> ## Documentation Index
> Fetch the complete documentation index at: https://help.descript.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Troubleshooting and Using AI Speakers

> Fix common AI Speaker issues like sequence errors and accent mismatches in Descript

Most AI Speaker snags come down to a few recurring issues, like sequence errors and accent mismatches. Here’s how to fix the common ones.

<AccordionGroup>
  <Accordion title="I'm not happy with my AI Speaker — how can I improve it?">
    If you're not happy with the results, create a new AI Speaker with a fresh recording. There's no way to add more voice samples or training data to an existing AI Speaker.

    **When re-recording:**

    * Choose the tone and style you want — casual and friendly, formal and authoritative, or anything else.
    * Speak clearly and intentionally; your delivery during the consent script directly shapes how your AI Speaker will sound.
    * Use your usual microphone and recording setup.
  </Accordion>

  <Accordion title="Can I create different voice styles with my AI Speaker?">
    Descript doesn't support style variations within a single AI Speaker. However, you can create multiple AI Speakers using the same process described above. For example:

    * Create one AI Speaker with a casual, conversational tone.
    * Create another AI Speaker with a more formal, professional delivery.
    * Create additional AI Speakers with different emotional qualities or speaking styles.

    Each AI Speaker appears as a separate option in your speaker dropdown menu, allowing you to choose the most appropriate voice for different sections of your project.
  </Accordion>

  <Accordion title="AI Speaker is mispronouncing a word">
    Sometimes, an AI Speaker might mispronounce a word or phrase. See our [guide with tips on getting the pronunciation right](/ai-speech/pronunciation).
  </Accordion>

  <Accordion title="Why is the AI Speaker generating more words than I select?">
    That's normal! AI Speakers generate a little extra on either side to give you editing flexibility in case words don't transition perfectly. Use the [trim tool](https://help.descript.com/hc/en-us/articles/10249345076365) to line things up and a [cross-fade](https://help.descript.com/hc/en-us/articles/10255990548877#fades) to blend them together.
  </Accordion>

  <Accordion title="When I use AI Speakers, it inserts black frames into the project">
    Text-to-speech and Regenerate currently do not work over sequences. When used on a sequence, the video will be removed. We're working on improvements ([see more info](https://www.descript.com/video-regenerate)).

    In the meantime, try this workaround:

    1. [Convert the AI voice clip into an audio layer.](/ai-speech/covert-to-audio)
    2. Select the AI audio clip and cut (`Cmd + X` or `Ctrl + X`).
    3. Use the [trim tool](https://help.descript.com/hc/en-us/articles/10249345076365) to restore the original audio/video in the Script track.
    4. Paste the AI audio clip as a layer above the original audio.
    5. Use the <img src="https://mintcdn.com/descript-5bf56f3f/3Cc57GbXKoHVrvhX/images/external/descript-28867125866637-5b5623736e.png?fit=max&auto=format&n=3Cc57GbXKoHVrvhX&q=85&s=685311da3813bf60763b5bff4f97fde5" alt="Blade icon" width="27" height="20" style={{ display: "inline-block", verticalAlign: "middle", margin: "0 0.125rem" }} data-path="images/external/descript-28867125866637-5b5623736e.png" /> [blade tool](/timeline/timeline-tools) to split the Script track, then mute the replaced portion in the [Properties panel](/visuals/layer-properties).
    6. Adjust as needed.
  </Accordion>

  <Accordion title="Audio isn't generating for the selected text">
    If you're typing text and no audio generates, try:

    * Ensure speech generation is enabled for your speaker. If not, [create a new AI Speaker](/ai-speech/custom-speaker).
    * Try duplicating the project and check again.
    * Try creating a new project to see if the issue persists.
  </Accordion>

  <Accordion title="The AI-generated speech is too fast or too slow">
    AI speech uses a predefined voice model, so cadence and pacing are consistent. [Here are some tips](https://help.descript.com/hc/en-us/articles/10165955417869) that might help.
  </Accordion>

  <Accordion title="AI Speaker doesn't match my accent">
    The current model is based on US English pronunciation. We're exploring broader accent support in the future — [upvote this on our feedback board](https://feedback.descript.com/feature-requests). In the meantime, try using the [Translate](/repurpose/translate-captions) feature to create a version of your voice in another language.
  </Accordion>

  <Accordion title="Unable to adjust the clip speed of AI-generated speech">
    To adjust the speed of AI-generated clips, first click **Convert to audio**. Once converted, adjust speed using the [selection toolbar](/descript-tour/selection-toolbar).
  </Accordion>

  <Accordion title="The AI-generated speech has unexpected background noise or artifacts">
    Unexpected audio artifacts are usually caused by issues in the source media. Try to eliminate:

    * Static or sudden loud sounds
    * Background noise (appliances, traffic, music)
    * Excessive mouth noise or breathing
  </Accordion>
</AccordionGroup>