class

OpenAI::RealtimeConversationItemMessageUserContentItem

Inherits JSON::Serializable < Reference < Object

Constructors

Source

new(*, __pull_for_json_serializable pull : JSON::PullParser)

Source

Instance methods

audio

Base64-encoded audio bytes (for input_audio), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Source

audio=(audio : String | Nil)

Base64-encoded audio bytes (for input_audio), these will be parsed as the format specified in the session input audio type configuration. This defaults to PCM 16-bit 24kHz mono if not specified.

Source

detail

The detail level of the image (for input_image). auto will default to high.

Source

detail=(detail : RealtimeConversationItemMessageUserContentItemDetail | Nil)

The detail level of the image (for input_image). auto will default to high.

Source

image_url

Base64-encoded image bytes (for input_image) as a data URI. For example data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA.... Supported formats are PNG and JPEG.

Source

image_url=(image_url : String | Nil)

Base64-encoded image bytes (for input_image) as a data URI. For example data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA.... Supported formats are PNG and JPEG.

Source

text

The text content (for input_text).

Source

text=(text : String | Nil)

The text content (for input_text).

Source

transcript

Transcript of the audio (for input_audio). This is not sent to the model, but will be attached to the message item for reference.

Source

transcript=(transcript : String | Nil)

Transcript of the audio (for input_audio). This is not sent to the model, but will be attached to the message item for reference.

Source

type_value

The content type (input_text, input_audio, or input_image).

Source

type_value=(type_value : RealtimeConversationItemMessageUserContentItemType | Nil)

The content type (input_text, input_audio, or input_image).

Source