An AI-powered personalized children's education platform. We provide instant, dynamic adjustments to various content formats of children's learning experiences and interactive creation. Using LLMs, image generation, voice content, and video content generation technologies, engaging multimedia children's educational content in multiple languages.

🔊 Kokoro Web: Free AI text-to-speech, online or self-hosted, OpenAI compatible!

🗣️🎤 elevenlabs-api is an open source Java wrapper around the ElevenLabs Voice Synthesis and Cloning Web API.

✨ NovelAI api python sdk, easy to use, modern and user-friendly.

AI generates conversational podcast for ANY research paper, vividly!

Voice Alignment and Conversion with Neural Networks and the WORLD codec.

A script that automatically installs all the required stuff to run selected AI interfaces on AMD Radeon 7900XTX.

EasyTTS是一个便捷的工具，旨在方便地使用第三方API服务来调用OpenAI的文本转语音（TTS）功能。 EasyTTS允许用户输入文本，并选择不同的模型、音色、格式来生成音频文件。

Project page for StableForm-TTS: Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation

Voice Generator Project FEAT. Hatsune Miku

A raspberryPi magic mirror based on facial recognition

Personal surveillance system using screenshots, webcam and OpenAI GPT-4o to check if the user is focused on his tasks. If not, the user will be roasted by GLaDOS voice and character to regain focus again.

create audio books from pdfs with one click , available on windows , linux, mac

Proyecto que utiliza la API de Google Cloud Text-to-Speech para convertir texto en voz natural. Permite sintetizar texto escrito en archivos de audio reproducibles, con aplicaciones en accesibilidad, asistentes virtuales e interfaces interactivas.

Your AI Clone with Voice Capabilities

Text-to-Speech Voiceover Generator

NeuroTalk can demonstrate that EEG contain the properties needed to generate mel-spectrograms, and show that EEG can generate speech