Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/evancohen/sonus
:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection
https://github.com/evancohen/sonus
alexa hotword-detection keyword-spotting node speech speech-recognition speech-to-text stt voice-control voice-recognition
Last synced: about 2 months ago
JSON representation
:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection
- Host: GitHub
- URL: https://github.com/evancohen/sonus
- Owner: evancohen
- License: mit
- Created: 2016-08-30T22:10:06.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2024-04-06T17:36:01.000Z (2 months ago)
- Last Synced: 2024-04-14T09:12:04.982Z (2 months ago)
- Topics: alexa, hotword-detection, keyword-spotting, node, speech, speech-recognition, speech-to-text, stt, voice-control, voice-recognition
- Language: JavaScript
- Homepage:
- Size: 1.34 MB
- Stars: 615
- Watchers: 33
- Forks: 78
- Open Issues: 36
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-raspberry-pi - Sonus - Node.js voice control for your Pi (and everything else) with customizable offline hotword detection. (Projects)
- awesome-raspberry-pi-zh - Sonus - 开源、跨平台的语音识别框架（Google Cloud Speech） (目录)
- awesome-raspberry-pi - Sonus - Node.js voice control for your Pi (and everything else) with customizable offline hotword detection. (Projects)
- awesome-stars - sonus
- awesome-stars - sonus - :speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection (JavaScript)
- awesome-keyword-spotting - Sonus
- awesome-raspberry-pi - Sonus - Node.js voice control for your Pi (and everything else) with customizable offline hotword detection. (Projects)
- awesome-raspberry-pi-zh - Sonus - 开源、跨平台的语音识别框架（Google Cloud Speech） (目录)
README
A dead simple STT library in Node
Sonus lets you quickly and easily add a VUI (Voice User Interface) to any hardware or software project. Just like Alexa, Google Assistant, and Siri, Sonus is always listening offline for a *customizable* hotword. Once that hotword is detected your speech is streamed to the cloud recognition service of your choice - then you get the results in realtime.
### Platform Support
- [X] Linux - most major distros (Including Raspbian)
- [X] macOS
- [ ] Windows
### Streaming Recognition Services
- [X] Google Cloud Speech
- [ ] Alexa Voice Services
- [ ] Wit.ai
- [ ] Microsoft Cognitive Services
- [ ] Houndify
## Installation
```
npm install --save sonus
```
## Dependencies
Generally, running `npm install` should suffice. This module however, requires you to install [SoX](http://sox.sourceforge.net).
### For most linux disto's
Recommended: use `arecord`, which comes with most linux distros.
Alternatively:
```
sudo apt-get install sox libsox-fmt-all
```
### For macOS
```
brew install sox
```
## Usage
Configure out cloud speech recognition system of choice, like [Google Cloud
Speech API](https://cloud.google.com/speech/docs/getting-started).
__Note:__ You need to use the `GOOGLE_APPLICATION_CREDENTIALS` environment variable for your JSON keyfile, or check the examples to see how you can pass in the keyflie path.
Add sonus and said recognizer:
``` javascript
const Sonus = require('sonus')
const speech = require('@google-cloud/speech')
const client = new speech.SpeechClient()
```
Add your keyword and initialize Sonus with a [Snowboy](https://snowboy.kitt.ai)
hotword:
``` javascript
const hotwords = [{ file: 'resources/snowboy.umdl', hotword: 'snowboy' }]
const sonus = Sonus.init({ hotwords }, client)
```
Create your own Alexa in less than a tweet:
``` javascript
Sonus.start(sonus)
sonus.on('hotword', (index, keyword) => console.log("!"))
sonus.on('final-result', console.log)
```
### [Full API Documentation](docs/API.md)
## Versioning
This project uses semantic versioning as of `v0.1.0`
## How do I set up Google Cloud Speech API?
Follow [these instructions](https://cloud.google.com/speech/docs/getting-started).
## How do I make my own hotword?
Sonus uses [Snowboy](https://snowboy.kitt.ai) for offline hotword recognition.
You can use [their website](https://snowboy.kitt.ai) or
[API](http://docs.kitt.ai/snowboy/#restful-api) to train a model for a new
hotword. Hotword training must occur online through their web service.
## Built [#withsonus](https://twitter.com/hashtag/withsonus?src=github)
- [L.I.S.A. - Home automation project](https://github.com/mylisabox/lisa-box)
- [ioBroker - Home automation project](https://github.com/ioBroker/ioBroker.sonus)
*If you've build a project with Sonus [send a PR](https://github.com/evancohen/sonus/edit/master/README.md) and include it here!*
## Authors
Evan Cohen: [@_evnc](https://twitter.com/_evnc)
Ashish Chandwani: [@ashishschandwa1](https://twitter.com/ashishschandwa1)
## License
Licensed under [MIT](https://github.com/evancohen/sonus/blob/master/LICENSE).