Constructor Detail

Method Detail

• format

   final Optional<RealtimeAudioConfig.Input.Format> format()

  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.

• noiseReduction

   final Optional<RealtimeAudioConfig.Input.NoiseReduction> noiseReduction()

  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.

• transcription

   final Optional<RealtimeAudioConfig.Input.Transcription> transcription()

  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.

• turnDetection

   final Optional<RealtimeAudioConfig.Input.TurnDetection> turnDetection()

  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 conjunction 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.

• _format

   final JsonField<RealtimeAudioConfig.Input.Format> _format()

  Returns the raw JSON value of format.

  Unlike format, this method doesn't throw if the JSON field has an unexpected type.

• _noiseReduction

   final JsonField<RealtimeAudioConfig.Input.NoiseReduction> _noiseReduction()

  Returns the raw JSON value of noiseReduction.

  Unlike noiseReduction, this method doesn't throw if the JSON field has an unexpected type.

• _transcription

   final JsonField<RealtimeAudioConfig.Input.Transcription> _transcription()

  Returns the raw JSON value of transcription.

  Unlike transcription, this method doesn't throw if the JSON field has an unexpected type.

• _turnDetection

   final JsonField<RealtimeAudioConfig.Input.TurnDetection> _turnDetection()

  Returns the raw JSON value of turnDetection.

  Unlike turnDetection, this method doesn't throw if the JSON field has an unexpected type.

• _additionalProperties

   final Map<String, JsonValue> _additionalProperties()

• toBuilder

   final RealtimeAudioConfig.Input.Builder toBuilder()

• validate

   final RealtimeAudioConfig.Input validate()

• isValid

   final Boolean isValid()

• equals

   Boolean equals(Object other)

• hashCode

   Integer hashCode()

• toString

   String toString()

• builder

   final static RealtimeAudioConfig.Input.Builder builder()

  Returns a mutable builder for constructing an instance of Input.