Speech synthesis

Speech-to-Speech is a modular, low-latency voice-agent pipeline that chains VAD → STT → LLM → TTS components, exposing them via an OpenAI...

VieNeu-TTS is a specialized Vietnamese text-to-speech system with instant voice cloning, designed for on-device inference with real-time CPU...

VoxCPM2 is a tokenizer-free text-to-speech system generating multilingual speech with 48kHz audio quality, supporting 30 languages, voice design from...

Abogen is a specialized text-to-speech tool that converts ePub, PDF, text, and markdown files into audiobooks with synchronized subtitles, using the...

Chatterbox TTS Server is a self-hosted text-to-speech API server that wraps Resemble AI's open-source Chatterbox TTS model, offering...

MLX-Audio is a specialized speech processing library for Apple Silicon Macs, providing TTS, STT, and STS capabilities optimized for M-series chips...

Supertonic is a compact (99M-parameter), on-device multilingual text-to-speech engine that runs locally via ONNX Runtime across 31 languages with low...

edge-tts is a Python library that provides access to Microsoft Edge's neural text-to-speech service without requiring Edge, Windows, or API keys. It...

Speech Note is a Linux desktop and Sailfish OS application for note-taking, reading, and translating text entirely offline using local...

NVIDIA NeMo Speech is a production-grade framework for building speech AI systems, including automatic speech recognition (ASR), text-to-speech...

ESPnet is an end-to-end speech processing toolkit supporting speech recognition, text-to-speech, speech translation, speaker diarization, speech...

PaddleSpeech is a specialized speech and audio toolkit built on PaddlePaddle that provides state-of-the-art models for ASR, TTS, speaker...

RHVoice is a free, open-source speech synthesizer using statistical parametric synthesis (HTS-based) that supports 10+ languages including Russian,...

A fork of so-vits-svc that adds realtime voice conversion and improved UI for singing voice synthesis using SoftVC VITS models. This is a specialized...

Leon is an open-source personal AI assistant built with TypeScript and Python, designed to operate locally with privacy-aware execution. It serves...

Voice-Pro is a Gradio-based web application for creators and developers that integrates YouTube downloading, speech recognition (Whisper),...

eSpeak NG is a compact, open-source text-to-speech synthesizer supporting over 100 languages and accents across Linux, Windows, Android, and other...

OpenUtau is an open-source singing synthesis editor designed as a successor to UTAU, enabling users to create expressive vocal covers and original...

Amphion is a specialized toolkit for audio, music, and speech generation tasks (TTS, singing voice synthesis, voice conversion, text-to-audio, and...