Function: generateTranscription()

function generateTranscription<TAdapter, TStream>(options): TranscriptionActivityResult<TStream>;

Defined in: packages/ai/src/activities/generateTranscription/index.ts:164

Transcription activity - converts audio to text.

Uses AI speech-to-text models to transcribe audio content.

Type Parameters

TAdapter

TAdapter extends TranscriptionAdapter<string, TranscriptionProviderOptions<TAdapter>>

TStream

TStream extends boolean = false

Parameters

options

TranscriptionActivityOptions<TAdapter, TStream>

Returns

TranscriptionActivityResult<TStream>

Examples

import { generateTranscription } from '@tanstack/ai'
import { openaiTranscription } from '@tanstack/ai-openai'

const result = await generateTranscription({
  adapter: openaiTranscription('whisper-1'),
  audio: audioFile, // File, Blob, or base64 string
  language: 'en'
})

console.log(result.text)

const result = await generateTranscription({
  adapter: openaiTranscription('whisper-1'),
  audio: audioFile,
  responseFormat: 'verbose_json'
})

result.segments?.forEach(segment => {
  console.log(`[${segment.start}s - ${segment.end}s]: ${segment.text}`)
})

for await (const chunk of generateTranscription({
  adapter: openaiTranscription('whisper-1'),
  audio: audioFile,
  stream: true
})) {
  console.log(chunk)
}