These examples assume you are comfortable using a linux terminal command line interface. If not, instructions exist for alternative environments or Javascript.
The easiest way to get started is to post a wav file to the STT API and get back the resultant text string like this ...
curl -X POST -F "file=@sample.wav" -F "quality=normal" -F "key=XXXXXXXXXXXXXXXX" api.privox.io/stt
This will post the file named "sample.wav" to the API and get back a text representation of the supplied wav file. If you don't have a wav file you can download this sample. Wav files should be recorded as 16khz, mono using the 16 bit little endien format (S16_LE). This is easily accomplished using the built-in linux utility 'arecord' like this ...
arecord -c 1 -r 16000 -f S16_LE sample.wav
Press Ctl+C when you are finished recording.
To try out text to speech (TTS) use the following command ...
curl -X POST http://api.privox.io/tts -H "Content-Type: application/x-www-form-urlencoded" -d "key=XXX&voice=voice1&text=testing one two three" > junk.wav;aplay junk.wav
If you don't have the curl command you can use any command which can post binary data (like PostMan), or you can run the sample python scripts provided in the repository.
The STT and TTS APIs are standard HTTP(s) RESTful endpoints. See STT and TTS APIs for additional options.