Updated the speaking evaluation to use the new endpoint

src/pages/api/evaluate/speaking.ts

@@ -29,8 +29,8 @@ async function handler(req: NextApiRequest, res: NextApiResponse) {
 		const snapshot = await uploadBytes(audioFileRef, binary);
 
 		const backendRequest = await axios.post(
-			`${process.env.BACKEND_URL}/speaking_task_1`,
-			{question: fields.question, answer: snapshot.metadata.fullPath},
+			`${process.env.BACKEND_URL}/speaking_task_3`,
+			{answers: [{question: fields.question, answer: snapshot.metadata.fullPath}]},
 			{
 				headers: {
 					Authorization: `Bearer ${process.env.BACKEND_JWT}`,