AurelsOpenAIClient is a simple .NET library for integrating OpenAI APIs into your applications. It supports various functionalities such as Chat Completion, Speech-to-Text, Text-to-Speech, Translation, Image Generation. All you need is an OpenAI API key.
Text-to-speech for Spine apps with what a caption or an avatar needs to follow it: the installed voices with their quality (Apple's Enhanced and Premium voices too), and for each utterance its start, each word as the voice reaches it, its position and its end. AVSpeechSynthesizer on iOS and Mac Catalyst, TextToSpeech on Android, SpeechSynthesizer on Windows. On Apple also speech-to-text from audio the app already has (SFSpeechRecognizer) and the voices rendered to PCM16 for a voice conversation's own engine.
Self-hosted, OpenAI-compatible multimodal AI for .NET Aspire — a LocalAI-based container resource for image generation, text-to-speech, speech-to-text and video generation, with gallery model management, GPU support and Open WebUI. The self-hosted counterpart of AddOllama for everything beyond text.
WebTTS.Ivona provides Ivona Text-To-Speech service to WebTTS core. Read more on GitHub repo.
Shiny Speech - Cross-platform speech-to-text and text-to-speech for .NET MAUI
Shiny Speech - Cross-platform speech-to-text and text-to-speech for .NET MAUI
Generated C# SDK for SmallestAI -- Lightning TTS, Pulse STT, voice cloning, and pronunciation dictionaries.
Voice for Spine apps: a full-duplex audio engine with the platform's echo cancellation, PCM16 in and out at a provider's rate, a playback queue that can be flushed when the user talks over the answer, and levels and 24 bands each way for visuals. The base for realtime voice AI, and voice pipelines that let any chat model (Claude) talk: speech-to-text, the chat and text-to-speech, each on the device or the server.
This repo is C# implementation of edge-tts. EdgeTTS allows you to use Microsoft Edge's online text-to-speech service from C#.
A CLI tool for text-to-speech using Google Gemini TTS API
Core interfaces and models for Text-to-Speech synthesis. Provides ITtsProvider, TtsRequest, TtsResult and other abstractions.
TTS provider implementations for Azure, EdgeTTS, Google, and VoiceRSS. Multi-provider fallback with circuit breaker support.
.NET native android-x64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
.NET native osx-arm64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
.NET native linux-arm64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
.NET native osx-x64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
.NET native android-arm64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
.NET native linux-x64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
Generated C# SDK for Gradium -- text-to-speech, speech-to-text, voices, pronunciations, and metering.
TTS orchestration with circuit breaker pattern and multi-provider fallback chain using Polly.
Use the built-in Text-To-Speech (TTS) engine under Windows, OSX and Linux.
A .NET NuGet package that provides a unified API for working with multiple cloud-based and local Text-to-Speech (TTS) services. Supports 20+ TTS engines including Azure, Google, AWS Polly, OpenAI, ElevenLabs, and SherpaOnnx for offline TTS.
Text-to-Speech models and DTOs shared across Lyo TTS provider implementations.
Connector-agnostic AI abstractions (chat history reduction, transcription, text-to-speech) for Access.It.Ia providers
Piper TTS provider for offline, local text-to-speech synthesis using ONNX neural voice models.
Shared helpers for building Voxta text-to-speech (TTS) modules, including text normalization and audio handling utilities.
A Client for the Reverso Web API, written in C#/.NET (Based on Site API and HTML parsing)
A C# (.NET) library for Microsoft Edge's online Text-to-Speech service. Feature-complete migration of the Python edge-tts library.
Shiny Speech - Cross-platform speech-to-text and text-to-speech for .NET MAUI
OpenAI provider for Access.It.Ia: chat completion, transcription and text-to-speech via Microsoft.Extensions.AI (IChatClient) and the OpenAI SDK
Official C# SDK for Typecast Text-to-Speech API. Supports .NET Standard 2.0+, .NET 6+, Unity (via NuGetForUnity), and Blazor.
.NET native win-x64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
.NET native win-arm64 wrapper for the piper-phonemize project. In general, you don't need to use this package directly. Please use https://www.nuget.org/packages/com.github.csukuangfj.piper.phonemize instead
C# SDK for the Hume AI API -- emotion recognition, expression measurement, empathic voice interface (EVI), and text-to-speech (TTS).
Azure OpenAI provider for Access.It.Ia: chat completion, transcription and text-to-speech via Semantic Kernel
Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without recursion.
A .NET library for VibeVoice text-to-speech using ONNX Runtime. Supports automatic model download from HuggingFace, voice presets, and native C# inference with no Python dependency.
Base Text-to-Speech service interface and implementation for converting text to speech.
Voice cloning extension for ElBruno.QwenTTS. Clone any voice from a 3-second audio sample using the Qwen3-TTS Base model with ECAPA-TDNN speaker encoder.
C# bindings for piper-phonemize, a text-to-phoneme library based on espeak-ng. See https://github.com/csukuangfj/piper-phonemize for details.