AWS S3 to OpenAI Whisper via Node.js stream

README.md

Current (2023-03-01) OpenAI Whisper API expects a file uploaded as part of multipart/form-data in POST request. I initially struggled to use this API inside Node.js with an audio file stored inside an AWS s3 bucket, so I decided to share this snippet:

The API usage example from the OpenAI docs:

curl --request POST \
  --url https://api.openai.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer TOKEN' \
  --header 'Content-Type: multipart/form-data' \
  --form file=@/path/to/file/openai.mp3 \
  --form model=whisper-1

See the Node.js + AWS S3 example below:

index-aws@2.js

import fetch from "node-fetch";
import AWS from "aws-sdk"; // v2
import fs from "fs";
import FormData from "form-data";

// Set the region and access keys for your AWS account
AWS.config.update({
    region: 'eu-central-1',
    accessKeyId: '***',
    secretAccessKey: '***'
});

// Create an S3 client
const s3 = new AWS.S3();

// Set the bucket and file key
const bucketName = 'openai-sample';
const fileKey = 'path/to/file/openai.mp3';

// Set the parameters for the S3 getObject operation
const params = {
    Bucket: bucketName,
    Key: fileKey
};

// Get audio metadata to retrieve size and type
s3.headObject(params, function(err, data) {
    if (err) throw err;
    
    // Get read object stream
    const s3Stream = s3.getObject(params)
      .createReadStream();

    // create form data to be send to whisper api
    const formData = new FormData();
    // append stream with a file
    formData.append('file', s3Stream, {
        contentType: data.ContentType,
        knownLength: data.ContentLength,
        filename: fileKey
    });
    formData.append('model', 'whisper-1');


    fetch('https://api.openai.com/v1/audio/transcriptions', {
        method: 'POST',
        body: formData,
        headers: {
            'Authorization': 'Bearer TOKEN',
            ...formData.getHeaders()
        }
    }).then(res => res.json()).then(json => console.log(json.text));
});

index-aws@3.js

import fetch from "node-fetch";
import {S3Client, GetObjectCommand, HeadObjectCommand} from '@aws-sdk/client-s3'; //v3
import FormData from "form-data";

/*
curl --request POST \
  --url https://api.openai.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer TOKEN' \
  --header 'Content-Type: multipart/form-data' \
  --form file=@/path/to/file/openai.mp3 \
  --form model=whisper-1
 */

// Set the region and access keys for your AWS account
const s3 = new S3Client({
    region: 'eu-central-1',
    credentials: {
        accessKeyId: '***',
        secretAccessKey: '***'
    }
});

// Set the bucket and file key
const bucketName = 'openai-sample';
const fileKey = 'path/to/file/openai.mp3';

// Set the parameters for the S3 getObject operation
const params = {
    Bucket: bucketName,
    Key: fileKey
};

// Call the S3 getObject operation with the specified parameters
const getObjectOutput = await s3.send(new GetObjectCommand(params));

const formData = new FormData();
// getObjectResult.Body is a ReadableStream
formData.append('file', getObjectOutput.Body, {
    contentType: getObjectOutput.ContentType,
    knownLength: getObjectOutput.ContentLength,
    filename: fileKey
});
formData.append('model', 'whisper-1');

const result = await fetch('https://api.openai.com/v1/audio/transcriptions', {
    method: 'POST',
    body: formData,
    headers: {
        'Authorization': 'Bearer TOKEN',
        ...formData.getHeaders()
    }
}).then(res => res.json());

console.log(result);