#Speech-synthesis
Showing 60 of 82 repositories tagged #speech-synthesis, ranked by stars
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
🧠 Leon is your open-source personal assistant.
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
End-to-End Speech Processing Toolkit
so-vits-svc fork with realtime support, improved interface and more features.
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
Build local voice agents with open-source models
Generate audiobooks from EPUBs, PDFs and text with synchronized captions.
Foundational model for human-like, expressive TTS
Converts text to speech in realtime
Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
An open-source ChatGPT app with a voice
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Controllable and fast Text-to-Speech for over 7000 languages!
Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
a free and open source speech synthesizer for Russian and other languages
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
An Open-Sourced LLM-empowered Foundation TTS System
DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
The Implementation of FastSpeech based on pytorch.
A talking LLM that runs on your own computer without needing the internet.
AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.
A Generative Flow for Text-to-Speech via Monotonic Alignment Search
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
Machine learning based speech synthesis Electron app, with voices from specific characters from video games
RNN-based generative models for speech.
Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2
High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！
StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
Translations with speech synthesis in your terminal as a ruby gem
A simple text-to-speech client for Azure TTS API.
libfaceid is a research framework for prototyping of face recognition solutions. It seamlessly integrates multiple detection, recognition and liveness models w/ speech synthesis and speech recognition.
Audio Development Tools (ADT) is a project for advancing sound, speech, and music technologies, featuring components for machine learning, sound synthesis, speech and music generation, signal processing, game audio, digital audio workstations (DAWs), and more.
ICASSP 2022: "Text2Video: text-driven talking-head video synthesis with phonetic dictionary".
Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.
UTokyo-SaruLab MOS Prediction System
WaveNet-Vocoder implementation with pytorch.
A fast, high-quality neural vocoder.
Access the latest AI models like ChatGPT, LLaMA, Deepseek, Diffusion, Hugging face, and beyond through a unified prompt layer and performance evaluation
World's First Multilingual Inexpensive Therapeutic Sophisticated Ultra-responsive Holographic Agent. In simple terms, an AI you can talk to and it'll talk back with a body using VTube Studio.
AI-WEBUI: A universal web interface for AI creation, 一款好用的图像、音频、视频AI处理工具
Translations with speech synthesis in your terminal as a node package
Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT, code supports SV) — C++, C#, Rust, Go, Python, npm (WASM). VITS + Prosody, streaming, CUDA/CoreML/DirectML. pip install piper-plus | npm install piper-plus | cargo install piper-plus-cli