The 200-year prehistory of speech synthesis: von Kempelen's 1791 speaking machine to 1970
ArtificialOther · x · 2026-11-18
A shared history of speech synthesis (1770–1970): the first machine-speech attempts came in the late 18th century — Kratzenstein synthesized vowels with resonance tubes on organ pipes in 1773, while Wolfgang von Kempelen (1734–1804, also creator of the chess-playing "Turk") built the first machine able to produce whole words and short sentences. His 1791 book detailed the mechanism for others to reproduce; it could be learned in about three weeks, working best with Latin, French, or Italian. A rare resource on the lineage leading to modern TTS.
More from Research
- EACL 2027 results: 1,118 papers accepted from 4,136 submissions, main track rate just 13.5% — IAugenstein · 2026-11-18
- Stanford Marin releases all 57 intermediate checkpoints of its 535B-A23B pretraining run — MaziyarPanahi · 2026-11-18
- CADMAGEDDON: open-source agent rebuilds editable CAD locally on a single GPU — Oleg Pavlov · 2026-11-18
- MillBill: local 27B model beats frontier models at generating machining programs — Gennadii Savrasov · 2026-11-18
- Ex-DeepMind's Ryutaro Tanno joins AI biotech Pathos as Chief AI Officer — davidstutz92 · 2026-11-18
- VRST 2027 Goes Fully Distributed With Three Equal Sites Across US, Europe and Asia — plopesresearch · 2026-11-18