[ghjhome]

I've been playing with the raw ElevenLabs and OpenAI TTS APIs for a while now, and the latency and quality profile here feel familiar. Can you be transparent about what your actual tech stack is? What's the "secret sauce" or the proprietary tech here beyond a nice UI wrapper, and why should I use this instead of just hitting the APIs directly with my own scripts?

[jrlee]

Great question, and this gets to the heart of what makes us different. While we utilize some external APIs for supplementary functions, our core TTS engine is our own proprietary technology that we run on our own servers. Our team (Humelo) has been focused solely on audio AI and TTS in Korea for the last 8 years. We've built a strong technology base there, but the market for audio content is small. We launched Sohri to bring our tech to creators in the larger US market and would love your support.