- A 32-BIT FISHINO! WiFi, SD card, RTC, audio codec, LiPo and more…Posted 2 days ago
- A full featured mp3 DemoboardPosted 1 week ago
- A 32-BIT FISHINO board for your powerful IoT!Posted 4 weeks ago
- FairWind: when marine electronics, open source and the University meetPosted 4 weeks ago
- The Discovery of the Future: Stretchable integrated circuitPosted 4 weeks ago
- Robots are going to replace developers quicklyPosted 1 month ago
- 3D Prints with Computational HydrographicsPosted 1 month ago
- Open Source into Microsoft’s reality finallyPosted 1 month ago
- Guide to Mobile Apps for 3D DesigningPosted 1 month ago
- A FPGA controlled RGB LED MATRIX for Incredible Effects – the SoftwarePosted 1 month ago
Make your own Siri or Cortana with Raspberry Pi 3
Are you wondering about how can you create your own version of Siri using a Raspberry Pi?
Our friend posted on AliceIa.it a great solution to understand the basics about Speech to Text and Text to Speech.
First, we need a system that translates our voice into text. In order to that we use the python library Speech Recognition. This library is very easy to use and it’s compatible with Google’s Speech Recognition, a tool that may be familiat to some of you.
Now that we have our STT we need a TTS to give our Raspberry a voice. I use gTTS, a python library that convert a string to an audio file. This library, as the previous one, is based on Google’s API. This library can be used to create an MP3 file given a string as input, that can later be broadcasted using a speaker connected to your Pi.
Now, you are able to start your own project that uses your voice as input and a TTS system for the outputs.
Follow this link to see the scripts and source code: Raspberry Pi 3: TTS and STT – Alice – A Boy and his IA