Mastra Deepgram voice integration
A speech to text module.
macOS local GPU speech workspace for document reading, dictation, and library analysis.
Microsoft Cognitive Services Speech plugin for Sketch-thru-Plan
CLI for the MiniMax AI Platform
Microsoft Speech SDK for browsers
Customizable chat component for AI APIs
A React component that visually hides its content
Generates a Google Cloud Speech API SpeechContext for an API.AI agent.
FLAC data stream encoder and decoder compiled in JavaScript using emscripten.
Rhino Speech-to-Intent engine for web browsers (via WebAssembly)
Web api for using VITS based models in the browser!
A high-performance React Native library for text-to-speech on iOS and Android
Functional wrapper around the SpeechRecognition Web API
Bindings for the WebRTC VAD.
Powerful, user-friendly voice activity detector (VAD) for the browser
🎤 Make websites that talk. Demo: https://computer_programmer.neocities.org/browser-speech
Press Ctrl+Shift+R to dictate prompts into Pi using VolcEngine ASR
Type-safe MiniMax TTS client for Node.js — sync & streaming synthesis, voice cloning, voice design. ESM + CJS.
Customizable chat component for AI APIs
TypeScript definitions for react-speech-kit
React Native Real-time Speech Recognition Library powered by Nitro Modules
Node binding for continuous offline voice recoginition with Vosk library.
<div align="center">