A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
Updated means this listing was last refreshed on Mar 22, 2026.
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control Aratako/Irodori-TTS is an open source project on GitHub with 166 stars. Built primarily in Python. Licensed under MIT. Topics: diffusion-models, flow-matching, python, speech-synthesis, text-to-speech, tts, voice-cloning.
Create podcasts, audiobooks, and videos with cinematic emotional voice cloning that laughs, whispers, and breathes naturally. The tool supports many languages and can also produce
Edit Video & Audio as Easily as a Text Document
The Worlds Most Realistic AI Speech & Video Dubbing
Cursor Editor
The AI-First Code Editor Built for Speed & Efficiency
StudyBuddy
AI tool for summarizing documents and generating study aids like flashcards and quizzes.
AIclicks
Track your brand visibility in ChatGPT, Gemini, and Perplexity: GEO/AEO monitoring, competitor analysis, analytical reports, weekly recommendations, content creation, and LLM optim
Google Antigravity
The next generation of AI development platforms (IDEs) powered by Google's Gemini 3. It can plan, code, test, and debug complete applications autonomously. You can also create your