Not Monitored
Tag not monitored by Microsoft.
43,482 questions
A community member has associated this post with a similar question:
How can I add variability to TTS in Azure AI Speech?
Only moderators can edit this content.
Any plans to add style support or instruction prompts to OpenAI voices in Azure AI Speech?
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(144, 54%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJW%3C/text%3E%3C/svg%3E)
James Withers
20
Reputation points
I'm using the en-US-NovaTurboMultilingualNeural voice in Azure AI Speech's text-to-speech (TTS) service.
In March 2025, OpenAI announced that their gpt-4o-mini-tts model would support instruction prompts (see https://openai.com/index/introducing-our-next-generation-audio-models/). Is there any plan to support this kind of steerability in the TTS service in Azure AI Speech?
Not Monitored
{count} votes
-
James Withers 20 Reputation points
2025-05-04T08:58:47.14+00:00 The main reason I'm using Azure AI Speech is because of the phoneme/viseme ID output, which other services lack, so it's not feasible to move to something else.
-
Prashanth Veeragoni 4,355 Reputation points Microsoft External Staff Moderator2025-05-05T03:22:13.04+00:00