STT Options

interface STTOptions {
  /** Language code for transcription */
  language?: string

  /** Enable punctuation in output */
  punctuation?: boolean

  /** Enable speaker diarization (multi-speaker) */
  diarization?: boolean

  /** Enable word-level timestamps */
  wordTimestamps?: boolean

  /** Audio sample rate (default: 16000) */
  sampleRate?: number
}

// English
const english = await RunAnywhere.transcribe(audioBase64, { language: 'en' })

// Spanish
const spanish = await RunAnywhere.transcribe(audioBase64, { language: 'es' })

// French
const french = await RunAnywhere.transcribe(audioBase64, { language: 'fr' })

// Auto-detect (slower)
const auto = await RunAnywhere.transcribe(audioBase64)

// Without punctuation (default for some models)
const noPunct = await RunAnywhere.transcribe(audioBase64, {
  language: 'en',
  punctuation: false,
})
// "hello how are you today"

// With punctuation
const withPunct = await RunAnywhere.transcribe(audioBase64, {
  language: 'en',
  punctuation: true,
})
// "Hello, how are you today?"

const result = await RunAnywhere.transcribe(audioBase64, {
  language: 'en',
  wordTimestamps: true,
})

console.log('Transcription:', result.text)

// Each segment contains word-level timing
for (const segment of result.segments) {
  console.log(`[${segment.startTime.toFixed(2)}s - ${segment.endTime.toFixed(2)}s] ${segment.text}`)
}

interface Subtitle {
  start: number
  end: number
  text: string
}

async function generateSubtitles(audioBase64: string): Promise<Subtitle[]> {
  const result = await RunAnywhere.transcribe(audioBase64, {
    language: 'en',
    wordTimestamps: true,
  })

  return result.segments.map((segment) => ({
    start: segment.startTime,
    end: segment.endTime,
    text: segment.text.trim(),
  }))
}

// Convert to SRT format
function toSRT(subtitles: Subtitle[]): string {
  return subtitles
    .map((sub, i) => {
      const start = formatSRTTime(sub.start)
      const end = formatSRTTime(sub.end)
      return `${i + 1}\n${start} --> ${end}\n${sub.text}\n`
    })
    .join('\n')
}

function formatSRTTime(seconds: number): string {
  const h = Math.floor(seconds / 3600)
  const m = Math.floor((seconds % 3600) / 60)
  const s = Math.floor(seconds % 60)
  const ms = Math.floor((seconds % 1) * 1000)
  return `${h.toString().padStart(2, '0')}:${m.toString().padStart(2, '0')}:${s.toString().padStart(2, '0')},${ms.toString().padStart(3, '0')}`
}

const result = await RunAnywhere.transcribe(audioBase64, {
  language: 'en',
  diarization: true,
})

// Segments include speaker IDs
for (const segment of result.segments) {
  console.log(`[Speaker ${segment.speakerId}]: ${segment.text}`)
}

// Standard 16kHz (default, recommended for STT)
const standard = await RunAnywhere.transcribeBuffer(samples)

// Higher quality 44.1kHz (will be downsampled internally)
const highQuality = await RunAnywhere.transcribeBuffer(samples, {
  sampleRate: 44100,
})

// Load STT model with specific type
await RunAnywhere.loadSTTModel(modelPath, 'whisper')

// Check if model is loaded
const isLoaded = await RunAnywhere.isSTTModelLoaded()

// Unload when done
await RunAnywhere.unloadSTTModel()

// Full-featured transcription
const result = await RunAnywhere.transcribe(audioBase64, {
  language: 'en',
  punctuation: true,
  wordTimestamps: true,
})

// Access all result data
console.log('Text:', result.text)
console.log('Language:', result.language)
console.log('Confidence:', result.confidence)
console.log('Duration:', result.duration, 'seconds')
console.log('Segments:', result.segments.length)

// Alternatives (if available)
if (result.alternatives.length > 0) {
  console.log('Alternatives:')
  result.alternatives.forEach((alt, i) => {
    console.log(`  ${i + 1}. ${alt.text} (confidence: ${alt.confidence})`)
  })
}