ML-powered speech recognition directly in your browser
Generate Vietnamese speech from text and reference audio
Generate text from audio input
MaskGCT TTS Demo
Talk to Qwen2Audio with Gradio and WebRTC ⚡️
✨[With v1.0.0] Accelerated TTS on Kokoro-82M
Generate realistic voices from text
Generate speech from text
Generate audio and SRT subtitles from text
Transcribe Persian audio to text
Kokoro is an open-weight TTS model with 82 million parameters.
Turn Any Article to Podcast
Whisper Large V3 Turbo WebGPU is a machine learning-powered speech recognition tool designed to work directly in your web browser. It leverages advanced WebGPU technology to enable fast and accurate transcription of spoken words into text. This tool is optimized for real-time performance, making it ideal for applications requiring quick and reliable speech-to-text conversion.
• Real-time transcription: Convert spoken words into text instantly. • Browser-based: Operates directly in your web browser without the need for additional software. • High accuracy: Delivers precise transcription even in noisy environments. • WebGPU optimized: Utilizes WebGPU for enhanced performance and efficiency. • Multi-language support: Supports transcription in multiple languages.
What browsers support Whisper Large V3 Turbo WebGPU?
Whisper Large V3 Turbo WebGPU is optimized for modern browsers that support WebGPU, including Chrome, Firefox, and Safari.
Is my speech data private?
Yes, all transcription happens locally in your browser, ensuring your speech data remains private and secure.
Can I use it in noisy environments?
Yes, Whisper Large V3 Turbo WebGPU is designed to handle background noise and deliver accurate transcriptions even in less-than-ideal acoustic conditions.