CapCut text to speech: add character voices to your videos
CapCut’s built-in text to speech is the quickest way to put a voice on a video: type, pick a voice, done. That is also why the same few voices narrate countless videos in every feed.
SuperClonica adds voices CapCut does not have, from calm narrators to game, anime and cartoon characters, free to try online. This guide shows when the built-in voices are enough, how to bring a SuperClonica voice into a CapCut project and how to voice whole scripts offline.
When CapCut’s own voices are enough
For a quick edit, the built-in voices are the simplest choice; reach for another voice when you want the video to sound like nobody else’s.
- CapCut’s text to speech is free to try and offers more than 200 voices in many languages, Chinese among them.
- CapCut’s FAQ says the audio can be used commercially.
- It works right inside the editor, next to your captions.
- Because it is so easy, the same voices are heard in countless other videos.
Try a character voice free
On the page of any voice, type a line of 30 to 100 characters, choose the language and press Voice it. In a few seconds you can listen and download the recording, with no account, also from a phone browser.
Add the voice to a CapCut project
A different voice is one of the quickest ways to stand out in a feed full of the same narrators.
- Voice the line on the voice page and download the recording.
- In CapCut, import the file and place it on the audio track under the clip.
- Split, move and fade it like any other sound, and add captions with auto captions if you need them.
- For a whole script, voice one file per scene and import them all.
Whole scripts offline
For longer scripts, buy the voice once, download its file and install the free SuperClonica engine on a computer: python -m pip install superclonica-cpu. Save each scene as a text file and voice it with one command: superclonica --text-file scene01.txt --voice character.json --lang en --output scene01.mp3. The engine writes MP3 or WAV, splits long texts at natural pauses and runs offline on an ordinary processor, with no character limit.
Voices and rights
Character voices in the catalog are fan-made and not endorsed by the rights holders: use them for parody and fan videos within the SuperClonica terms. For brand or monetized content, use the ten stock voices of the model or a voice trained from a speaker who agreed. Never make a voice that imitates a real person say things they did not say.