STT Options

data class STTOptions(
    val language: String = "en",              // BCP-47 language code
    val detectLanguage: Boolean = false,      // Auto-detect spoken language
    val enablePunctuation: Boolean = true,    // Add punctuation
    val enableDiarization: Boolean = false,   // Identify speakers
    val maxSpeakers: Int? = null,             // Max speakers to identify
    val enableTimestamps: Boolean = true,     // Word-level timestamps
    val vocabularyFilter: List<String> = emptyList(),  // Custom vocabulary
    val audioFormat: AudioFormat = AudioFormat.PCM,
    val sampleRate: Int = 16000               // Audio sample rate
)

val options = STTOptions(
    language = "en",
    enablePunctuation = true
)

val options = STTOptions(
    detectLanguage = true,
    enablePunctuation = true
)

val result = RunAnywhere.transcribeWithOptions(audioData, options)
println("Detected language: ${result.detectedLanguage}")

val options = STTOptions(
    language = "en",
    enableTimestamps = true
)

val result = RunAnywhere.transcribeWithOptions(audioData, options)
result.wordTimestamps?.forEach { word ->
    println("[${word.startTime}s - ${word.endTime}s]: ${word.word}")
}

val options = STTOptions(
    language = "en",
    enableDiarization = true,
    maxSpeakers = 2
)

val options = STTOptions(
    language = "en",
    vocabularyFilter = listOf(
        "RunAnywhere",
        "Kotlin",
        "ONNX",
        "llama.cpp"
    )
)

enum class AudioFormat {
    PCM,    // Raw PCM samples
    WAV,    // WAV container
    MP3,    // MP3 compressed
    AAC,    // AAC compressed
    OGG,    // Ogg Vorbis
    OPUS,   // Opus codec
    FLAC    // FLAC lossless
}

val result = RunAnywhere.transcribeWithOptions(audioData, options)

val metadata = result.metadata
println("Model: ${metadata.modelId}")
println("Processing time: ${metadata.processingTime}s")
println("Audio length: ${metadata.audioLength}s")
println("Real-time factor: ${metadata.realTimeFactor}x")