Simple Space for the Kokoro Model
Kokoro is an open-weight TTS model with 82 million parameters.
Talk to Qwen2Audio with Gradio and WebRTC ⚡️
WebGPU text-to-Speech powered by OuteTTS and Transformers.js
Generate speech from text with adjustable speed
SText to Audio(Sound SFX) Generator
Generate text from audio input
Convert text to speech with different voices
Generate audio from text with customizable voice
"Designed for all users, including those with disabilities."
Lunch web-based text-to-speech interface
A demo of Indic Parler-TTS
Kokoro is a cutting-edge speech synthesis tool designed to generate high-quality speech from text. It serves as a simple and dedicated space for the Kokoro model, allowing users to leverage advanced text-to-speech capabilities. With support for multiple engines and models, Kokoro makes it easy to convert written content into natural-sounding audio.
• Multiple Engines and Models: Kokoro supports various speech synthesis engines and models, ensuring diverse voice options.
• Custom Voice Generation: Users can generate speech using different voices tailored to their needs.
• Multi-Language Support: Kokoro enables text-to-speech conversion in multiple languages, catering to a global audience.
• User-Friendly Interface: The platform is designed for simplicity, making it accessible even to those new to speech synthesis.
What types of text can Kokoro process?
Kokoro supports a wide range of text inputs, including articles, scripts, and casual writing. It is designed to handle most written content effectively.
Can Kokoro be used offline?
No, Kokoro is primarily an online tool and requires an internet connection to process and generate speech.
How do I access different voices in Kokoro?
To access different voices, navigate to the settings or voice selection menu within the platform. Here, you can choose from available options based on your needs or preferences.