Grandmother's fairy tales on audio figures

Request: „Turn grandmother's recordings into Tonies for the kids.“

1. Catalogue and transcribe all recordings.
2. Tell the speakers apart automatically — via the fundamental frequency of the voice (pitch).
3. Bundle the tales into seven packs and prepare them for the audio figures (Tonies).
4. Load the first pack and hand it to the kids.

99 recordings on old media, without titles, without order, with changing speakers.

Which stories first — and the listening.

Unstructured legacy holdings become usable once a tool catalogues them and one feature — here the pitch — sorts them automatically.

Grandmother read fairy tales aloud; 99 recordings sat on old media — without titles, without order, with changing speakers. The AI catalogued and transcribed everything and told the speakers apart by the pitch of their voices. The result: seven packs for the kids' audio figures. The first Tonie has been playing in the kids' room since June. Technology was the means here; the purpose is a voice that stays.