Kokoro is an open-weight TTS model with 82 million parameters.
Generate text and audio responses to user queries
Generate speech using a speaker's voice
Generate speech from text with reference audio
Talk to Qwen2Audio with Gradio and WebRTC ⚡️
Generate audio from text in multiple languages
Transcribe voice to text
Generate audio from text with adjustable speed
Explore and analyze audio data with AudioBench Leaderboard
Generate natural-sounding speech from text using a voice you choose
Generate speech from text with adjustable rate and pitch
Better AI powered platform to purify your speech signal
viXTTS Demo is a state-of-the-art speech synthesis application designed to showcase the capabilities of advanced text-to-speech technology. It allows users to explore and experiment with voice generation, tone customization, and speech patterns in a user-friendly environment. The demo version provides a glimpse into the full-range features of the viXTTS platform.
• Text-to-Speech Conversion: Easily convert written text into natural-sounding speech. • Voice Customization: Adjust pitch, speed, and tone to create unique voice outputs. • Multiple Languages Support: Generate speech in various languages to cater to a global audience. • Real-Time Preview: Hear the output in real-time before finalizing the audio. • User-Friendly Interface: Intuitive design for seamless navigation and customization. • Customizable Settings: Fine-tune speech parameters to achieve the desired output.
What is included in the viXTTS Demo?
The demo version includes core features of the full application, allowing users to explore text-to-speech conversion, voice customization, and basic settings. Advanced features may be limited or unavailable in the demo.
How do I save the generated audio?
To save the audio, go to the "Output" section, select the desired format, and choose a location to save the file. Note that some saving options may be restricted in the demo version.
Does viXTTS Demo support multiple languages?
Yes, the demo version supports multiple languages, allowing users to generate speech in various languages. The exact list of supported languages may be limited compared to the full version.