pub struct RealtimeResponse {Show 13 fields
pub id: Option<String>,
pub object: Option<Object>,
pub status: Option<Status>,
pub status_details: Option<StatusDetails>,
pub output: Option<Vec<RealtimeConversationItem>>,
pub metadata: Option<Metadata>,
pub usage: Option<Usage>,
pub conversation_id: Option<String>,
pub voice: Option<VoiceIdsShared>,
pub modalities: Option<Vec<Item>>,
pub output_audio_format: Option<OutputAudioFormat>,
pub temperature: Option<Number>,
pub max_output_tokens: Option<MaxOutputTokens>,
}Expand description
The response resource.
Fields§
§id: Option<String>The unique ID of the response.
object: Option<Object>The object type, must be realtime.response.
status: Option<Status>The final status of the response (completed, cancelled, failed, or
incomplete, in_progress).
status_details: Option<StatusDetails>Additional details about the status.
output: Option<Vec<RealtimeConversationItem>>The list of output items generated by the response.
metadata: Option<Metadata>§usage: Option<Usage>Usage statistics for the Response, this will correspond to billing. A Realtime API session will maintain a conversation context and append new Items to the Conversation, thus output from previous turns (text and audio tokens) will become the input for later turns.
conversation_id: Option<String>Which conversation the response is added to, determined by the conversation
field in the response.create event. If auto, the response will be added to
the default conversation and the value of conversation_id will be an id like
conv_1234. If none, the response will not be added to any conversation and
the value of conversation_id will be null. If responses are being triggered
by server VAD, the response will be added to the default conversation, thus
the conversation_id will be an id like conv_1234.
voice: Option<VoiceIdsShared>The voice the model used to respond.
Current voice options are alloy, ash, ballad, coral, echo, sage,
shimmer, and verse.
modalities: Option<Vec<Item>>The set of modalities the model used to respond. If there are multiple modalities,
the model will pick one, for example if modalities is ["text", "audio"], the model
could be responding in either text or audio.
output_audio_format: Option<OutputAudioFormat>The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.
temperature: Option<Number>Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
max_output_tokens: Option<MaxOutputTokens>Maximum number of output tokens for a single assistant response, inclusive of tool calls, that was used in this response.
Implementations§
Source§impl RealtimeResponse
impl RealtimeResponse
Sourcepub fn builder() -> RealtimeResponseBuilder<((), (), (), (), (), (), (), (), (), (), (), (), ())>
pub fn builder() -> RealtimeResponseBuilder<((), (), (), (), (), (), (), (), (), (), (), (), ())>
Create a builder for building RealtimeResponse.
On the builder, call .id(...)(optional), .object(...)(optional), .status(...)(optional), .status_details(...)(optional), .output(...)(optional), .metadata(...)(optional), .usage(...)(optional), .conversation_id(...)(optional), .voice(...)(optional), .modalities(...)(optional), .output_audio_format(...)(optional), .temperature(...)(optional), .max_output_tokens(...)(optional) to set the values of the fields.
Finally, call .build() to create the instance of RealtimeResponse.
Trait Implementations§
Source§impl Clone for RealtimeResponse
impl Clone for RealtimeResponse
Source§fn clone(&self) -> RealtimeResponse
fn clone(&self) -> RealtimeResponse
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
source. Read more