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

Api key auth

application/json

Body Required

Create an ephemeral API key with the given session configuration.

modalities array[string]

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

Values are text or audio. Default value is ["text", "audio"].
input_audio_format string

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.

Values are pcm16, g711_ulaw, or g711_alaw. Default value is pcm16.
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.
Hide input_audio_transcription attributes Show input_audio_transcription attributes object
- model string
  
  The model to use for transcription, current options are gpt-4o-transcribe, gpt-4o-mini-transcribe, and whisper-1.
  
  Values are gpt-4o-transcribe, gpt-4o-mini-transcribe, or 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.
Hide turn_detection attributes Show turn_detection attributes object
- type string
  
  Type of turn detection.
  
  Values are server_vad or semantic_vad. Default value is server_vad.
- eagerness string
  
  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.
  
  Values are low, medium, high, or auto. Default value is auto.
- 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. Not available for transcription sessions.
  
  Default value is true.
- 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. Not available for transcription sessions.
  
  Default value is true.
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.
Hide input_audio_noise_reduction attribute Show input_audio_noise_reduction attribute object
- 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.
  
  Values are near_field or far_field.
include array[string]
The set of items to include in the transcription. Current available items are:
- item.input_audio_transcription.logprobs

Responses

200 application/json

Session created successfully.
Hide response attributes Show response attributes object
- client_secret object Required
  
  Ephemeral key returned by the API. Only present when the session is created on the server via REST API.
  
  Hide client_secret attributes Show client_secret attributes object
  
  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 array[string]
  
  The set of modalities the model can respond with. To disable audio, set this to ["text"].
  
  Values are text or 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.
  
  Hide input_audio_transcription attributes Show input_audio_transcription attributes object
  
  model string
  
  The model to use for transcription. Can be gpt-4o-transcribe, gpt-4o-mini-transcribe, or whisper-1.
  
  Values are gpt-4o-transcribe, gpt-4o-mini-transcribe, or 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. The prompt should match the audio language.
- 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.
  
  Hide turn_detection attributes Show turn_detection attributes object
  
  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.

POST /realtime/transcription_sessions

curl \
 --request POST 'https://api.openai.com/v1/realtime/transcription_sessions' \
 --header "Authorization: Bearer $ACCESS_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":42.0,"prefix_padding_ms":42,"silence_duration_ms":42,"create_response":true,"interrupt_response":true},"input_audio_noise_reduction":{"type":"near_field"},"include":["string"]}'

Request examples

{
  "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": 42.0,
    "prefix_padding_ms": 42,
    "silence_duration_ms": 42,
    "create_response": true,
    "interrupt_response": true
  },
  "input_audio_noise_reduction": {
    "type": "near_field"
  },
  "include": [
    "string"
  ]
}

Response examples (200)

{
  "client_secret": {
    "value": "string",
    "expires_at": 42
  },
  "modalities": [
    "text"
  ],
  "input_audio_format": "string",
  "input_audio_transcription": {
    "model": "gpt-4o-transcribe",
    "language": "string",
    "prompt": "string"
  },
  "turn_detection": {
    "type": "string",
    "threshold": 42.0,
    "prefix_padding_ms": 42,
    "silence_duration_ms": 42
  }
}