For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
PlaygroundChangelogSign In
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
  • Overview
      • Can I use speaker diarization with Streaming Speech-to-Text?
      • How accurate is your Streaming transcription compared to Async transcription?
      • How does automatically scaling concurrency for Streaming STT work?
      • How does Universal Streaming session-based pricing work?
      • What languages are supported for Streaming Speech-to-text?
      • Resolving SSL Certificate Verification Error When Trying to Use Streaming STT
      • I am getting a "Model deprecated. See docs for new model information" error message. What does it mean?
LogoLogo
PlaygroundChangelogSign In
On this page
  • What happens when I exceed my new streaming sessions per minute rate limit?
  • Additional resources
OverviewStreaming audio

How does automatically scaling concurrency for Streaming STT work?

Was this page helpful?
Previous

How does Universal Streaming session-based pricing work?

Next
Built with

Our Streaming STT feature includes automatically scaling concurrency limits.

We do not limit the total number of concurrent streaming sessions. Instead, there is only a limit on the number of new streaming sessions that can be created per minute.

Anytime you are using 70% or more of your current limit, your new sessions rate limit will automatically increase and scale up by 10% every 60 seconds.

As your traffic starts to scale back down and you are using less than 50% of your current limit, your new sessions rate limit will also start to scale back down until it eventually returns to your default value.

What happens when I exceed my new streaming sessions per minute rate limit?

When you reach your streaming new sessions rate limit, new requests will receive a 1008 error with the message ā€œUnauthorized connection: Too many concurrent sessionsā€.

Additional resources

For a more detailed explanation on how automatically scaling concurrency for streaming works, please see our documentation on Streaming Speech-to-Text usage limits.