Add audio and saved generated voices to a video

How the tool works

Import an audio file, extract audio from a video, or reuse a text-to-speech voice you have already generated. Reusing that saved voice adds a copy; it does not generate speech again or spend new generation credits. Added sounds have their own positions, trims, volume, and fades.

Build it step by step

Start with a source you have permission to use. Listen to the file before importing so you know whether it contains silence, speech, or a useful musical passage.

• Position the project cursor at the intended start of the sound and open Add audio.
• Choose an audio file, extract audio from a Photos or Files video, or select an existing generated voice.
• Wait for import and select the resulting sound on its own audio lane.
• Trim away the unused beginning or end and move the clip if its entrance is too early.
• Listen with the video, adjust volume, and keep only the interval that supports the explanation.

An example to adapt

Illustrative exercise: pair a silent product close-up with a voice you previously generated from its script. Add that saved voice at the moment the product enters the frame, then trim the picture to follow the explanation.

If the speech finishes before the video, do not stretch the voice to fill the space. Shorten the ending or leave a deliberate visual pause, and check that any music remains balanced.

Check before finishing

Until the end uses only the remaining source and does not loop a short file. Extracting audio does not add a video take. Moving a video clip does not automatically move its added sound, so revisit audio timing after picture edits. Imported files take storage space on the device.

The timeline editor requires Starter or above. Check the app for current feature access and purchase options before planning your edit.