🌸Kokoro TTS Voice
Studio-grade 82M AI voice — 10 voices, on-device. Free, private, no signup — files never leave your browser.
Kokoro 82M by Hexgrad — model downloads once (~90MB), then runs on-device. 10 voices, 0.5x–2x speed, 24 kHz WAV out.
Studio voice. Zero studio.
Ten top-graded voices from an 82M model that runs fully on your device. No upload, no signup, no watermark.
How to use Kokoro TTS Voice
Studio sound without a studio. Pick one of 10 top-graded American and British voices, set the speed, and download a natural 24 kHz voice-over. The model downloads once (~90MB) and is cached — everything after that is instant and private.
- 1Type or paste up to 2000 characters.
- 2Pick a voice (Heart, Bella, George, Emma and more) and set speed.
- 3Hit Generate and download the WAV voice-over.
Use cases
What kokoro tts voice does
- ✓Ten top-graded US and UK voices, female and male.
- ✓Speed slider from 0.5x to 2x.
- ✓High-quality 24 kHz WAV download for editors.
- ✓Up to 2000 characters per generation.
- ✓Fully local ONNX: no uploads, no accounts, no watermarks.
Specs
- Speed
- Seconds per render, on-device
- Input
- Text up to 2000 characters
- Output
- WAV voice-over (24 kHz)
- Privacy
- On-device ONNX, zero uploads
- Cost
- Free, unlimited, no signup
Frequently asked questions
Is my text sent to a server?
No. Kokoro runs 100% in your browser via ONNX. Your text never leaves your device.
Which voices are available?
Ten voices: Heart, Bella, Nicole, Sarah, Fenrir, Michael, Puck, Emma, Isabella and George.
Why does the first run take longer?
The voice model (~90MB) downloads once and is cached by your browser. Every run after that starts faster.
What format is the download?
A 24 kHz WAV voice-over file you can drop into any video or podcast editor.