pub type ChatCompletionModalities = Vec<ChatCompletionModality>;
Expand description
Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default:
["text"]
The gpt-4o-audio-preview
model can also be used to generate audio. To
request that this model generate both text and audio responses, you can
use:
["text", "audio"]
Aliased Typeยง
pub struct ChatCompletionModalities { /* private fields */ }