SSML-prosody-library

Open Source framework for voice and multimodal conversational AI

Build real-time multimodal AI applications ????

??♀?Your new best friend powered by an artificial neural network

Conversational AI SDK for iOS to enable text and voice conversations with actions (Swift, Objective-C)

Conversational AI SDK for Android to enable text and voice conversations with actions (Java, Kotlin)

? The React for Voice and Chat: Build Apps for Alexa, Messenger, Instagram, the Web, and more

Conversational AI SDK for Ionic to enable text and voice conversations with actions (React, Angular, Vue)

? Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断

Conversational AI SDK for Apache Cordova to enable text and voice conversations with actions (iOS and Android)