Record your voice or generate it from a script
To add a voice-over to a video, record narration in a video editor or generate it from a script with an AI voice, place it on its own audio track under the picture, lower the video's original sound, and export the result as MP4.
A voice-over, also called narration or VO, is speech added over a video by someone who is not on screen. When the new speech replaces the original speakers in another language, it is called dubbing.
| Record yourself | AI voice-over from a script | |
|---|---|---|
| What you need | A microphone and a quiet room | A written script |
| Change a word later | Record the line again | Edit the text and generate again |
| Sound | Your own voice | A synthetic voice, or a clone of your own voice |
| Good for | Vlogs, tutorials in your voice, personal videos | Explainers, product demos, many languages |
Record a voice-over in iMovie on iPhone
iMovie records straight onto the timeline at the playhead, according to Apple's iMovie guide.
- Open the project and scroll the timeline so the playhead sits where the voice-over should start.
- Tap Add Media, then Voiceover, and allow microphone access.
- Tap Record. After a three-second countdown, speak, then tap Stop.
- Tap Review to listen, Retake to try again, or Accept to keep it. The recording appears as a purple clip.
Record a voice-over in Clipchamp on Windows
Clipchamp, Microsoft's free video editor, records voice-overs in the browser or the Windows app.
- Open the video and choose Record and create, then Audio.
- Allow the microphone and pick the right microphone source.
- Select the red microphone button, speak, then select Stop.
- Preview the take, then choose Save and edit. The recording lands on the timeline.
Record a voice-over in CapCut
In CapCut's online editor, the record button sits in the timeline area, according to CapCut's own how-to article. On the phone app, CapCut's site describes Sound, then the microphone icon. Menu names can change between versions.
- Open a project and import the video.
- Select the microphone icon in the timeline area, then Record. The keyboard icon opens a prompter for your script.
- Stop, listen, and run background noise removal if the room was noisy.
Recording tips that make the biggest difference
Most voice-over problems come from the room and the microphone distance, not the editor.
- Record in a quiet room with the door closed. Soft furniture and curtains reduce echo.
- Keep the microphone about 4 to 12 inches (10 to 30 cm) from your mouth, as Home Brew Audio recommends, and move closer or further until the voice is loud without popping.
- Record a 10-second test and listen with headphones before the full take.
- Read from a script split into short lines, and pause between lines so you can cut mistakes.
- After recording, remove background noise and bring the level up to a consistent loudness.
Make an AI voice-over that matches your video's timing
An AI voice-over turns a script into speech, so you can change a word without recording again. Clipchamp has text to speech under Record and create. To time each line to the picture, SoundHalo's voice-over tool reads an SRT or WebVTT file, or plain lines that start with a time such as 0:05.
Each line starts at its time. A line that is too long for its slot is sped up to at most 1.25 times, and if it still runs over, it plays in full and is flagged so you can shorten it. Add your video in the optional field to get the voice-over track and an MP4 with the original sound lowered under the voice or replaced.
- Write the script with a start time for each line, or export an SRT from your editor.
- Paste or upload it into the voice-over tool and pick a voice.
- Add the video, choose to lower or replace its sound, and generate.
- Watch the result and fix any flagged line before you download.
Do you have to label an AI voice-over on YouTube?
YouTube requires creators to disclose realistic content that is made or meaningfully changed with AI, such as making a real person appear to say something they did not say. Its help page lists cloning your own voice to create voice-overs or dubs as an example that does not need disclosure.
The page does not mention a generic synthetic narrator. If the voice could make viewers believe a real person said the words, turn on the AI use setting when you upload in YouTube Studio.