> ## Documentation Index
> Fetch the complete documentation index at: https://docs.prem.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Audio Transcription

## Basic Audio Transcription

Transcribe audio files to text:

```typescript theme={"system"}
import createRvencClient from "@premai/api-sdk";
import fs from "fs";

const client = await createRvencClient({
  apiKey: process.env.API_KEY,
  clientKEK: process.env.CLIENT_KEK
});

const audioFile = fs.createReadStream("./audio.mp3");

const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
});

console.log(transcription.text);
```

## Transcription with Language Specification

Improve accuracy by specifying the language:

```typescript theme={"system"}
const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
  language: "en",
});

console.log(transcription.text);
```

## Transcription with Timestamps

Get word-level or segment-level timestamps:

```typescript theme={"system"}
const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
  language: "en",
  response_format: "verbose_json",
  timestamp_granularities: ["word", "segment"],
});

console.log(transcription);
```

## Transcription with Custom Prompt

Provide context to improve accuracy:

```typescript theme={"system"}
const transcription = await client.audio.transcriptions.create({
  file: audioFile,
  model: "openai/whisper-large-v3",
  prompt: "This is a medical consultation discussing patient symptoms and treatment options.",
});

console.log(transcription.text);
```