Kokoro is an open-weight TTS model with 82 million parameters.
Generate speech from text with customizable voices
Transcribe audio from microphone, file, or YouTube link
Transcribe audio with emotions and events
Convert speech to text from audio files
Accessibility PDF & pasted text to speech converter w/ gTTs
✨[With v1.0.0] Accelerated TTS on Kokoro-82M
Request evaluation of a speech recognition model
audio-arena
Convert spoken words to text
Convertir texto a audio
Transcribe or translate audio and YouTube videos
viXTTS Demo is a speech synthesis application that allows users to convert text into natural-sounding speech. It provides an easy-to-use platform to explore the capabilities of voice synthesis technology. Designed for quick demonstrations, the tool is perfect for testing various speech outputs and experimenting with different voices and settings.
• Multiple Voices: Access a variety of voices to customize the output.
• Language Support: Synthesize text in multiple languages for global compatibility.
• Customization Options: Adjust speech parameters like speed, pitch, and volume to tailor the output to your needs.
• User-Friendly Interface: An intuitive web-based interface makes it easy to input text and generate speech.
• Real-Time Synthesis: Get instant results with minimal processing time.
• Download Capability: Save the generated speech as audio files for later use.
What is the purpose of viXTTS Demo?
viXTTS Demo is designed to showcase the capabilities of speech synthesis technology, allowing users to experiment with text-to-speech conversion in a user-friendly environment.
Is viXTTS Demo free to use?
Yes, the demo version is free to use for testing and evaluation purposes. For commercial use, please refer to the licensing terms.
Which languages does viXTTS Demo support?
The tool currently supports a range of languages, including English, Spanish, French, German, and Chinese. Additional languages may be added in future updates.