Local text processing
Your text is converted to speech in this browser after the model files load.
Browser AI audio tool
Text to Speech
Local TTSWebGPUWAV output
Turn short English text into a WAV voice clip with Kitten TTS running locally through WebGPU. No text upload.
Text input
Ready
English Only · 91/500 characters
Bigger models sound better but load longer.
Pick a bundled voice.
Set the voice pace.
0.5x1.00x2.0x
How it works
Three steps to finish the browser workflow.
Upload Your File
Choose the source file for Text to Speech from your device.
Adjust Settings
Review the preview and tune the options for the result you want.
Preview and Download
Check the finished result, then download the exported file.
Everything you need
Core details about privacy, browser support, output, and practical limits before you start.
WebGPU runtime
The engine uses browser WebGPU compute shaders, so a compatible modern browser is required.
English voices
The current Kitten TTS model is designed for English prompts and short passages.
Frequently asked questions
Find quick answers about privacy, browser support, exports, and what to try when a file is heavy.
Related tools
Continue editing with nearby ArtPlayer tools that work with the same local, browser-first workflow.
