Speech-to-Text

完全解耦的浏览器语音 SDK：独立的唤醒词检测 + 语音转写，支持智能自动停止。

A modern React package for voice-to-text conversion with real-time speech recognition and file upload support

Soniox async transcription helpers and SRT generation (TypeScript port).

n8n community node for Wiro AI — 290+ AI models: video, image, audio, LLM, 3D, and more.

Welcome to the MonsterAPI Whisper Playground! This React template allows you to quickly set up a real-time speech-to-text transcription application using the Whisper model from MonsterAPI.

On-device speech-to-text and voice control for web applications with Moonshine.

A library for text-to-speech (TTS) and speech-to-text (STT) operations using Google Cloud and OpenAI.

openai-whisper-js is a Node.js wrapper for the OpenAI Whisper library, enabling seamless audio transcription using Whisper models. This package simplifies the process of interacting with Whisper by providing a JavaScript interface to execute transcription

Node bindings for OpenAI's Whisper. Optimized for CPU.

Essa solução de biblioteca é para quem usa estrutura funcional e não quer abdicar o uso de hooks já que a antiga só tem suporte para o uso de classes.

Live SDK for Maestra AI transcription services

An improved speech recognition library with TypeScript support

getUserMedia to Text via Google's Speech to Text API

This package provides an integration for Deepgram's speech-to-text and text-to-speech services within the Restack AI framework.

A powerful AI package (built using typescript) for interacting with the Google Bard API, without needing to set your own cookie!

React voice search component with audio visualization, speech recognition, and cross-browser support for Web Speech API. SSR-compatible with Next.js.

React hook for speech-to-text using multiple STT providers

Audio file transcription services. Your speech. Private.

n8n community node package for interacting with the AssemblyAI API for speech-to-text transcription

Use the AssemblyAI block for Studio to use AssemblyAI's models to [transcribe audio with Speech-to-Text models](https://www.assemblyai.com/products/speech-to-text?utm_source=studio), analyze audio with [audio intelligence models](https://www.assemblyai.co

A React Native utility kit for AI-powered apps with chat, image generation, speech-to-text, and text-to-speech capabilities

A minimal CLI tool that gives you quick voice typing in every Mac app.

Microphone plugin for use of speech-to-text in Hyper Butter

Node.js backend package for building AI chatbots and voicebots with Retrieval-Augmented Generation (RAG). It ingests website pages or local files (PDF, DOCX, TXT, MD), creates embeddings with LangChain + OpenAI, stores them in a fast in-memory vector data

The default blueprint for ember-cli addons.

Library for managing Argmax Local Server on macOS

🎙️ Real-time conversational audio with AI transcription. Build ChatGPT-style voice interfaces in minutes with <300ms latency

Library for managing Argmax Local Server on macOS

A text-to-speech library for React Native IOS version.

A wrapper around the Web Speech API for speech-to-text functionality.

React Native module for IBM Bluemix services

Dynamic Sentence Error Rate Testing: A Package for testing the CRIS speech-to-text model, quantifying the quality of the model with respect to its Word Error Rate

AugnitoSDK lets you make use of the Speech Recognition AI. You can edit, format and complete reports at the speed of human speech, with the best-in-class accuracy

A text-to-speech library for React Native.

Simple speech-to-text in the browser for choo

For using the node `speech-to-text`, `sox` is needed for mac/windows users and `arecord` is needed for linux users.

Official SDK for SLNG.AI Voice API - Text-to-Speech, Speech-to-Text, and LLM services

Dialog extensions for botbuilder-calling to manage speech-to-text and language understanding

Generic word-error-rate evaluation package

DataFire integration for Cloud Speech-to-Text API

This angular library helps you recording someone and put the output audio into a Google Speech-to-text compatible format.

CLI tool that transcribes audio/video files using AssemblyAI's API and outputs formatted markdown transcripts

A Node.js package that converts text to speech (TTS) and generates MP3 audio files, using the Google Translate API. A simple and efficient solution for adding voice to your projects.

You can query the blockchain using voice.

Node.JS library for Yandex Cloud Speech-to-Text with streaming recognition

Aiola Speech-To-Text JavaScript SDK

React component for speech-to-text transcription with silence detection

Web Speech API adapter to use Cognitive Services Speech Services for both speech-to-text and text-to-speech service.

A Quill rich text editor module that adds speech-to-text input capabilities

Multi-tenant ElevenLabs MCP server for advanced speech-to-text transcription with speaker diarization