---
title: "Transcribe audio to text"
section: "frontend/predictions"
platforms: ["angular", "javascript", "nextjs", "react", "react-native", "vue"]
gen: 2
last-updated: "2026-03-25T17:40:00.000Z"
url: "https://docs.amplify.aws/react/frontend/predictions/transcribe-audio/"
---

export async function getStaticPaths() {
  return getCustomStaticPath(meta.platforms);
}

<Callout informational>

**Note:** Make sure to complete the [getting started](/[platform]/build-a-backend/add-aws-services/predictions/set-up-predictions/) section first, where you will set up the IAM roles with the right policy actions

</Callout>

## Working with the API

You can transcribe a PCM Audio byte buffer to Text, such as a recording from microphone.

```ts
import { Predictions } from '@aws-amplify/predictions';

const { transcription } = await Predictions.convert({
  transcription: {
    source: {
      bytes
    }
  }
})
```

To view the complete list of all the supported languages and language specific features refer to [the supported languages list](https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html). The language data input type has to support streaming for it to work with Amplify Predictions.