RealtimeSession
objectRealtime session object configuration.
Unique identifier for the session object.
The set of modalities the model can respond with. To disable audio,
set this to [“text”].
Any OfThe Realtime model used for this session.
The default system instructions (i.e. system message) prepended to model
calls. This field allows the client to guide the model on desired
responses. The model can be instructed on response content and format,
(e.g. “be extremely succinct”, “act friendly”, “here are examples of good
responses”) and on audio behavior (e.g. “talk quickly”, “inject emotion
into your voice”, “laugh frequently”). The instructions are not guaranteed
to be followed by the model, but they provide guidance to the model on the
desired behavior.
Note that the server sets default instructions which will be used if this
field is not set and are visible in the session.created event at the
start of the session.
The voice the model uses to respond. Voice cannot be changed during the
session once the model has responded with audio at least once. Current
voice options are alloy, ash, ballad, coral, echo sage,
shimmer and verse.
Allowed values:alloyashballadcoralechosageshimmerverse
The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.
For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate,
single channel (mono), and little-endian byte order.
Allowed values:pcm16g711_ulawg711_alaw
The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.
For pcm16, output audio is sampled at a rate of 24kHz.
Allowed values:pcm16g711_ulawg711_alaw
Configuration for input audio transcription, defaults to off and can be
set to null to turn off once on. Input audio transcription is not native
to the model, since the model consumes audio directly. Transcription runs
asynchronously through Whisper and should be treated as rough guidance
rather than the representation understood by the model.
Show Child Parameters
Configuration for turn detection. Can be set to null to turn off. Server
VAD means that the model will detect the start and end of speech based on
audio volume and respond at the end of user speech.
Show Child Parameters
Tools (functions) available to the model.
Show Child Parameters
How the model chooses tools. Options are auto, none, required, or
specify a function.
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
One OfMaximum number of output tokens for a single assistant response,
inclusive of tool calls. Provide an integer between 1 and 4096 to
limit output tokens, or inf for the maximum available tokens for a
given model. Defaults to inf.
RealtimeSessionCreateRequest
objectRealtime session object configuration.
The set of modalities the model can respond with. To disable audio,
set this to [“text”].
The Realtime model used for this session.
Allowed values:gpt-4o-realtime-previewgpt-4o-realtime-preview-2024-10-01gpt-4o-realtime-preview-2024-12-17gpt-4o-mini-realtime-previewgpt-4o-mini-realtime-preview-2024-12-17
The default system instructions (i.e. system message) prepended to model
calls. This field allows the client to guide the model on desired
responses. The model can be instructed on response content and format,
(e.g. “be extremely succinct”, “act friendly”, “here are examples of good
responses”) and on audio behavior (e.g. “talk quickly”, “inject emotion
into your voice”, “laugh frequently”). The instructions are not guaranteed
to be followed by the model, but they provide guidance to the model on the
desired behavior.
Note that the server sets default instructions which will be used if this
field is not set and are visible in the session.created event at the
start of the session.
The voice the model uses to respond. Voice cannot be changed during the
session once the model has responded with audio at least once. Current
voice options are alloy, ash, ballad, coral, echo sage,
shimmer and verse.
Allowed values:alloyashballadcoralechosageshimmerverse
The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.
For pcm16, input audio must be 16-bit PCM at a 24kHz sample rate,
single channel (mono), and little-endian byte order.
Allowed values:pcm16g711_ulawg711_alaw
The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.
For pcm16, output audio is sampled at a rate of 24kHz.
Allowed values:pcm16g711_ulawg711_alaw
Configuration for input audio transcription, defaults to off and can be set to null to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through OpenAI Whisper transcription and should be treated as rough guidance rather than the representation understood by the model. The client can optionally set the language and prompt for transcription, these fields will be passed to the Whisper API.
Show Child Parameters
Configuration for turn detection. Can be set to null to turn off. Server
VAD means that the model will detect the start and end of speech based on
audio volume and respond at the end of user speech.
Show Child Parameters
Tools (functions) available to the model.
Show Child Parameters
How the model chooses tools. Options are auto, none, required, or
specify a function.
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
One OfMaximum number of output tokens for a single assistant response,
inclusive of tool calls. Provide an integer between 1 and 4096 to
limit output tokens, or inf for the maximum available tokens for a
given model. Defaults to inf.
RealtimeSessionCreateResponse
objectA new Realtime session configuration, with an ephermeral key. Default TTL
for keys is one minute.
Ephemeral key returned by the API.
Show Child Parameters
The set of modalities the model can respond with. To disable audio,
set this to [“text”].
The default system instructions (i.e. system message) prepended to model
calls. This field allows the client to guide the model on desired
responses. The model can be instructed on response content and format,
(e.g. “be extremely succinct”, “act friendly”, “here are examples of good
responses”) and on audio behavior (e.g. “talk quickly”, “inject emotion
into your voice”, “laugh frequently”). The instructions are not guaranteed
to be followed by the model, but they provide guidance to the model on the
desired behavior.
Note that the server sets default instructions which will be used if this
field is not set and are visible in the session.created event at the
start of the session.
The voice the model uses to respond. Voice cannot be changed during the
session once the model has responded with audio at least once. Current
voice options are alloy, ash, ballad, coral, echo sage,
shimmer and verse.
Allowed values:alloyashballadcoralechosageshimmerverse
The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.
The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.
Configuration for input audio transcription, defaults to off and can be
set to null to turn off once on. Input audio transcription is not native
to the model, since the model consumes audio directly. Transcription runs
asynchronously through Whisper and should be treated as rough guidance
rather than the representation understood by the model.
Show Child Parameters
Configuration for turn detection. Can be set to null to turn off. Server
VAD means that the model will detect the start and end of speech based on
audio volume and respond at the end of user speech.
Show Child Parameters
Tools (functions) available to the model.
Show Child Parameters
How the model chooses tools. Options are auto, none, required, or
specify a function.
Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.
One OfMaximum number of output tokens for a single assistant response,
inclusive of tool calls. Provide an integer between 1 and 4096 to
limit output tokens, or inf for the maximum available tokens for a
given model. Defaults to inf.
ReasoningEffort
stringo1 and o3-mini models only
Constrains effort on reasoning for
reasoning models.
Currently supported values are low, medium, and high. Reducing
reasoning effort can result in faster responses and fewer tokens used
on reasoning in a response.
Allowed values:lowmediumhigh
Default:medium
ResponseFormatJsonObject
objectThe type of response format being defined: json_object
Allowed values:json_object