Constructor Detail

Method Detail

• type

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder type(TranscriptionCreateParams.ChunkingStrategy.VadConfig.Type type)

  Must be set to server_vad to enable manual chunking using server side VAD.

• type

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder type(MultipartField<TranscriptionCreateParams.ChunkingStrategy.VadConfig.Type> type)

  Sets Builder.type to an arbitrary multipart value.

  You should usually call Builder.type with a well-typed Type value instead. This method is primarily for setting the field to an undocumented or not yet supported value.

• prefixPaddingMs

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder prefixPaddingMs(Long prefixPaddingMs)

  Amount of audio to include before the VAD detected speech (in milliseconds).

• prefixPaddingMs

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder prefixPaddingMs(MultipartField<Long> prefixPaddingMs)

  Sets Builder.prefixPaddingMs to an arbitrary multipart value.

  You should usually call Builder.prefixPaddingMs with a well-typed Long value instead. This method is primarily for setting the field to an undocumented or not yet supported value.

• silenceDurationMs

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder silenceDurationMs(Long silenceDurationMs)

  Duration of silence to detect speech stop (in milliseconds). With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

• silenceDurationMs

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder silenceDurationMs(MultipartField<Long> silenceDurationMs)

  Sets Builder.silenceDurationMs to an arbitrary multipart value.

  You should usually call Builder.silenceDurationMs with a well-typed Long value instead. This method is primarily for setting the field to an undocumented or not yet supported value.

• threshold

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder threshold(Double threshold)

  Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

• threshold

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder threshold(MultipartField<Double> threshold)

  Sets Builder.threshold to an arbitrary multipart value.

  You should usually call Builder.threshold with a well-typed Double value instead. This method is primarily for setting the field to an undocumented or not yet supported value.

• additionalProperties

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder additionalProperties(Map<String, JsonValue> additionalProperties)

• putAdditionalProperty

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder putAdditionalProperty(String key, JsonValue value)

• putAllAdditionalProperties

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder putAllAdditionalProperties(Map<String, JsonValue> additionalProperties)

• removeAdditionalProperty

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder removeAdditionalProperty(String key)

• removeAllAdditionalProperties

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig.Builder removeAllAdditionalProperties(Set<String> keys)

• build

   final TranscriptionCreateParams.ChunkingStrategy.VadConfig build()

  Returns an immutable instance of VadConfig.

  Further updates to this Builder will not mutate the returned instance.

  The following fields are required:

  .type()