Launching today
Wfloat
Distributing lifelike on-device Speech AI to your app
2 followers
Distributing lifelike on-device Speech AI to your app
2 followers
Wfloat ("dubfloat") makes speech AI that runs on-device instead of in a data center. We train speech models built for AI-powered games, assistants, agents, tutors, and other apps that need text-to-speech at scale. Rather than charging for every second of generated audio, Wfloat distributes lightweight speech models directly to your users’ devices. That means speech is fast, private, and completely free at inference time.
Hey everyone, I'm Mitchell, founder of Wfloat.
Speech needs to be a normal part of AI products, not a premium feature that only works when the economics make sense for certain apps.
Now that the basic system for Wfloat is working end to end, most of my effort is going into making the models better. Better voices, lower latency, smaller downloads, and more control over emotion, speed, style, etc.
Currently it works in web browsers and React Native for iOS and Android, and I want to add more platforms/features based on feedback.
I'd love to hear your thoughts! What do you like and what still needs work?