A node.js library for transcribing audio to text using OpenAIs Whisper model
Mastra Sarvam AI voice integration
Google cloud speech to text streaming GRPC module
MCP server for audio transcription using Gemini models via OpenRouter
Comprehensive Cloudflare Workers & Pages integration with config-based patterns, middleware, router, workflows, AI (with text-to-image, audio/music generation, TTS, ASR), React hooks, multi-tenant support, and the cf-ship deploy CLI
Hold space to dictate into pi's prompt, transcribed locally with sherpa-onnx.
TypeScript typings for Cloud Speech-to-Text API v1p1beta1
MCP server for vid2context. Turn any video into context for AI agents and LLMs: YouTube transcripts, captions, speech-to-text, metadata and chapters with timestamps your agent can cite. Free-first: local models, then free tiers, then keyless hosts, paid A
React Native wrapper for Moonshine Voice on-device transcription
Speech-to-text native module for React Native (iOS & Android).
Voice plugin for TheoKit — STT + TTS bridge with browser MediaRecorder helper + UI components.
Speech-to-text core for Koncept UI - a Web Speech API session with auto-restart, transcript assembly, caret-aware insertion into text fields and audio level bars. Framework-free TypeScript, zero runtime dependencies.
Official Speko TypeScript SDK — one API, every voice provider
Local speech-to-text for Pi
Drop-in AI chat UI for React Native & Expo: streaming markdown, chat history, image/document sharing, voice, and one-line OpenAI / Claude / Gemini setup.
A highly customizable React chatbot component with support for Gemini, OpenAI, Anthropic, and Groq APIs.
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
TypeScript SDK for transcribing videos from YouTube, X, TikTok, Instagram, Facebook, Bluesky, Twitch, Dailymotion, Pinterest, LinkedIn and Snapchat, plus audio/video files, with transcript1.
Better input experience for DeepSeek Harness: file-to-Markdown, local file input, prompt optimization, and voice input
MCP server for apimodels.app — call chat, image, video, speech, transcription, music, embedding and media models, plus the asset library, with one API key, from Claude Desktop, Cursor and any MCP client.
n8n node for AssemblyAI speech-to-text transcription models.
This can use to convert voice to text real time in device
Martin's self-contained two-way voice plugin for the DSH web app: unified voice composer in, per-message speaker buttons and auto-read out (own TTS server), plus the speech-to-text wiring. Forked from @deepseek-ai/dsh-experimental-client-ui-voice-input 0.
Local Whisper (multilingual, Russian-capable) ONNX transcription with a managed sherpa-onnx process; downloads its model on first use
google-cloud-speech-to-text
React Native module that allows an React Native application to call native speech recognition APIs and to get the recognized text in return. This is a work in progress since it only works on Android. Although the work on iOS is almost finished.
Experimental speech recognition with independently selectable providers
A highly customizable React chatbot component with support for Gemini, OpenAI, Anthropic, and Groq APIs.
A library for using Web Speech API with Angular
AdminForth audio adapter for OpenAI speech-to-text and text-to-speech.
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection [termux android-arm64 build with bundled .so]
Command line for vid2context. Turn any video into context for AI agents and LLMs: YouTube transcripts, captions, speech-to-text, metadata and chapters with timestamps your agent can cite. Free-first: local models, then free tiers, then keyless hosts, paid
TypeScript port of SYSTRAN/faster-whisper for Node.js, built on CTranslate2, Koffi, FFmpeg, and ONNX Runtime.
Authenticated experimental speech transcription for browser clients
N8N community node for Groq API - Speech-to-Text transcription using Whisper AI. Convert audio to text with high accuracy. Perfect for WhatsApp voice messages, audio files, and voice automation workflows.
Runs voice conversations with live transcription, chat orchestration, and spoken replies.
Qwen ASR Realtime WebSocket client with microphone recording
Speech-to-text interface for Directus using OpenAI Whisper API
Live speech-to-text that runs entirely in the browser (Parakeet TDT v3 on WebGPU or WASM).
The official Node.js REST API wrapper for Rymi.
Permissionless communication supercharger MCP server — 40+ Lightning-paid tools: AI phone calls in any language, voice in 602 languages, translation across 119 plus 452 rare languages frontier models don't serve, fax, SMS, transcription, audiobooks, and m
Run LLMs locally and offline with React Native & Expo - Tool calling, RAG, Speech-to-Text, Text-to-Speech, and VAD
MCP server for OpenRouter — 21 tools: chat with 300+ LLMs, analyze & generate images/audio/video, TTS/STT, embeddings, reranking, structured decisions, async completions, response caching
DSH audio tools: probe, convert/extract audio tracks, and transcribe speech with your own ffmpeg + whisper.cpp or any OpenAI-compatible transcription API.