pub struct RealtimeResponse {Show 13 fields
pub id: Option<String>,
pub object: Option<RealtimeResponseObject>,
pub status: Option<RealtimeResponseStatus>,
pub status_details: Option<RealtimeResponseStatusDetails>,
pub output: Option<Vec<RealtimeConversationItem>>,
pub metadata: Option<Metadata>,
pub usage: Option<RealtimeResponseUsage>,
pub conversation_id: Option<String>,
pub voice: Option<VoiceIdsShared>,
pub modalities: Option<Vec<RealtimeResponseModality>>,
pub output_audio_format: Option<RealtimeResponseOutputAudioFormat>,
pub temperature: Option<f64>,
pub max_output_tokens: Option<RealtimeResponseMaxOutputTokens>,
}
Expand description
The response resource.
Fields§
§id: Option<String>
The unique ID of the response.
object: Option<RealtimeResponseObject>
The object type, must be realtime.response
.
status: Option<RealtimeResponseStatus>
The final status of the response (completed
, cancelled
, failed
, or
incomplete
).
status_details: Option<RealtimeResponseStatusDetails>
Additional details about the status.
output: Option<Vec<RealtimeConversationItem>>
The list of output items generated by the response.
metadata: Option<Metadata>
§usage: Option<RealtimeResponseUsage>
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
, fable
,
onyx
, nova
, sage
, shimmer
, and verse
.
modalities: Option<Vec<RealtimeResponseModality>>
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<RealtimeResponseOutputAudioFormat>
The format of output audio. Options are pcm16
, g711_ulaw
, or g711_alaw
.
temperature: Option<f64>
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
max_output_tokens: Option<RealtimeResponseMaxOutputTokens>
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