Products & Services

Spokestack ASR and VAD

A one-stop shop for Automatic Speech Recognition (ASR) and Voice Activity Detection (VAD)

Easily add ASR and VAD to your app with one of our open source libraries. Spokestack ASR and VAD allow you to turn user utterances into text, which is the first step to responding to a user. From there, use Spokestack Wakeword, TTS and NLU to complete the voice experience.

Get started

Spokestack Wakeword

Choose the keyword that will be the wakeword for your app.

Use your brand name or any keyword of your choice to put your app into listen mode, also with the help of one of the Spokestack libraries. Like “Siri”, “OK Google”, or “Alexa”, your app will respond to your wakeword while it is open.

Email us for details on getting a custom wakeword

Spokestack TTS

Create a custom voice for your brand.

Get a custom voice or use the default voice for free. Respond to your users with our proprietary Text-to-Speech (TTS) service.

Our TTS engine can create a custom voice for your brand with as little as five minutes of recordings. We can also work with your own voice talent in a professional recording studio to produce a high quality branded voice for your app.

Email us for details on getting a custom branded voice

Try some of our voice samples below. Each voice is generated using different recording times and methods.

Sample a Custom Voice

Enter your text below. We support IPA input enclosed in {{ double braces }}, or a subset of Speech Markdown including breaks, characters, IPA, and numbers.

Spokestack NLU

Keep your data and customer conversations in your app where it belongs with our Natural Language Understanding (NLU) engine.

Use the Spokestack NLU engine to communicate the unique requests, context and pronunciations of words that matter to you and users. Combined with Spokestack TTS, Spokestack NLU helps create a voice-enabled user experience optimized for your brand.

Email us for details on getting a custom NLU for your app