Convert spoken words to text
Generate speech from text with reference audio
Generate sexual voice sounds from text
Generate speech from text with customizable voices
Generate edited English speech from audio and text
MaskGCT TTS Demo
StyleTTS2 trained on ukrainian dataset
Transcribe spoken Russian into text
Generate speech from text with custom voice
✨[With v1.0.0] Accelerated TTS on Kokoro-82M
Generate audio from text
High-fidelity Text-To-Speech
Generate text from audio input
Whisper WebGPU is a cutting-edge speech synthesis and audio processing tool designed to handle speech-to-text conversion with high accuracy. It leverages the power of WebGPU to provide high-performance processing for various speech recognition tasks, offering a robust solution for developers and users alike.
• Hardware Acceleration: Uses WebGPU for fast and efficient processing of audio data.
• Accurate Speech Recognition: Delivers high-quality transcription of spoken words into text.
• Low Latency: Processes audio in real-time with minimal delay.
• Cross-Platform Compatibility: Runs seamlessly on multiple devices and browsers.
• Developer-Friendly: Equipped with APIs for integration into custom applications.
What browsers support Whisper WebGPU?
Whisper WebGPU is compatible with modern browsers that support WebGPU, including Chrome, Firefox, and Edge.
Is WebGPU enabled by default in browsers?
No, WebGPU may need to be manually enabled in your browser settings.
What audio formats does Whisper WebGPU support?
Whisper WebGPU supports common formats like WAV, MP3, and AAC, but exact supported formats may vary based on implementation.