WebGPU text-to-Speech powered by OuteTTS and Transformers.js
Kokoro is an open-weight TTS model with 82 million parameters.
Generate speech from text with reference audio
Pyxilab's Pyx r1-voice demo
Convert speech to text from audio files
Generate speech from text with adjustable speed
Generate Vietnamese speech from text and reference audio
High-fidelity Text-To-Speech
Generate speech from text with custom voice
Transcribe or translate audio files
Belarusian TTS
Text-to-Speech WebGPU is a cutting-edge text-to-speech service powered by OuteTTS and Transformers.js. It leverages WebGPU technology to synthesize natural-sounding speech from text input. This tool is designed to provide high-quality, efficient, and scalable speech synthesis for various applications, from voice assistants to content creation.
What browsers are supported?
Text-to-Speech WebGPU works on modern browsers that support WebGPU, including Chrome, Edge, and Firefox.
Can I use it offline?
Yes, once the model is loaded, you can use Text-to-Speech WebGPU offline.
Are there any usage limits?
Usage limits depend on the hosting platform. By default, the demo version may have constraints for free-tier users.