🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

Persian/Farsi text to speech(TTS) training using coqui tts

Korean TTS using coqui TTS (glowtts and multiband melgan) - 한국어 TTS

An implement of GlowTTS model. Several modes are added: speaker embedding, prosody encoder(GST), and gradient reversal.

Tensorflow implementation of Glow-TTS

제주어 음성 합성 (보완 중)

An end-to-end Neural Voice AI system featuring zero-shot voice cloning and generative text-to-speech. Powered by XTTS-v2 and Glow-TTS with a PyTorch/Flask inference backend. The application is fully Dockerized for live cloud deployment on Hugging Face Spaces and wrapped in a futuristic, audio-reactive WebGL interface featuring glassmorphism design.

🔊 Convert text into MP3 audio files quickly, enhancing content, accessibility, and automation with clear, spoken audio.

🎤 Create high-quality text-to-speech audio using FastSpeech 2 in PyTorch. Easily customize for English and Mandarin with multi-speaker support.

🗣️ Enable text-to-speech with Qwen TTS, a simple API solution that seamlessly integrates into your applications using Docker and Home Assistant.

Generate AI-voiced short videos with synced subtitles using Python, ElevenLabs TTS, and FFmpeg for clear, automated social media and educational content.

포스코 청년 AI·Big Data 아카데미 - AI 프로젝트

Offline-capable, multilingual voice-based medical assistant using Claude 3.5, BioGPT, Whisper, and RAG. Built for reliability in low-connectivity settings.

Support AI vs AI matches for Gomoku, Xiangqi, and Chess with customizable API integration and real-time legal move validation in a Next.js app.

Generate zero-shot multilingual TTS nodes for ComfyUI with voice cloning and voice design, supporting 600+ languages

Accelerate Qwen3-TTS inference with Triton kernel fusion for faster text-to-speech performance on NVIDIA GPUs

Run pure C inference for Mistral Voxtral-4B-TTS with mmap safetensors, BF16 weights, and 24kHz WAV output.