elevenlabs-deploy-integration

# ElevenLabs Deploy Integration ## Overview Deploy ElevenLabs TTS/voice applications to cloud platforms. Covers Vercel (serverless), Fly.io (containers), and Google Cloud Run with proper secrets management, timeout configuration, and streaming support. ## Prerequisites - ElevenLabs API key for production - Platform CLI installed (`vercel`, `fly`, or `gcloud`) - Application code tested locally ## Instructions ### Vercel Deployment (Serverless) **Key constraint:** Vercel functions have a 10-second timeout on Hobby (30s on Pro). Use Flash model for speed. ```bash # Set secrets vercel env add ELEVENLABS_API_KEY production vercel env add ELEVENLABS_API_KEY preview # Deploy vercel --prod ``` **API Route (Next.js / Vercel):** ```typescript // app/api/tts/route.ts import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js"; import { NextResponse } from "next/server"; export const runtime = "nodejs"; export const maxDuration = 30; // Vercel Pro max const client = new ElevenLabsClient(); export async function POST(req: Request) { const { text, voiceId = "21m00Tcm4TlvDq8ikWAM" } = await req.json(); if (!text || text.length > 5000) { return NextResponse.json( { error: "Text required, max 5000 characters" }, { status: 400 } ); } try { const audio = await client.textToSpeech.convert(voiceId, { text, model_id: "eleven_flash_v2_5", // Fast for serverless output_format: "mp3_22050_32", voice_settings: { stability...