Concurrency estimator | ElevenLabs Documentation

The concurrency estimator recommends a concurrency limit from your traffic volume, how long each request lasts and when your traffic happens. Share the result with your account team when you discuss your plan.

Voice agents

Chat agents

Text to Speech API

Speech to Text API

Type of calls

Phone or web calls with an ElevenLabs agent where callers reach you, such as support lines, hotlines or reservations.

Traffic

How many calls do you handle?

Your normal volume across the whole contact center.

Average call length, in minutes

Talk time, from answer to hang-up.

When do you take calls?

Days per week

Used to spread weekly and monthly volumes across your active days.

Advanced

How solid are these numbers?

Rougher estimates get a larger cushion.

How sure do you need to be of covering normal ups and downs?

Higher confidence adds more headroom above your average.

Recommended concurrency limit

20 to 28 concurrent calls

The minimum relies on burst for normal ups and downs. The maximum covers them without burst.

With a limit of 20, burst lets you briefly run up to 60, so your expected peak of 27.3 fits. Burst is for occasional spikes: calls above your limit are billed at twice the standard rate and get lower priority for speech processing. A limit of 28 covers it without burst.

How this is calculated

Calls per active day	2,000
Calls per minute, over 8 active hours	4.17
× average call length	4.0 min
= Average concurrency	16.7
× cushion for how solid your numbers are	1.20×
= Average with cushion	20
+ normal ups and downs at 95% confidence (z × √average)	+7.3
= Expected peak	27.3
Minimum limit: average with your cushion, or expected peak ÷ 3 for burst, whichever is higher	20
Maximum limit: expected peak, rounded up	28

These are planning estimates, not a guarantee of capacity. They assume your traffic is spread across your active hours. If a large share of it arrives at once, talk to your account team before you plan a limit around it. Final limits are confirmed with your ElevenLabs account team.

Next steps

Concurrency and priority lists the Text to Speech and Speech to Text limits for each plan and explains how requests count toward them.
How many ElevenAgents requests can I make? covers agent limits by plan.
Burst pricing explains how agents handle calls above the limit, and what those calls cost.
Call queueing holds callers instead of rejecting them when an agent is at its limit.
Chat mode describes the chat-only limit, which is separate from voice calls.
Batch calls explains how much of your concurrency a batch uses.
Usage analytics shows your concurrent requests over time, which helps you measure your traffic.