STT Options - RunAnywhere Documentation

val options = SttOptions(
    language = "en",
    punctuation = true,
    wordTimestamps = true,
    diarization = false,
    maxSpeakers = null,
    translateToEnglish = false
)

val transcription = RunAnywhere.stt.transcribe(audio, options)

Fields

Field	Type	Default	Meaning
`language`	`String?`	none, auto-detect	BCP-47 code such as `"en"`
`punctuation`	`Boolean`	`DEFAULT_PUNCTUATION`	Insert punctuation and casing
`wordTimestamps`	`Boolean`	`DEFAULT_WORD_TIMESTAMPS`	Per-word timings
`diarization`	`Boolean`	`false`	Attribute speech to speakers
`maxSpeakers`	`Int?`	none	Cap the speaker count
`translateToEnglish`	`Boolean`	`false`	Translate rather than transcribe

The two defaults are public constants read from the proto defaults, so reference them rather than a literal:

SttOptions.DEFAULT_PUNCTUATION
SttOptions.DEFAULT_WORD_TIMESTAMPS

Language

Leave language unset to auto-detect. Set it when you know the language: detection costs time and picks wrong on short clips.

Word timestamps

SttOptions(wordTimestamps = true)

Use these for captions, or to seek a player to a spoken word.

Diarization

diarization = true labels speakers inside the transcription. For a standalone “who spoke when” answer over a recording, use the diarization namespace:

val result = RunAnywhere.diarization.diarize(AudioInput.file(path))

Translation

translateToEnglish = true returns English regardless of the source language.