Text to Video: Turn a Script into a Video with AI Voice and Captions
Type or paste a script and get a vertical video for Reels, Shorts or TikTok: a natural AI voice reads it, big captions light up word by word, and the background moves with the voice. It's free with no sign-up, and it's all made on your device.
Your script never leaves your device. How?
The voice is made by an AI model that runs in your browser, and the video is drawn and encoded by your device too, so nothing is uploaded. The model (about 92 MB) downloads once from Hugging Face and is then kept on your device.
0 / 5,000 characters
Preview of the look (the voice comes when you make the video)
Free, no sign-up. The first time, the AI voice downloads once (about 92 MB); after that it starts in seconds.
How to turn text into a video
Write or paste your script
A fact, a story, a tip, a quote or a product pitch: up to 5,000 characters, about 5 minutes of video.
Pick a voice
Tap ▶ to hear any of the 12 voices first, then choose a speed.
Choose the look
The shape, a background or your own picture, a waveform and a caption style. The preview shows it as you change it.
Make the video
The first time, the AI voice downloads once (about 92 MB). Then the voice and the video are made on your device; download the MP4 or share it straight to an app.
What people make with it
Faceless videos for YouTube Shorts, Instagram Reels and TikTok: facts, stories, quotes, motivation, tips and short explainers, posted without filming yourself or recording your voice. Captions matter there because most people scroll with the sound off, and big words that light up as they're spoken keep them watching.
It also makes quick videos for a WhatsApp Status, a product or a shop, a lesson, or an announcement, in English or Hindi.
How the video is made
The voice comes from Kokoro, an open-source AI speech model that sounds natural and can be used commercially. It runs in your browser and reads your script sentence by sentence. Because the words are known, each one is placed where it's said in the voice (the pauses after commas and full stops pin the timing), so the captions follow the voice without anything being sent anywhere.
Then every frame is drawn on your device (the background, a waveform that moves with the voice, and the captions) and encoded into an MP4 by your phone's or computer's own video encoder. Nothing is uploaded: your script stays private, and it works the same on a phone.
Features
Natural AI voices
12 voices, American, British and Hindi, women and men. Hear each one before you choose, at four speeds.
Word-by-word captions
8 free caption styles (Highlight, Box, One word and more), with 18 more in Pro: Hustle, Slam, Karaoke, Neon…
Any shape
9:16 for Reels, Shorts and TikTok, 1:1 for posts, 16:9 for YouTube. A colour background or your own picture, and a waveform in your colour.
Private and free
Made on your device: no upload, no sign-up, no queue. Free videos carry a small cliputils.com tag in the corner; Pro removes it.
Frequently asked questions
Is this text to video free?
Yes. There's no sign-up and no daily limit: make as many videos as you like, up to 5,000 characters each. Free videos have a small cliputils.com tag in the corner; ClipUtils Pro removes it and adds more caption styles.
Does it make AI-generated footage, like Sora?
No. It makes faceless videos: your script read by an AI voice, with big captions over a background that moves with the voice (a colour, or a picture you choose). That's the format most Shorts and Reels channels use, and it's made in a minute or two on your own device.
Can I use the videos on YouTube and monetize them?
Yes. The voices come from Kokoro, an open-source model released under the Apache 2.0 license, so the voice can be used in monetized videos. The script and the picture you add are yours.
Is my script uploaded?
No. The AI voice runs in your browser and the video is made by your device, so nothing leaves it. Only the voice model itself (about 92 MB) is downloaded, once, from Hugging Face.
Which languages does it speak?
English (American and British voices) and Hindi. Hindi scripts are read in Hindi script (देवनागरी), with any English words in them read the English way.
How long can the video be?
Up to 5,000 characters of script, about 5 minutes of video. A 60-second Short takes about 150 words. On a phone, a long script takes a few minutes to make; keep the page open while it works.
Related: Text to Speech · Audio to Video · Auto Subtitles · AI Dubbing · All tools