Spokestack can be integrated with Android apps developed in Java and Kotlin.
Integrations by Feature
Add speech recognition, language understanding, and text-to-speech to your Android app with one simple API.
Select a feature you’d like to use to see a minimal configuration using only that feature. Configurations shown here may also be combined; see the individual documentation pages on the left for more information.
val spokestack = Spokestack.Builder() .setProperty("wake-filter-path", "path/to/filter.tflite") .setProperty("wake-encode-path", "path/to/encode.tflite") .setProperty("wake-detect-path", "path/to/detect.tflite") .withoutNlu() .withoutTts() // listener inherits from SpokestackAdapter .addListener(listener) .build() spokestack.start()
Try a Wake Word in Your Browser
Test a wake word model by pressing “Start test,” then saying “Spokestack”. Wait a few seconds for results. This browser tester is experimental.
Say “Spokestack” when testing
- Test a model by pressing "start test" above
- Then, try saying any of the utterances listed above. Wait a few seconds after saying an utterance for a confirmation to appear.
Spokestack Android SDKs
Spokestack manages voice interactions and delivers actionable user commands with just a few lines of code. To integrate, first decide whether you want to manage the UI yourself or use a drop-in UI widget to display the conversation history.
Extensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
spokestack-android, check out our Getting Started Guide.
spokestack-tray-android, check out our Android Tray Tutorial.
Want to dive deeper into the world of Android voice integration? We've got a lot to say on the subject: