Skip to main content
We enforce rate limits to ensure fair usage and stable performance for all users. Rate limits specify the maximum number of API requests that can be made within a given time window for an account.

​
Default Rate Limits

Every account starts with the following default rate limits.
APIRate limit
TTS — Synthesize Speech100 requests per second
TTS — Clone Voice5 requests per minute
LLM25 requests per second (some models may have additional limits)
Embeddings50 requests per second
STT50 audio chunks per second
These limits are usually sufficient for many interactive use cases, including applications with thousands of concurrent users.

​
Request A Rate Limit Increase

If you need a higher limit, follow the steps below. You can typically expect a response within 48 hours.
  1. In the Inworld Portal, click your profile icon in the top-right corner and select Billing.
  2. Click Increase rate limit in the top-right corner and fill in the details for your request, including the expected usage increase and why the increase is needed.
  3. Click Submit. Our team will review your request and may reach out with follow-up questions.

​
Notes

  • Rate limits apply per account and are shared across your API keys.
  • Very high limits may require additional lead time and mutual commitments, since physical GPU capacity may need to be reserved to support sustained throughput.