On 31/03/2027 the Long Audio API of Azure AI Speech will be retired. Please transition to the new batch synthesis API by that date.
We encourage you to make the switch sooner to gain the richer benefits of the new batch synthesis API and enjoy the better price. In addition to the familiar features you are using, here’s a quick comparison between the long Audio API and replacement.
Long Audio API Features
- Small Subset of Voices available
- Higher Latency
- Limited Audio Output Formats supported
- Does not support advanced features such as word boundaries or background audios
- More expensive
Batch Synthesis API Features
- All platform TTS voices available
- Lower latency
- Same output formats supported as the real-time synthesis API
- Supports advanced features such as word boundaries and background audios during synthesis
- Same price as the real-time synthesis API
From now through 31/03/2027, you can continue to use the Long Audio API or transition to <the new batch synthesis API> before 31 March 2027.
After 31/03/2027, the Long Audio API will not be supported.
Required action
Follow the detailed steps to transition to the new batch synthesis API. View pricing here.
Help and support
If you have questions, get answers from community experts in Microsoft Q&A. If you have a support plan and you need technical help, create a support request. <Please provide details on how to complete the support ticket.
-
For Issue type, select Technical.
-
For Subscription, select your subscription.
-
For Service, select My services, then select Cognitive Services.
-
Select the Azure resource that you are creating a support request for.
-
For Summary, type a description of your issue.
-
For Problem type, select Text to Speech.
-
For problem subtype, select Neural Voice.
