Search results
95 packages found
A powerful AI package (built using typescript) for interacting with the Google Bard API, without needing to set your own cookie!
Video Summary SDK is a powerful Node.js module for advanced video processing, offering features like speech-to-text transcription, content summarization, automatic chapter extraction, and comprehensive video summarization. It's perfect for developers look
- video processing
- speech-to-text
- video summarization
- audio transcription
- whisper
- audio summarization
- transcription
- chapter extraction
- video analysis
- Node.js
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 simple node.js module that simplifies instantiating our speech synth/recog modules (to be used by ws_speech_server and mrcp_server)
Servicio Angular para manejar el plugin Cordova cordova-plugin-offline-speech ## install - cordova plugins add cordova-plugin-offline-speech - npm i angular-speech-to-text
High level wrappers for AI conversation tools: text to speech, speech to text, LLMs
'react-native-voice-to-text' is a React Native module facilitating real-time conversion of spoken words into text, enabling hands-free interaction in mobile applications for tasks like messaging, note-taking, and search functionalities.
- react-native
- ios
- android
- react-native-voice-to-text
- speech-to-text
- speech recognition
- voice recognition
- voice to text
A node.js library for transcribing audio to text using OpenAIs Whisper model
Real-time speech recognition with Next-gen Kaldi
- speech-to-text
- real-time speech recognition
- without internet connection
- embedded systems
- open source
- zipformer
- asr
- speech
- WebAssembly
- wasm
- local
- privacy
- ncnn
Use speech-to-text and/or word prediction to support writers' needs. Runs on any Chromium, Safari, or Firefox based browser that supports WebAssembly.
This is a node.js module used to transcribe wav files using Olaris v2 realtime transcription service
👂 RxJS operator for realtime speech-to-text (STT/S2T) using Deepgram speeh-to-text
- speech-to-text
- s2t
- stt
- transcription
- transcribe
- voice control
- deepgram
- speech recognition
- rxjs
- reactive
- observables
- stream
- streaming
- realtime
👂 RxJS operator for realtime speech-to-text (STT/S2T) using AWS Transcribe
- speech-to-text
- s2t
- stt
- transcription
- transcribe
- voice control
- aws transcribe
- speech recognition
- rxjs
- reactive
- observables
- stream
- streaming
- realtime
👂 RxJS operator for realtime speech-to-text (STT/S2T) using Google speeh-to-text
- speech-to-text
- s2t
- stt
- transcription
- transcribe
- voice control
- gcp speech-to-text
- speech recognition
- rxjs
- reactive
- observables
- stream
- streaming
- realtime
Node bindings for OpenAI's Whisper. Optimized for CPU. (Updated with latest whisper.cpp September 2023)
Node bindings for OpenAI's Whisper. Optimized for CPU.
The speech to text API provides two endpoints, transcriptions and translations, based on our state-of-the-art open source large-v2 Whisper model.
- node-red
- nodejs
- javascript
- api
- flow
- npm
- machine-learning
- node
- example
- speech-to-text
- openai
- conversational-ai
- whisper
- whisper-1
- View more
Node.js plugin for speech recognition that works with OpenAI's Whisper models using ONNX.
- openai
- whisper
- onnx
- huggingface
- transformers
- transformers.js
- transcribe
- audio recognition
- speech
- speech-to-Text
- wav2text
- stt
- tts
A free package for SpeechRecognition
cordova-offile-speech is a Cordova plugin for speech functionality.