microsoft#10493 --------- Co-authored-by: SergeyMenshykh <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2.2.0-beta.1 for both Azure OpenAI SDK and OpenAI SDK now supports Audio Content
This issue tracks this requirement to be added as a new feature on both OpenAI and AzureOpenAI Connectors.
https://github.com/Azure/azure-sdk-for-net/blob/c2aa8d8448bdb7378a5c1b7ba23aa75e39e6b425/sdk/openai/Azure.AI.OpenAI/CHANGELOG.md?plain=1#L9
Audio input for Chat Completions using
gpt-4o-audio-previewor other compatible models: provide input audio viaChatMessageContentPart.CreateInputAudioPart(), setAudioOptionsandResponseModalitiesonChatCompletionOptions, retrieve response audio viaOutputAudioonChatCompletion, and reference audio history from the assistant by using theAssistantChatMessage(ChatCompletion)constructor or usingChatMessageContentPart.CreateAudioPart(string). For more information, refer to the examples in the OpenAI README.The text was updated successfully, but these errors were encountered: