Forum Discussion
Slow down entire slide/voice - text to speech
Hello BrittnyTedford,
We appreciate you sharing your voice with us! We understand you’d like better control over timing directly in AI text-to-speech so you can create polished narration more efficiently. We’ve shared your feedback with our product team. We'll share any future updates in this thread, so all are in the loop!
Thanks again for helping us improve the AI experience.
I am trying to slow down text-to-speak narration (not AI) and followed the instructions provided. This doesn't work for me. The voice now says, "Less than Speak, less than Parsody=slow, greater than, and then the narration; followed by less than slash parsody greater than less than slash speak, greater than.
In other words, it's reading/speaking the tags.
Any suggestions?
Marty Evans
I've successfully used Audacity (free audio tool widely available) for just this purpose. Upside: the pacing and delivery rate are easy to alter, and give me the narration that I want. Downside: Time. You export the .mp3, import to Audacity, tweak/correct, export the revised .mp3, and then reimport to SL360.
It works, and it sounds terrific, but like other aspects of life... good things will take time.
Hi MartinEvans-338,
I can understand how that behavior would be confusing.
Storyline’s standard text-to-speech supports SSML, but when the formatting isn’t recognized, the tags can be read aloud instead of applied, which sounds like what you’re experiencing.
It may help to double-check the syntax to make sure everything is formatted correctly. For example, a basic structure to slow down narration would look like this:
<speak>
<prosody rate="slow">
Your text here
</prosody>
</speak>If the tags aren’t written exactly in this format, Storyline may read them as text instead of applying the effect.
Thanks as well to JHauglie for jumping in here.
If it continues, feel free to share your Storyline file with our support team so we can take a closer look at how it’s set up.
