This page will guide you through some of the most common issues using AI speakers. Also see our Solving AI speaker training and submission issues.
AI speaker is mispronouncing a word
Sometimes an AI speaker mis-pronounces a word. We've created a guide that goes over some helpful tips on getting the pronunciation right.
AI speaker is generating more words than I wrote
That's normal! AI speakers are designed to generate a little more on either side to give you some editing flexibility in case words don't transition perfectly. You can use the trim tool to line things up and a cross-fade to blend it together.
I'm seeing black frames when I use AI speakers
Text-to-speech and Overdub currently do not work over sequences. Learn about that and more in this quick guide to using Overdub with video clips.
Audio isn't generating
If you're typing text and audio doesn't generate, try these things:
- Make sure that speech generation is enabled for your speaker. How to check
- Try duplicating the project and see if that fixes it
- Try creating a new project and see if you have the same issue there
AI speech is too fast / slow
AI speech is rendered based on a pre-defined AI model, so voices will typically speak with the same cadence and inflection. Here are some tips that might help.
AI speaker doesn't match my (English) accent
AI speaker's AI model is currently based on a US English pronunciation model. We do plan to open this up to other accents in the future so make sure to upvote the feature requests on our feedback page.
I can't adjust the clip speed of AI speech
Before AI speech clip speed can be adjusted, you need to click the Convert to audio button. At that point they will be rendered as audio clips. Note that after converting you will need to use the Hover toolbar to make further changes.
AI speaker has unexpected background noise / audio artifacts
Whenever an AI speaker has unexpected audio artifacts, it's typically because there is an issue with the source media. Check for and try to eliminate:
- Any unexpected audio artifacts (such as static, loud burst of sound)
- Background noise (such as appliances, traffic, neighborhood garage bands)
- Recorded music in source audio
- Excessive mouth noise or heavy breathing
Overdub isn't pronouncing my (non-English) language correctly
AI speakers are currently only supported for the English language. We plan to support other languages in the future so make sure to upvote the feature requests on our feedback page.