Simple Space for the Kokoro Model
Generate speech from text
Whisper model to transcript japanese audio to katakana.
Convert text to speech with different voices
Kokoro is an open-weight TTS model with 82 million parameters.
Transcribe audio from microphone, file, or YouTube link
Generate speech from text with customizable voices
MaskGCT TTS Demo
Talk to Qwen2Audio with Gradio and WebRTC ⚡️
Generate realistic audio from text
Transcribe audio with emotions and events
Turn Any Article to Podcast
Transcribe YouTube videos to text
Kokoro is a speech synthesis tool designed to convert text into natural-sounding speech. It provides a simple and intuitive interface for generating audio from written content, leveraging advanced models and engines to deliver high-quality voice outputs.
• Multiple Voice Options: Choose from a variety of voices to match your needs.
• Language Support: Generate speech in multiple languages for global accessibility.
• Engine Flexibility: Utilize different speech synthesis engines for varying output styles.
• SSML Support: Customize speech patterns, pitch, and speed using Speech Synthesis Markup Language.
• Real-Time Generation: Quickly convert text to speech with minimal processing time.
What engines does Kokoro support?
Kokoro supports a range of engines, including Google Text-to-Speech, Amazon Polly, and others, depending on your setup.
Can I customize the speech output?
Yes, Kokoro allows you to customize speech using SSML, enabling control over pitch, speed, and emphasis.
Is Kokoro free to use?
Kokoro offers a free tier with basic features, but advanced options may require a subscription or payment.