Give your video a spoken script.

Write what you want to say and turn it into a voiceover on your iPhone. Tap Captions uses Apple's speech synthesis technology in iOS 27, with video processing on your device.

Explain the footage you already filmed

Voiceover works well when the action is more useful than a person speaking to the camera. Explain a recipe, describe a product or narrate a screen recording. Start with a short script that follows what appears in the video.

Speech synthesis turns text into audio. It does not identify words that someone already said. To put an existing recording into text, use automatic captions.

Write for the time you have

Read your script aloud before generating it. If a sentence runs past the action it describes, shorten the sentence. Give viewers time to notice the step on screen before moving to the next one.

Spell out a number or abbreviation when its intended pronunciation is unclear. Listen to names and technical words in the generated result. Punctuation can help communicate phrasing, but the final audio still needs a human review.

Keep narration close to the video

The workflow lets you preview the spoken script alongside the clip, revise the words and save a finished video locally. Keep background audio low enough for the narration to be understood, and review the result with both headphones and the iPhone speaker.

Voice availability depends on the language and speech assets on your iPhone. Prepare the voice you want to use before working offline.

A useful first project

Try a short tutorial with one sentence for each step. The text-to-speech guide explains how to prepare the script and review the finished audio.