POST
/
realtime
/
sessions
Create session
curl --request POST \
  --url https://api.openai.com/v1/realtime/sessions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "modalities": [
    [
      "text",
      "audio"
    ]
  ],
  "model": "gpt-4o-realtime-preview",
  "instructions": "<string>",
  "voice": "ash",
  "input_audio_format": "pcm16",
  "output_audio_format": "pcm16",
  "input_audio_transcription": {
    "model": "<string>",
    "language": "<string>",
    "prompt": "<string>"
  },
  "turn_detection": {
    "type": "server_vad",
    "eagerness": "auto",
    "threshold": 123,
    "prefix_padding_ms": 123,
    "silence_duration_ms": 123,
    "create_response": true,
    "interrupt_response": true
  },
  "input_audio_noise_reduction": null,
  "tools": [
    {
      "type": "function",
      "name": "<string>",
      "description": "<string>",
      "parameters": {}
    }
  ],
  "tool_choice": "auto",
  "temperature": 0.8,
  "max_response_output_tokens": 123
}'
{
  "client_secret": {
    "value": "<string>",
    "expires_at": 123
  },
  "modalities": [
    "text"
  ],
  "instructions": "<string>",
  "voice": "ash",
  "input_audio_format": "<string>",
  "output_audio_format": "<string>",
  "input_audio_transcription": {
    "model": "<string>"
  },
  "turn_detection": {
    "type": "<string>",
    "threshold": 123,
    "prefix_padding_ms": 123,
    "silence_duration_ms": 123
  },
  "tools": [
    {
      "type": "function",
      "name": "<string>",
      "description": "<string>",
      "parameters": {}
    }
  ],
  "tool_choice": "<string>",
  "temperature": 123,
  "max_response_output_tokens": 123
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Create an ephemeral API key with the given session configuration.

Realtime session object configuration.

​
modalities
enum<string>[]

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

​
model
enum<string>

The Realtime model used for this session.

Available options:
gpt-4o-realtime-preview,
gpt-4o-realtime-preview-2024-10-01,
gpt-4o-realtime-preview-2024-12-17,
gpt-4o-mini-realtime-preview,
gpt-4o-mini-realtime-preview-2024-12-17
​
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

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.

Example:

"ash"

​
input_audio_format
enum<string>
default: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.

Available options:
pcm16,
g711_ulaw,
g711_alaw
​
output_audio_format
enum<string>
default: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.

Available options:
pcm16,
g711_ulaw,
g711_alaw
​
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.

​
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.

​
input_audio_noise_reduction
object

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.

​
tools
object[]

Tools (functions) available to the model.

​
tool_choice
string
default:auto

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

​
temperature
number
default: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

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.

Response

200 - application/json

Session created successfully.

A new Realtime session configuration, with an ephermeral key. Default TTL for keys is one minute.

​
client_secret
object
required

Ephemeral key returned by the API.

​
modalities
enum<string>[]

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

​
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

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.

Example:

"ash"

​
input_audio_format
string

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.

​
output_audio_format
string

The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.

​
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 Whisper and should be treated as rough guidance rather than the representation understood by the model.

​
turn_detection
object

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.

​
tools
object[]

Tools (functions) available to the model.

​
tool_choice
string

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

​
temperature
number

Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.

​
max_response_output_tokens

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.