What’s Needed in Tech to bring Voice to the Future
summary
Argues for concrete tooling: a voice-specific CMS that edits audio nuances and SSML, plugability so developers can plug any TTS voice into third-party skills, and smoother long-form audio players with resume and seamless handoff. Names existing projects (multi-vocal, speech markdown, jovo) as partial solutions, shows a released game called Snatch Word that exposes marketplace discovery failures, and calls for reusable components plus reliable cross-device context handoff and finer-grained intent control.
AI-written summary · about
chapters (4)
- 0:00Start
- 1:09Alan Furstenberg
- 14:30Reusable Open Source Components
- 18:20What Are the Tools That We Need
related talks
50mSpeak To Me: Voice App Conversation Practices
20mVoice games – An overview of an up-and-coming category
49mDesigning voice interfaces
29mFinding Your Voice: Building Screenless Interfaces with Node.js
12mVOICE Summit 2019 | VED Talks | John Gillilan | July 23
44mDelivering On The Promise Of Voice With Alexa
17mBuilding Effective Voice Agents
17mReimagining Customer Experiences Integrating Voice into Digital Strategy