commandlinefu.com is the place to record those command-line gems that you return to again and again.
You can sign-in using OpenID credentials, or register a traditional username and password.
Subscribe to the feed for:
The FLAC audio must be encoded at 16000Hz sampling rate (SoX is your friend).
Outputs a short JSON string, the actual speech is in the hypotheses->utterance, the accuracy is stored in hypotheses->confidence (ranging from 0 to 1).
Google also accepts audio in some special speex format (audio/x-speex-with-header-byte), which is much smaller in comparison with losless FLAC, but I haven't been able to encode such a sample.
There is 1 alternative - vote for the best!
If you can do better, submit your command here.
You must be signed in to comment.