Overview

At Retell, we’ve made reliability our top priority. Our platform is built on enterprise-grade infrastructure to ensure consistent, high-quality performance for all your voice AI needs.

We focus on three key areas to maintain exceptional service quality:

1. Phone Call Performance

   • Reliable handling of inbound and outbound calls
   • Consistent connection throughout conversations
   • High voice quality

2. Agent Reliability

   • Consistent low latency during interactions

3. Agent Performance

   • Accurate speech transcription
   • Strict adherence to prompt instructions

​

Our Commitment to Reliability

At Retell, we gurantee >99.9% uptime. To acheive this, we’ve invested on the following areas:

1. Enterprise-grade infrastructure
2. Fallbacks and Resilience Features
3. 24/7 Monitoring and Alerting
4. 24/7 Support

​

Detailed Overview

1. Enterprise-grade infrastructure: We conduct extensive load testing on high traffic and maintain dedicated auto-scaling and provisioning to handle varying loads. Our enterprise-grade compute, networking, and infrastructure ensure stable performance.

   • We guarantee >99.9% uptime - Subscribe to our Status Page to get notified about any issues.
   • Self-hosted models to reduce third-party dependencies.

2. Proactive Monitoring: We maintain 24/7 latency monitoring and alerting systems to catch and address issues before they impact your operations.

   • Including ASR, TTS, LLM, Knowledge base, time to first token, and network latency distribution, p75, p90, p95, p99 latencies.
   • Failed calls count, ASR, LLM, TTS timeout, and error rate.
   • Server CPU, GPU, memory, and network usage. Database, API response time.

3. Resilience Features: We’ve implemented fallbacks, retries, and other features to improve reliability:

   • Branded Call/Verified Phone Number Features to improve call pick up rate and allowlist carriers calls
   • TTS Fallback to ensure conversation experience even when TTS fails
   • Upcoming features:
     • LLM fallback as an optional feature
     • Automated test cases that run after every prompt change
     • Additional self-hosted models to reduce third-party dependencies

4. Support System: Our dedicated support team is ready to assist if any issues arise.

   • 7 Days/Week on-call schedule including all founders.
   • 6 hours minimum support SLA between 9 AM to 9 PM PST. (Lower for enterprise customers)
   • Not your average emotional support - all support are done by engineers, who built the features you are using. A developer supporting another developer.