How does automatically scaling concurrency for Streaming STT work?

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 “Unauthorized connection: Too many concurrent sessions”.

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.