How much is my Speech to text Pay as you go tier's concurrency rate limits, looks like it's not 50 #1487
Replies: 3 comments 1 reply
-
|
Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently. |
Beta Was this translation helpful? Give feedback.
-
|
Hey there! It looks like you haven't connected your GitHub account to your Deepgram account. You can do this at https://community.deepgram.com - being verified through this process will allow our team to help you in a much more streamlined fashion. |
Beta Was this translation helpful? Give feedback.
-
|
It looks like we're missing some important information to help debug your issue. Would you mind providing us with the following details in a reply?
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi, we are running a live speech to text web app using Deepgram api, to be specific, Speech‑to‑text via WebSocket (streaming) with nova-2 or nova-3 depends on different speaking language. My current tier is pay as you go, i saw in related documentation that my tier should has up to 50 concurrent streaming requests per project.
https://developers.deepgram.com/reference/api-rate-limits
However:
1 When I have more than 50 concurrent speech to text sessions, I did not receive the "429: Too Many Requests" error or any connection failure error;
2 In my local end to end test: every 30 seconds, i set up a Deepgram connection through websocket, then start streaming real audio, even though 120 concurrent speech to text sessions did not trigger any rate limit or deepgram connection error, all sessions transcripts arrived as normal;
3 In my deepgram sdk connection test: every 15 ms, i create a connection "connection = deepgram.listen.live(CONFIG.CONNECTION_OPTIONS);", then send keepalive signal to keep connection alive. This methods still did not trigger the 429 error or rate limite error or connection error if I have more than 50 deepgram websocket connection.
My questions:
1 How exactly is my concurrency limits, looks like it's more than 50, even more than 120.
2 In your doc about "Concurrency rate limits define the maximum number of API requests you can make in a given time frame.", but did not further explain what is the given time frame. Is this relevant to the concurrency confusion I am having?
https://developers.deepgram.com/docs/working-with-concurrency-rate-limits
Thanks a lot.
Beta Was this translation helpful? Give feedback.
All reactions