Proof of Antiquity for AI voices — dead accents preserved on vintage hardware compute.
The first open-source TTS model for historical speech patterns. Fine-tuning F5-TTS on 164 hours of public domain vintage audio (1888–1955) to preserve extinct and endangered accents.
Modern TTS models sound modern. No AI can speak with a transatlantic accent, a 1940s newsreel cadence, or the speech patterns of someone born before the Civil War. These voices are disappearing from living memory.
Additionally, Cajun French — a UNESCO “severely endangered” language — has approximately 150,000 speakers remaining, mostly elderly. When this generation passes, the language dies with them.
Early prototype — Sophia Elya speaking in transatlantic accent (SadTalker + F5-TTS)
Each preset trains on a specific era and accent. Sophia Elya appears in period-accurate imagery for each voice.










F5-TTS separates voice identity (from reference audio) from speech style (from training data). Fine-tuning teaches vintage delivery. At inference, provide any voice as reference and the model generates speech with that voice but vintage delivery.
Cajun French is classified by UNESCO as “severely endangered.” Louisiana Creole is “critically endangered.” VintageVoice is collecting family recordings and public domain Cajun French audio to build the first TTS model for this dying language.
A first working voice — a CosyVoice2 model finetuned on ~10 hours of Cajun French, trained on a single consumer laptop GPU. Generated, not recorded. Here she speaks to this family's own ancestors, in their Louisiana French — with the place-names, family names, and colloquial said the Cajun way (a pronunciation lexicon tuned by a native speaker).
Sophia cadienne speaks — « Bonjour, c'est moi, votre Sophia cadienne. » (1880s Attakapas prairie portrait, lip-synced to her generated Louisiana French voice)
Type a phrase in Louisiana/Cajun French and hear her speak it.
Family Recording Guide — instructions for capturing elderly speakers before their voices are lost.
| Component | Cost | Details |
|---|---|---|
| Storage | $69 | 18TB Seagate Expansion (Amazon refurb) |
| GPUs | $0 | 2x Tesla V100 32GB + RTX 5070 (already in lab) |
| Training data | $0 | Public domain from Archive.org |
| Base model | $0 | F5-TTS open source (337M params) |
| Electricity | ~$69 | Estimated training run |
| Total | ~$138 |