A speech to text module.
Authenticated experimental speech transcription for browser clients
Experimental speech recognition with independently selectable providers
Local SenseVoice ONNX transcription with a managed sherpa-onnx process
Javascript client library for Soniox Speech-to-Text websocket API
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
The AssemblyAI JavaScript SDK provides an easy-to-use interface for interacting with the AssemblyAI API, which supports async and real-time transcription and text-to-speech.
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
Node implementation of Deepgram's WebVTT and SRT formatting. Given a transcription, this package can return a valid string to store as WebVTT or SRT caption files.
TypeScript/Node.js bindings for transcribe.cpp — a C/C++ speech-to-text library built on ggml
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
n8n node for integrating Palatine Speech API into workflow
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
Official Soniox SDK for client-side applications
Browser SDK for SpekoAI — real-time voice conversations
Official Soniox SDK for Node
TikTok LIVE API for Node.js: The #1 library for real-time chat, gift, like, follow and viewer events from any TikTok livestream.
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
Simple cross-browser speech to text using react hooks.
Glin-Profanity is a lightweight and efficient npm package designed to detect and filter profane language in text inputs across multiple languages. Whether you’re building a chat application, a comment section, or any platform where user-generated content
Cross-platform speech recognition library for React Native using native APIs (Speech Framework & SpeechRecognizer)
Node bindings for OpenAI's Whisper. Optimized for CPU.
Polyfill Web Speech API with Cognitive Services Speech-to-Text service
Fast, accurate, on-device speech-to-text, text-to-speech, and voice dialogs in the browser via WebAssembly.
Multi-engine ASR (Whisper + NVIDIA Parakeet + MOSS-Transcribe-Diarize) inference addon for qvac on the Bare runtime
An easy way to run AI models in React Native with ExecuTorch
Bare-only in-process core of the QVAC SDK. Runs inference directly on the Bare runtime with explicit plugin assembly and no RPC, worker, or subprocess layer.
Authenticated experimental speech transcription for browser clients
Local SenseVoice ONNX transcription with a managed sherpa-onnx process
Durable, framework-light browser voice input with IndexedDB recovery, pluggable transcription, and optional React controls.
n8n community node for Transcript.lol - AI-powered audio and video transcription service
Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection
AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.
Transcribe audio in the browser using Whisper and WebGPU
Reson8 STT plugin for LiveKit Agents for Node.js
Speech-to-text for Clipkit — transcribe an audio/video source into word-timestamped captions. Runs the same Whisper model (Transformers.js / ONNX) in the browser (WebGPU/WASM) and in Node (onnxruntime-node); no paid API, no native binaries. The output map
Official Soniox React SDK
React Native wrapper for sherpa-onnx TTS and STT capabilities
Experimental speech recognition with independently selectable providers
On-device speech-to-text and voice control for web applications with Moonshine.
Offline Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD with sherpa-onnx for React NativeSpeech-to-Text with sherpa-onnx for React Native
Companion tools for Swttch that live outside the plugin bundle: Claude Code account/usage SDK, the ccb CLI, speech-to-text and text-to-speech.
Client audio capture, host transcription, and autonomous narration for Pi agents.
Speech recognition module for react native using Vosk library
Local Needle tool calling and Whistle speech transcription for browsers and Node.js, standalone or with Vercel AI SDK.
One chat for every product: a composer with a microphone that always works, a thread that does not fight the reader, messages with copy and retry, LLM markdown, and a messenger for people and the agents among them — the fleet's chat standard as a package.