web-speech-cognitive-services
Polyfill Web Speech API with Cognitive Services Speech-to-Text service
Polyfill Web Speech API with Cognitive Services Speech-to-Text service
[![npm version](https://badge.fury.io/js/react-say.svg)](https://badge.fury.io/js/react-say) [![Build Status](https://travis-ci.org/compulim/react-say.svg?branch=master)](https://travis-ci.org/compulim/react-say)
Browser TTS (using Web speech API) made easy
A JavaScript text to speech (TTS) library. Provides you with high quality TTS voices in many languages and a high quality language. These voices and engines runs on a Talkify hosted server. This lib also supports browser built in voices via the SpeechSynt
Client library for using Talestreamer in node.js (rich speech synthesis for your voice applications)
Client library for using Talestreamer in node.js (rich speech synthesis for your voice applications)
lib for recognition and synthesis of speech
Quickly add text-to-speech widgets to HTML, using the Web Speech API.
A React component that uses the Speech Synthesis API to read text out loud by sentence or word while the user follows along with their mouse or finger
RxJS text-to-speech wrapper
AI Interaction Software Development Kit
Basic wrapper around browser TTS functionality
Select and speak
Use TikTok TTS from node.js
A versatile library designed to interact with various AI services, including text generation, image processing, and audio conversion.
Overview -------- This npm package provides a simple and convenient way to perform text-to-speech (TTS) synthesis in your web applications. It utilizes either the Web Speech API or an external API to convert text into spoken language.
An easy-to-use speech toolset. Includes tools for synthesis, recognition, alignment, speech translation, language detection, source separation and more.
Polyfill Web Speech API with Cognitive Services Speech-to-Text service
Evaluate and integrate with latest AI models including ChatGPT, Llama, Diffusion, Cohere, Gemini, and Hugging Face.
Node.JS library for Sber SmartSpeech Text-To-Speech