Are files uploaded for this tool?

This browser tool processes the selected media locally on this device. The file is not uploaded to ArtPlayer servers for this workflow.

Will the export have a watermark?

No. ArtPlayer browser tools do not add watermarks to exported files.

The work runs in your browser, so speed depends on your device, browser, memory, source size, and the export settings needed for the result.

Recent Chrome, Edge, and other modern Chromium browsers usually work best for heavier browser media processing.

Try a smaller source, close other heavy tabs, reduce resolution or duration first, and keep the tab open until the export finishes.

Kitten TTS is English-only, so short English prompts work best.

The page downloads Kitten TTS model weights and voice data, then caches them in Cache Storage for later runs.

Use a recent WebGPU browser such as Chrome, Edge, or Safari. There is no wasm fallback for this runtime.

Browser AI audio tool

No. The entered text is converted to speech in this browser after the model files are downloaded.

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

Text to synthesizeEnglish Only · 91/500 characters

Model size

Voice

Speaking speed1.00x

Three steps to finish the browser workflow.

1
Upload Your File
Choose the source file for Text to Speech from your device.
2
Adjust Settings
Review the preview and tune the options for the result you want.
3
Preview and Download
Check the finished result, then download the exported file.

Core details about privacy, browser support, output, and practical limits before you start.

Your text is converted to speech in this browser after the model files load.

The engine uses browser WebGPU compute shaders, so a compatible modern browser is required.

The current Kitten TTS model is designed for English prompts and short passages.

Check supported inputs, output formats and usage requirements before you start.

Supported input	Short English text.
Output result	Export options: WAV.
Processing and privacy	Processing runs on this device. Source media is not uploaded for this workflow.
Browser requirements	WebGPU support, compatible graphics hardware and enough memory. Model files must download before the first run.
Usage limits	Up to 500 characters of English text. Model and GPU availability can prevent generation.
Which language does this TTS model support?	Kitten TTS is English-only, so short English prompts work best.