Destined AI open-sources accented speech model Hurston-1
What happened
On October 25, Hacker News' front page reported that Destined AI released Hurston-1, an open-source speech synthesis model. It is fine-tuned from Maya1, supports English accents from the southern US and several African regions, and lets users control the voice through natural language descriptions. Audio output is 24 kHz by default; a phone mode outputs 8 kHz G.711 audio for connecting to phone systems such as Twilio. The released model weights use the Apache-2.0 license.
Written by AI from the coverage · updated 2 hours ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageShow HN: Hurston-1 open source TTS that speak Southern American and Afro-English
Destined AI 发布开源语音合成模型 Hurston-1，基于 Maya1 微调，支持美国南部及多个非洲地区的英语口音。模型通过自然语言描述控制声音，默认输出 24 kHz 音频，电话模式输出 8 kHz G.711 音频以接入 Twilio 等电话系统，模型权重采用 Apache-2.0 许可。
Heat over time
Not enough continuous observations to draw a trend yet.