Consider using stream for faster TTS response

[jazelly]

Use stream to pass into eleven-labs for early TTS, e.g.

import { openai } from '@ai-sdk/openai'
import { StreamingTextResponse, streamText } from 'ai'
 
export async function POST(req) {
  const { messages } = await req.json()
  const result = await streamText({
    model: openai('gpt-4-turbo'),
    messages,
  })
 
  return new StreamingTextResponse(result.toAIStream())
}

and elevenlabs TTS streaming api

I think currently the app is serializing prompt and TTS? With streaming, it should significantly reduce the latency