Create transcription session

Create an ephemeral API token for use in client-side applications with the Realtime API specifically for realtime transcriptions. Can be configured with the same session parameters as the transcription_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/transcription_sessions

Create transcription session

cURL

curl --request POST \
  --url https://api.openai.com/v1/realtime/transcription_sessions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "modalities": [
    [
      "text",
      "audio"
    ]
  ],
  "input_audio_format": "pcm16",
  "input_audio_transcription": {
    "model": "gpt-4o-transcribe",
    "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,
  "include": [
    "<string>"
  ]
}
'

200

{
  "client_secret": {
    "value": "<string>",
    "expires_at": 123
  },
  "modalities": [
    "text"
  ],
  "input_audio_format": "<string>",
  "input_audio_transcription": {
    "model": "gpt-4o-transcribe",
    "language": "<string>",
    "prompt": "<string>"
  },
  "turn_detection": {
    "type": "<string>",
    "threshold": 123,
    "prefix_padding_ms": 123,
    "silence_duration_ms": 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 transcription session object configuration.

modalities · enum<string>[]

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

Available options: text, audio

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

input_audio_transcription · object

Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.

Show child attributes

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 child attributes

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.

Show child attributes

include · string[]

The set of items to include in the transcription. Current available items are:

• item.input_audio_transcription.logprobs

Response

200 - application/json

Session created successfully.

A new Realtime transcription session configuration.

When a session is created on the server via REST API, the session object also contains an ephemeral key. Default TTL for keys is one minute. This property is not present when a session is updated via the WebSocket API.

client_secret · object · required

Ephemeral key returned by the API. Only present when the session is created on the server via REST API.

Show child attributes

modalities · enum<string>[]

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

Available options: text, audio

input_audio_format · string

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

input_audio_transcription · object

Configuration of the transcription model.

Show child attributes

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.

Show child attributes