AI Voice Generator: Turn a script into an AI voice-over and save it as MP3 or WAV. Input: Text you type or paste and values you enter. Output: Results shown on the page and a downloaded file. Privacy: Runs in your browser: inputs and files stay on your device and are not uploaded. On first use it downloads an open AI model to your browser; processing still happens locally.
How to make an AI voice-over
- Type or paste your script. Write numbers and abbreviations the way they should be spoken. Add [pause 2] wherever you want a two-second pause.
- Pick a voice and the speed, and set the pause between sentences.
- Press Make the voice-over. The voice model downloads once, the first time.
- Listen, then download the MP3 or WAV.
An open voice model on your device
The voices come from Kokoro, an open text-to-speech model under the Apache 2.0 licence. It runs in your browser, on the graphics card where the browser supports WebGPU (several times faster than the speech itself; without WebGPU it takes about as long as the speech), so your script stays on your device, there is no character limit or monthly credit, and you can use the audio in your videos, courses and podcasts.
Is my script uploaded?
No. Only the voice model is downloaded, once. The speech is made on your device.
Can I use the voice-over in my videos?
Yes. The model's licence (Apache 2.0) allows commercial use, and nothing is added to the audio.
Which languages can it speak?
English, with American and British voices. Unusual names and foreign words may need to be spelled the way they sound.
How do I add a pause?
Type [pause] for one second or [pause 2.5] for two and a half. Sentence ends get the pause you set with the slider.