Frontend-SDK for integrating with the UneeQ Digital Human Platform
Invox Dictation SDK
Official Speko TypeScript SDK — one API, every voice provider
Declarative Web Speech components for Web Components. Framework-agnostic SpeechSynthesis (TTS) and SpeechRecognition (STT) primitives via wc-bindable-protocol.
百度数字员工基础套件 - AI智能体、语音识别、数字人渲染全链路SDK,事件驱动、框架无关
MCP server for SaluteSpeech — speech recognition and synthesis (Russia)
Platform Native SDK Kit for MRI OTA Mono
Sentifyd Realtime conversational AI chatbot with 3D avatar - npm package for React, Vue, and modern web frameworks
Sentifyd conversational AI chatbot with 3D avatar - npm package for React, Vue, and modern web frameworks
Build web apps with lifelike AI characters. The Convai Web SDK gives you real-time voice, lipsync, emotions, and dynamic context — with first-class support for React and vanilla TypeScript.
Browser/JavaScript SDK for SAA, the addressee layer for voice agents — emits a turn_ready event per device-directed utterance so only speech meant for your agent reaches your STT, LLM, or TTS. No wake word.
Declarative speech-recognition component for the AmiVoice cloud API. Server-side APPKEY, browser mic capture, two-channel relay, via wc-bindable-protocol.
Zero-dependency client SDK for ASR WebSocket speech recognition.
React component and hook to initiate a SpeechRecognition session