google-genai-kotlin/com.google.genai.kotlin.types/AudioTranscriptionConfig

AudioTranscriptionConfig

@Serializable

data class AudioTranscriptionConfig(val languageCodes: List<String>? = null, val languageAuto: LanguageAuto? = null, val languageHints: LanguageHints? = null, val customVocabulary: List<String>? = null, val adaptationPhrases: List<String>? = null, val diarization: Boolean? = null, val wordTimestamp: Boolean? = null, val mode: AudioTranscriptionConfigMode? = null)

The audio transcription configuration in Setup.

Constructors

constructor(languageCodes: List<String>? = null, languageAuto: LanguageAuto? = null, languageHints: LanguageHints? = null, customVocabulary: List<String>? = null, adaptationPhrases: List<String>? = null, diarization: Boolean? = null, wordTimestamp: Boolean? = null, mode: AudioTranscriptionConfigMode? = null)

Properties

adaptationPhrases

val adaptationPhrases: List<String>? = null

Deprecated. A list of phrases used for speech adaptation, which biases the ASR model to improve recognition of these specific terms.

customVocabulary

val customVocabulary: List<String>? = null

A list of custom vocabulary phrases, which biases the ASR model to improve recognition of these specific terms.

diarization

val diarization: Boolean? = null

Configures speaker diarization.

languageAuto

val languageAuto: LanguageAuto? = null

Deprecated: Auto-detection is now the default when language_codes is omitted. This field will be removed in a future version.

languageCodes

val languageCodes: List<String>? = null

BCP-47 language codes providing hints about the languages present in the audio. If omitted or empty, defaults to automatic language detection.

languageHints

val languageHints: LanguageHints? = null

Deprecated: Use top-level language_codes instead. This field will be removed in a future version.

mode

val mode: AudioTranscriptionConfigMode? = null

Optional. Configures transcription mode. Supported values: VERBATIM, SMART. If unspecified, defaults to VERBATIM transcription. In SMART mode, the model performs disfluency removal (eliminating filler words, repetitions, and false starts), light grammatical cleanup, automatic formatting (paragraphs, bullet points, numbered lists), and minor user edits (inline self-corrections). Timestamps and diarization are incompatible with mode SMART.

wordTimestamp

val wordTimestamp: Boolean? = null

Configures word-level timestamp generation.