Chapter 755: transcribe()

Core Idea

:::warning Unstable API: This package is experimental for the moment. As we test it, we might make a few changes to the API and switch to a WebGPU-based backend in the future.

Key Concepts

• Requirements
• Example
• Arguments
• channelWaveform
• model
• language?
• onProgress?
• onTranscriptionChunk?

Code Examples

const file = new File([], 'audio.wav');

const channelWaveform = await resampleTo16Khz({
  file,
  onProgress: (p) => console.log(`Resampling audio (${Math.round(p * 100)}%)...`),
});


const {transcription} = await transcribe({
  channelWaveform,
  model: 'tiny.en',
  onProgress: (p) => console.log(`Transcribing (${Math.round(p * 100)}%)...`),
});

console.log(transcription.map((t) => t.text).join(' '));

• What it demonstrates: Usage pattern for transcribe() from the official docs.

Key Takeaways

1. Understand requirements when working with transcribe().
2. Understand example when working with transcribe().
3. Understand arguments when working with transcribe().
4. Understand channelwaveform when working with transcribe().
5. Understand model when working with transcribe().

Connects To

• Convert to Captions: related page in the Whisper Web (@remotion/whisper-web) section.
• Download Whisper Model: related page in the Whisper Web (@remotion/whisper-web) section.
• Install Whisper cpp: related page in the Whisper Web (@remotion/whisper-web) section.