A developer created a spelling game using AI voice cloning and text-to-speech technology. They used VoxCPM2 and Chatterbox models via audio.cpp to generate word recordings in English, French, and Norwegian, but faced challenges with audio quality—words had incomplete beginnings or endings. They improved results by providing reference recordings and embedding isolated words within sentences to give the model context, then needed to precisely cut the audio at the right point to extract clean word recordings.
SamplePitcher is a browser-based audio pitch-shifting tool that processes samples locally using Web Audio DSP, allowing users to transpose audio files by semitone while preserving tempo. It supports multiple formats (WAV, MP3, AIFF, FLAC, OGG), enables batch processing with ZIP export, and keeps all files private in browser memory without server uploads.