---
title: "Create an ephemeral API token for use in client-side applications with the Realtime API. Can be configured with the same session parameters as the `session.update` client event. It responds with a session object, plus a `client_secret` key which contains a usable ephemeral API token that can be used to authenticate browser clients for the Realtime API."
method: POST
path: "/realtime/sessions"
tags: ["Realtime"]
---

# Create an ephemeral API token for use in client-side applications with the Realtime API. Can be configured with the same session parameters as the \`session.update\` client event. It responds with a session object, plus a \`client_secret\` key which contains a usable ephemeral API token that can be used to authenticate browser clients for the Realtime API.

`POST /realtime/sessions`

## Request body

- RealtimeSessionCreateRequest — Realtime session object configuration.
  - `modalities` string[] — The set of modalities the model can respond with. To disable audio, set this to ["text"].
  - `model` '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' — The Realtime model used for this session.
  - `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` union
    - string
    - 'alloy' | 'ash' | 'ballad' | 'coral' | 'echo' | 'fable' | 'onyx' | 'nova' | 'sage' | 'shimmer' | 'verse'
  - `input_audio_format` 'pcm16' | 'g711_ulaw' | 'g711_alaw' — 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.
  - `output_audio_format` 'pcm16' | 'g711_ulaw' | 'g711_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.
  - `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](https://platform.openai.com/docs/api-reference/audio/createTranscription) 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.
    - `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](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (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](/docs/guides/speech-to-text#prompting). 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.
    - `type` 'server_vad' | 'semantic_vad' — Type of turn detection.
    - `eagerness` 'low' | 'medium' | 'high' | '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`.
    - `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 — Whether or not to automatically generate a response when a VAD stop event occurs.
    - `interrupt_response` boolean — 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 — 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.
    - `type` 'near_field' | 'far_field' — 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.
  - `tools` object[] — Tools (functions) available to the model.
    - `type` 'function' — The type of the tool, i.e. `function`.
    - `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 — 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]. For audio models a temperature of 0.8 is highly recommended for best performance.
  - `max_response_output_tokens` union — 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`.
    - integer
    - 'inf'

## Response `200`

Session created successfully.

- RealtimeSessionCreateResponse — 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.
    - `value` string, required — Ephemeral key usable in client environments to authenticate connections to the Realtime API. Use this in client-side environments rather than a standard API token, which should only be used server-side.
    - `expires_at` integer, required — Timestamp for when the token expires. Currently, all tokens expire after one minute.
  - `modalities` 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` union
    - string
    - 'alloy' | 'ash' | 'ballad' | 'coral' | 'echo' | 'fable' | 'onyx' | 'nova' | 'sage' | 'shimmer' | 'verse'
  - `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.
    - `model` string — The model to use for transcription, `whisper-1` is the only currently supported 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.
    - `type` string — Type of turn detection, only `server_vad` is currently supported.
    - `threshold` number — 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 — Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms.
    - `silence_duration_ms` integer — 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.
  - `tools` object[] — Tools (functions) available to the model.
    - `type` 'function' — The type of the tool, i.e. `function`.
    - `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 — 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` union — 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`.
    - integer
    - 'inf'

## Changes

- **2025-03-22** `41844462b873` — 11 breaking, 20 info
  - request property `turn_detection/type` was restricted to a list of enum values
  - removed the enum value `alloy` of the request property `voice`
  - removed the enum value `ash` of the request property `voice`
  - removed the enum value `ballad` of the request property `voice`
  - …27 more
- **2025-03-11** `6ab43fe7798e` — 1 info
  - added the new optional request property `turn_detection/interrupt_response`
- **2025-01-31** `fc164a27fdb9` — 5 info
  - added the new optional request property `input_audio_transcription/language`
  - added the new optional request property `input_audio_transcription/prompt`
  - the response property `client_secret` became required for the status `200`
  - the response property `client_secret/expires_at` became required for the status `200`
  - …1 more
- **2025-01-21** `47138a7dd8b9` — 1 info
  - the request property `model` became optional
- **2025-01-21** `0d83ef8a5f65` — 1 breaking
  - the request property `model` became required

[Full history](https://skmtc.dev/openai/apis/openapi/changes/realtime/sessions/post.md)

---

[API](https://skmtc.dev/openai/apis/openapi.md) · [All operations](https://skmtc.dev/openai/apis/openapi/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/openai/openapi/revisions/86ed5d923809/schema)