I want to use speech to text API of open ai in my Next.js app. As don't have separate server i am using the code for api
// pages/api/audiototext.ts
import { NextApiRequest,NextApiResponse } from "next";
export const config = {
api: {
bodyParser: false,
},
}
export default async function handler(req: NextApiRequest, res: NextApiResponse) {
try{
fetch('https://api.openai.com/v1/audio/transcriptions',{
method: 'POST',
headers: {
'Authorization': `Bearer ${process.env.NEXT_PUBLIC_OPENAI_API_KEY}`,
},
body:req.body
})
.then(response => response.json())
.then(data => {
console.log(data)
res.status(200).json(data)
})
.catch((error) => {
res.status(500).json({error:error})
})
}
catch(error){
res.status(500).json({error:error})
}
}
and on client side the code is
const formData = new FormData();
formData.append('file', audioFileU);
formData.append('model', 'whisper-1');
const response = await fetch(`/api/audiototext`, {
method: 'POST',
body: formData, // Do not set Content-Type here
});
I am getting too many errors.
I tried Formidable and multer in both i am getting errors like sometime on server i am getting Boundary not found error during parsing sometimes i am getting error through open ai that Could not parse multipart form