Hurston-1 - Open-source TTS for Southern American and Afro-English accents
Show HN: Hurston-1 open source TTS that speak Southern American and Afro-English
Hurston-1 is an open-source text-to-speech model that finally gives voice to accents most TTS systems flatten into generic American English: Southern American, Nigerian, West African, East African, and Southern African. Built by Destined AI in Atlanta, it's a fine-tune of Maya1 trained on consented, paid contributors and real phone calls with AI agents. With a phone mode that outputs 8 kHz G.711 audio ready for Twilio, it's built for where voice AI actually lives—the phone line. Just describe the voice you want (gender, age, accent, style, pace) and generate speech. Perfect for accent testing, simulated callers, and inclusive voice prompts.
The South got something to say. These voices belong in AI, and now they have an open model.
- someperson
Sounds like your project is for southern American English presumably including African-American Vernacular English (AAVE), and for regional accents in the African continent specifically for the English language.
But tangentially related, for non-English languages of the African continent, the Gates Foundation are pledging some grants to improve AI access outside of English-speaking regions: https://news.bpdata.com/article/gates-foundation-pledges-1-b...
Despite being focused on English, your project could be of interest for their funding. It's probably worth reaching out to let them know about your work.
- fractorial
Seeing Atlanna inspire an open weight model was not on my 2026 bingo card.
- trollbridge
Regional African English accents, so Nigerian, Kenyan, South African?