Kokoro is an open-weight TTS model with 82 million parameters.
CPU powered, low RTF, emotional, multilingual TTS
Transcribe Persian audio files into text
Transcribe spoken Russian into text
Transcribe Persian audio to text
GPT-SoVITS for MITA!
Convert text to speech with voice customization
High-fidelity Text-To-Speech
Converse with Claude Play.ai and WebRTC ⚡️
Generate text transcripts with timestamps from audio or video
Generate anime character speech from text
MP-SENet is a speech enhancement model.
Pyxilab's Pyx r1-voice demo
Kokoro TTS is an advanced text-to-speech (TTS) tool designed to generate high-quality audio from text. It utilizes cutting-edge AI technology to deliver natural-sounding speech in multiple voices. Version 1.0 of Kokoro TTS introduces enhanced features and improvements, making it a robust solution for speech synthesis tasks.
• Multiple Voices: Choose from a variety of voices to customize the output.
• SSML Support: Fine-tune the speech output using Speech Synthesis Markup Language.
• High-Quality Audio: Generate clear and natural-sounding audio files.
• Customization: Adjust settings like pitch, speed, and tone to suit your needs.
• Integration: Easily integrate with other applications for seamless workflows.
What formats does Kokoro TTS support?
Kokoro TTS supports WAV, MP3, and other common audio formats for output.
Can I use Kokoro TTS for commercial purposes?
Yes, Kokoro TTS is suitable for both personal and commercial use, depending on the licensing agreement.
How many voices are available in Kokoro TTS?
The number of voices varies, but Kokoro TTS offers a diverse range of voices in different languages and tones.