https://github.com/tmc/speechtotext
streaming stdin to speech recognition tool via Google Cloud Speech API
https://github.com/tmc/speechtotext
Last synced: 11 months ago
JSON representation
streaming stdin to speech recognition tool via Google Cloud Speech API
- Host: GitHub
- URL: https://github.com/tmc/speechtotext
- Owner: tmc
- License: mit
- Created: 2016-07-25T20:17:04.000Z (almost 10 years ago)
- Default Branch: master
- Last Pushed: 2020-03-28T23:40:10.000Z (over 6 years ago)
- Last Synced: 2024-12-01T10:23:41.829Z (over 1 year ago)
- Language: Go
- Homepage:
- Size: 74.2 KB
- Stars: 88
- Watchers: 4
- Forks: 7
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
speechtotext
============
This project is a basic example of streaming stdin to [Google Cloud Speech API](https://cloud.google.com/speech/) via [gRPC](http://www.grpc.io/).
basic usage:
```sh
$ uname
Darwin
$ cat sample.wav | speechtotext -key (path to serviceaccount json key)
Alpha Beta gamma
$
$ ffmpeg -nostats -loglevel 0 -f avfoundation -i ":Built-in Microphone" -ar 16000 -acodec pcm_s16le -ac 1 -f wav - |tee out.wav | speechtotext -key (path to serviceaccount json key)
```