Tags

Blog

Noel Weichbrodt

Noel Weichbrodt, President

Spokestack Maker introduces sophisticated AutoML tools for voice interfaces to a new audience of prototypers, enthusiasts, and makers.

Introducing Spokestack Maker - AutoML Personal Voice for Creators

Spokestack exists to help put voice into software because voice is a humane way to interface with software and because software needs better, more accessible…

Josh Ziegler

Josh Ziegler, Principal Computational Linguist

"Voice app" is a convenient shorthand for "Alexa Skill" or "Google Action", but does it do more harm than good?

Why Haven't We Seen a Killer Voice App?

In the interest of fostering discussion about the state of voice tech, we're thinking of starting a new regular feature. It's tentatively titled "Ask the Cranky…

Josh Ziegler

Josh Ziegler, Principal Computational Linguist

Google provides a command line utility for converting TensorFlow models into TensorFlow.js format for running in a browser, but what if you want to do that conversion in code?

Converting a TensorFlow Model to TensorFlow.js in Python

At Spokestack, we use several different types of TensorFlow model, and we have various deployment targets for them: big models for the cloud, small TensorFlow…

Will Rice

Will Rice, ML Engineer

This tutorial leverages HuggingFace's Transformer library to make a voice question answering bot with Spokestack.

Question Answering With Spokestack and Transformers

The ability to find information is a fundamental feature of the internet. Often, the information sought is the answer to a question. When it comes to answering…

Josh Ziegler

Josh Ziegler, Principal Computational Linguist

Instructions on integrating and using the Spokestack Tray UI component in Android.

Integrating Spokestack in Android

Using voice as an interface can be a daunting proposition. First, you have to be able to actually process voice as input. Then, you have to decide what to do…

Previous
12345678
Next

Become a Spokestack Maker and #OwnYourVoice

Access our hosted services for model import, natural language processing, text-to-speech, and wakeword.