Show HN: Hurston-1 open source TTS that speak Southern American and Afro-English
Destined AI has released Hurston-1, an open-source text-to-speech model specifically trained to handle Southern American and various African English accents. The model is optimized for telephony, aiming to improve AI voice agent interactions in customer service settings.
Why it matters
This addresses a significant gap in AI accessibility and representation by improving the performance of synthetic speech for diverse, non-standard English accents.
Like 6 Follow destined 2 Text-to-Speech Safetensors English llama accents african-english southern-american-english synthetic-speech telephony narrowband nb-tts License: apache-2.0 Model card Files Files and versions xet Community 1 Copy to bucket new You need to agree to share your Hugging Face information to access this model This repository is publicly accessible, but you have to accept the conditions to access its files and content .
Hurston-1 The South got something to say Hear the South Voice descriptions Built for the phone (NB-TTS) What people build with it Evaluation Training data Limitations What's next Responsible use Credits and licenses Citation Hurston-1 Accented English text-to-speech built for the phone, steered by a plain-language voice description.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in