Building Voice-First Android Apps

on YouTube ↗47m

" summary

Covers concrete options: Android provides SpeechRecognizer and TextToSpeech; use ML Kit/TensorFlow Lite or Dialogflow for cloud NLU; Porcupine does hot word detection only; Snips and PocketSphinx provide offline NLU (works but misrecognizes outside a fixed lexicon); Amazon Lex requires cloud setup and maps to Alexa deployments; one Snowboy-powered app has over 1 million users; App Actions map intents via actions.xml + deep links to open app pages (developer preview, limited categories) — demos mostly work but need tuning.

AI-written summary · about

" chapters (7)

1. 0:00Start
2. 5:18What do I need to do?
3. 6:46Two strategies
4. 8:47Voice Interactions on Android
5. 31:51Development
6. 37:39App Actions - Developer Preview
7. 40:35Bug Reporting

" related talks

• 47mBuilding Voice-First Android AppsElaine Dias Batista · RS Conf 2019
• 42mThe State of Voice Interactions on AndroidElaine Dias Batista · DevFest Paris 2025
• 35mHaving a Voice on Android: How hard can it be?Paul-Louis Nech · droidcon London 2019
• 43mThe State of Voice Interactions on AndroidElaine Dias Batista · AndroidMakers by droidcon 2025
• 29mAndroid Gets a Voice: Building Real-Time AgentsMark Wickham · DroidKaigi 2026
• 36mVoice Enabling Mobile Apps and Custom Hardware DevicesOgnjen Todic · droidcon San Francisco 2022
• 50mSpeak To Me: Voice App Conversation PracticesHeather Downing · NDC London 2018
• 55mConversational power for Android appsAlfredo Morresi · DevFest Nantes 2016