Show HN: Hurston-1 open source TTS that speak Southern American and Afro-English

Hurston-1 is an open-source text-to-speech model developed by Destined AI that specializes in Southern American and African English accents, which most existing TTS systems poorly represent. The model includes a narrowband mode optimized for phone lines (8 kHz audio compatible with telephony systems like Twilio) and uses plain-language voice descriptions to generate diverse accents. Built by an independent Atlanta-based team using recorded contributors from the American South and Africa, it represents underrepresented voices in AI systems.