Day 8: Making Cool Raspberry Pi Projects even Cooler with Voice AI (3/4)

Today is the day for on-device audio transcription for Raspberry Pi

SDKs
.NET
C
Go language
Java
Node.js
Python
Rust

Let's use C!
Compatibility
C99-compatible compiler
Requirements
CMake version 3.13 or higher
Picovoice AccessKey
Build
Run this from the root of the repository:

cmake -S demo/c/ -B demo/c/build
cmake --build demo/c/build

Prints the usage:

usage: -a ACCESS_KEY -l LIBRARY_PATH -m MODEL_PATH [-d] [-v] audio_path0 audio_path1 

Replace ${ACCESS_KEY} with yours and ${AUDIO_PATH} with the path to an audio file you want to transcribe.

• Use the -d flag to disable automatic punctuation
• Use the -v flag to enable the printing of word metadata

This tutorial is intended for Raspberry Pi 4. If you're looking for Raspberry Pi 3 or Raspberry Pi 400 or Raspberry Pi 4 (64-bit) check out Leopard C Demos on GitHub

./demo/c/build/leopard_demo \
-a ${ACCESS_KEY} \
-m lib/common/leopard_params.pv \
-l lib/raspberry-pi/cortex-a72/libpv_leopard.so \
${AUDIO_PATH}