This page will guide you through some of the most common questions and issues while using AI speakers.
AI speaker is mispronouncing a word
Sometimes, an AI speaker might mispronounce a word or phrase. We've created a guide that goes over some helpful tips on getting the pronunciation right.
Why is the AI speaker generating more words than I select
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 them together.
When I use AI speakers it inserts black frames into the project
Text-to-speech and Regenerate currently do not work over sequences. When you use this on a sequence, the video will be removed. Until this is fully supported, you can try the following:
- Convert AI Speech Clips to Audio: Convert an AI voice clip into an audio layer.
- Select the AI Speech Audio Clip and Cut (Command + X or Ctrl + X).
- Use the Trim tool to restore the original audio/video in the Script track.
- Paste the AI Speech Audio Clip as a layer above the original audio.
- Use the
Blade tool to cut the Script track around the section you Regenerated, and then mute that clip from the Properties Panel.
- Adjust to as needed.
Audio isn't generating for the selected text
If you're typing text and audio doesn't generate, try these things:
- Make sure that speech generation is enabled for your speaker. Here is 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.
The AI-generated speech is too fast or too 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 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.
Unable to adjust the clip speed of AI-generated speech
Before the 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.
The AI-generated speech 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 bursts of sound).
- Background noise (such as appliances, traffic, and neighborhood garage bands)/
- Recorded music in source audio.
- Excessive mouth noise or heavy breathing.
My AI Speaker 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.