LXB Voice has used Polly’s standard text-to-speech engine since 2022. It now uses the neural engine on every install where Voice is turned on.
The two engines work differently. Standard voices use concatenative synthesis, which stitches together phonemes of recorded speech. As AWS puts it, “the inevitable variations in speech and the techniques used to segment the waveforms limits the quality of speech.” The neural engine takes a sequence-to-sequence approach that AWS says yields “higher-quality, more natural-sounding voices.”
We ran a side-by-side comparison of the same post in both engines before committing to the switch. The neural version was clearly better, so we made the change.
That matters for legal blogs specifically. Your posts run long and carry real analysis. Audio is the format for readers who want that analysis on a commute or between meetings, and for readers who prefer listening to reading. The quality of the voice decides whether that format is usable.
What you need to do
Nothing. The upgrade is live on every install where LXB Voice is enabled.
One thing to know about your archive: audio files are generated when a post is published or updated. New posts get neural voices automatically. Older posts keep their existing audio until the post itself changes. Regenerating years of back catalog would have cost more than the improvement is worth, so we left it to refresh naturally.
Who has it
LXB Voice is included in your subscription on all Blog Premiere publications and on every publication on an Enterprise platform. It’s available as an add-on for all other LexBlog blogs.
If you’re on Blog Premiere or Enterprise and haven’t turned Voice on, now is a good time—just let us know and we’ll take care of it. If you’re on another plan and want it, reach out all the same to have it added to your publication for a small upgrade cost.
Recent Comments