AI voiceover inside your video editor

Fuse voiceovers are designed to sound clear and usable for short videos, explainers, ads, and social content. Right now, the focus is on getting a strong result quickly inside the project workflow. Over time, we'll expand voice controls further, including more expressive delivery options and richer voice customization.

Yes, when speed and convenience matter more than using your personal voice. Fuse is a good fit for faceless videos, explainers, product clips, ads, and other short-form content where you want to add narration quickly. If your real voice is part of your identity, you can also upload your own audio and use Fuse to place and mix it in the project.

You can upload your own voice recordings as audio files and use them inside your project. We are planning to add direct voice recording and more advanced voice customization later, but right now uploaded audio is the way to work with your own voice.

Voiceovers use credits based on script length. Short lines use only a small number of credits, and you'll always see the exact cost before generating.

Yes. Voice tracks can trigger auto-duck, so background music lowers when the voice plays and rises again when the voice stops. Auto-duck is enabled by default, but you can turn it off if you want manual control.

Yes. You can edit the text, change settings, and generate a new version. Each generated voiceover is saved to your library, so you can compare takes, reuse earlier versions, and add the one that fits your project best.

Yes. You can set when a voiceover segment starts, and then place it on the timeline so it plays at the right moment in the video. This makes it easier to line up narration with what is happening on screen.

Yes. Fuse supports multiple voiceover segments, so you can break narration into smaller parts instead of generating one long block. This is useful when different moments in the video need different lines, pauses, or pacing.

Fuse supports multiple voiceover languages. Available results may vary depending on the selected voice and your script. If a language is supported in your current workspace, you'll be able to use it directly in the voiceover flow.

Yes. Fuse supports prompt-like text cues such as pauses and expressive instructions inside the script. This helps shape delivery without forcing you into a more complex voice-editing workflow.

Yes. You can generate the segment, preview it, and then decide whether to add it to the timeline or regenerate it. That makes it easier to test wording, timing, or voice choice before committing it to the edit.

Not right now as a dedicated feature. At the moment, Fuse voiceovers are focused on helping you generate and place narration inside a short-video workflow. If multilingual dubbing or translation is added later, we'll announce it in What's New.