Turn a script into a video voiceover.

Text to speech is useful when you have footage and need an explanation to go with it. Prepare the script around the action, generate the voice, then review both together.

Start with the video

Choose the sequence you want to explain. Watch it and make a note of the moments that need context. You may need to explain an ingredient, a setting or the reason for a step. Leave visual details to the footage when they are already clear.

In Tap Captions, open a local video from your iPhone and prepare the narration with on-device text to speech.

Write sentences you would say aloud

Keep each sentence focused on one thought. Use familiar words, and write out a number or abbreviation if the way it should be read is ambiguous. Read the script aloud before generating the audio.

For a matcha tutorial, a line such as “Pour the matcha slowly over the milk” gives the viewer a clear action. A long introduction about the whole recipe can wait for a place where the video has room for it.

Preview the voice with the footage

Generate the narration and listen while watching. Check names, place names and unfamiliar terms. Adjust spelling or phrasing if a word sounds wrong. Prepare any required voice assets while you have a connection.

Make sure the instruction arrives in time to explain the action. If the voiceover runs long, shorten the script first. Adding speed may make the words harder to understand.

Keep the voice audible

Background music and recorded sound should leave room for the narration. Listen on the iPhone speaker as well as headphones. Pay attention to the first word of a sentence and to any sudden change in volume.

Add captions for the spoken explanation so viewers can follow without sound. Recheck them after changing the script or regenerating the voice.

Export and review the saved file

Watch the exported copy instead of relying only on the editor preview. Check that the voice ends with the intended shot and that captions match the final wording.

Text-to-speech voiceover is different from translating or cloning a voice. Choose it when you want a written script spoken over your own footage.

Try Tap Captions on TestFlight, or see the tutorial workflow.