Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

A fast, local neural text to speech system

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

a free and open source speech synthesizer for Russian and other languages

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

Suno AI's Bark model in C/C++ for fast text-to-speech generation

Make Azure natural TTS voices accessible to any SAPI 5-compatible application.

Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android

Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.

This plugin integrates Azure Speech Cognitive Services in Unreal Engine.

Desktop application for neural speech synthesis written in C++

A ggml (C++) re-implementation of tortoise-tts

Windows "say"

Web interface for Microsoft Sam & friends

Streaming TTS based on Piper with optional RK3588 NPU support

Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT) — C++, C# (.NET), Rust, Python SDKs. VITS + Prosody, streaming, CUDA/CoreML/DirectML, custom dictionaries. Install: pip install piper-tts-plus | dotnet tool install PiperPlus.Cli | cargo install piper-plus-cli

A lightweight pure C++ Text-to-Speech (TTS) pipeline with OpenVINO, supporting multiple languages.

Persian Text-To-Speech