You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/cognitive-services/Speech-Service/speech-services-quotas-and-limits.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -111,7 +111,7 @@ In the following tables, the parameters without the **Adjustable** row aren't ad
111
111
112
112
<sup>3</sup> For the free (F0) pricing tier, see also the monthly allowances at the [pricing page](https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/).<br/>
113
113
<sup>4</sup> See [additional explanations](#detailed-description-quota-adjustment-and-best-practices) and [best practices](#general-best-practices-to-mitigate-throttling-during-autoscaling).<br/>
114
-
<sup>5</sup> See [additional explanations](#detailed-description-quota-adjustment-and-best-practices), [best practices](#general-best-practices-to-mitigate-throttling-during-autoscaling), and [adjustment instructions](#text-to-speech-increase-concurrent-request-limit-for-custom-neural-voices).<br/>
114
+
<sup>5</sup> See [additional explanations](#detailed-description-quota-adjustment-and-best-practices), [best practices](#general-best-practices-to-mitigate-throttling-during-autoscaling), and [adjustment instructions](#text-to-speech-increase-concurrent-request-limit).<br/>
115
115
116
116
## Detailed description, quota adjustment, and best practices
117
117
@@ -204,9 +204,9 @@ Suppose that a Speech service resource has the concurrent request limit set to 3
204
204
205
205
Generally, it's a very good idea to test the workload and the workload patterns before going to production.
206
206
207
-
### Text-to-speech: increase concurrent request limit for custom neural voices
By default, the number of concurrent requests for Custom Neural Voice endpoints is limited to 10. For the standard pricing tier, you can increase this amount. Before submitting the request, ensure that you're familiar with the material discussed earlier in this article, such as the best practices to mitigate throttling.
209
+
For the standard pricing tier, you can increase this amount. Before submitting the request, ensure that you're familiar with the material discussed earlier in this article, such as the best practices to mitigate throttling.
210
210
211
211
Increasing the limit of concurrent requests doesn't directly affect your costs. Speech service uses a payment model that requires that you pay only for what you use. The limit defines how high the service can scale before it starts throttle your requests.
0 commit comments