elevenlabs-prod-checklist

name	elevenlabs-prod-checklist
description	Execute an ElevenLabs production deployment checklist with health checks and rollback. Use when deploying TTS/voice integrations to production, preparing for launch, or implementing go-live procedures for ElevenLabs-powered apps. Trigger with "elevenlabs production", "deploy elevenlabs", "elevenlabs go-live", "elevenlabs launch checklist", or "production TTS".
allowed-tools	Read, Bash(curl:*), Bash(jq:*), Grep
version	1.6.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","voice","ai","elevenlabs","production","deployment"]
compatibility	Designed for Claude Code

ElevenLabs Production Checklist

Overview

Complete checklist for deploying ElevenLabs TTS/voice integrations to production. Covers API configuration, health checks, circuit breakers, monitoring, and rollback procedures. The deep code for the resilience primitives lives in references/ so this file stays a fast, scannable runbook — drill in when you need the full implementation.

Prerequisites

• Staging environment tested and verified
• Production API key (separate from dev/staging)
• Monitoring and alerting infrastructure ready

Instructions

Step 1: Pre-Deployment Verification

Walk the checklist below. Every unchecked box is a launch blocker.

Configuration:

• Production API key stored in secure vault (not in code)
• ELEVENLABS_API_KEY set in deployment platform's secrets
• Webhook secret configured (if using webhooks)
• Using production model ID (eleven_multilingual_v2 or eleven_v3)

Code Quality:

• All tests passing with mocked ElevenLabs SDK
• No hardcoded API keys (scan with grep -r "sk_" src/)
• Error handling covers 400, 401, 404, 429, 5xx responses
• Rate limiting implemented matching plan concurrency limit
• Text splitting handles inputs > 5,000 characters
• Audio output format appropriate for use case

Quota Planning:

• Estimated monthly character usage fits within plan limit
• Usage-based billing enabled (Creator+ plans) if needed
• Flash/Turbo models used where latency matters more than quality

Step 2: Wire the resilience primitives