Create session

Request body

• modalities

  object

  The set of modalities the model can respond with. To disable audio, set this to ["text"].

• model

  string

  The Realtime model used for this session.
  Show possible types

  • gpt-4o-realtime-preview

    string

  • gpt-4o-realtime-preview-2024-10-01

    string

  • gpt-4o-realtime-preview-2024-12-17

    string

  • gpt-4o-mini-realtime-preview

    string

  • gpt-4o-mini-realtime-preview-2024-12-17

    string

• instructions

  string

  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.

• voice

  string

  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, fable, onyx, nova, sage, shimmer, and verse.

  Show possible types

  • voice

    string

  • voice

    string

    Show possible types

    • alloy

      string

    • ash

      string

    • ballad

      string

    • coral

      string

    • echo

      string

    • fable

      string

    • onyx

      string

    • nova

      string

    • sage

      string

    • shimmer

      string

    • verse

      string

• input_audio_format

  string

  Defaults: pcm16

  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.

  Show possible types

  • pcm16

    string

  • g711_ulaw

    string

  • g711_alaw

    string

• output_audio_format

  string

  Defaults: pcm16

  The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw. For pcm16, output audio is sampled at a rate of 24kHz.

  Show possible types

  • pcm16

    string

  • g711_ulaw

    string

  • g711_alaw

    string

• input_audio_transcription

  object

  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 the /audio/transcriptions endpoint and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

  Show properties

  • model

    string

    The model to use for transcription, current options are gpt-4o-transcribe, gpt-4o-mini-transcribe, and whisper-1.

  • language

    string

    The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

  • prompt

    string

    An optional text to guide the model's style or continue a previous audio segment. For whisper-1, the prompt is a list of keywords. For gpt-4o-transcribe models, the prompt is a free text string, for example "expect words related to technology".

• turn_detection

  object

  Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to null to turn off, in which case the client must manually trigger model response. 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. Semantic VAD is more advanced and uses a turn detection model (in conjuction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency.

  Show properties

  • type

    string

    Defaults: server_vad

    Type of turn detection.
    Show possible types

    • server_vad

      string

    • semantic_vad

      string

  • eagerness

    string

    Defaults: auto

    Used only for semantic_vad mode. The eagerness of the model to respond. low will wait longer for the user to continue speaking, high will respond more quickly. auto is the default and is equivalent to medium.

    Show possible types

    • low

      string

    • medium

      string

    • high

      string

    • auto

      string

  • threshold

    number

    Used only for server_vad mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

  • prefix_padding_ms

    integer

    Used only for server_vad mode. Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.

  • silence_duration_ms

    integer

    Used only for server_vad mode. Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

  • create_response

    boolean

    Defaults: true

    Whether or not to automatically generate a response when a VAD stop event occurs.

  • interrupt_response

    boolean

    Defaults: true

    Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. conversation of auto) when a VAD start event occurs.

• input_audio_noise_reduction

  object

  Defaults: null

  Configuration for input audio noise reduction. This can be set to null to turn off. Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.

  Show properties

  • type

    string

    Type of noise reduction. near_field is for close-talking microphones such as headphones, far_field is for far-field microphones such as laptop or conference room microphones.

    Show possible types

    • near_field

      string

    • far_field

      string

• tools

  array

  Tools (functions) available to the model.
  Show possible types

  • items

    object

    Show properties

    • type

      string

      The type of the tool, i.e. function.

      Show possible types

      • function

        string

    • name

      string

      The name of the function.

    • description

      string

      The description of the function, including guidance on when and how to call it, and guidance about what to tell the user when calling (if anything).

    • parameters

      object

      Parameters of the function in JSON Schema.

• tool_choice

  string

  Defaults: auto

  How the model chooses tools. Options are auto, none, required, or specify a function.

• temperature

  number

  Defaults: 0.8

  Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance.

• max_response_output_tokens

  integer or string

  Maximum 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.

  Show possible types

  • max_response_output_tokens

    integer

  • max_response_output_tokens

    string

    Show possible types

    • inf

      string

Response