A maintenance technician who talks to pumps and pipes might not seem like the ideal person to entrust with keeping a factory running smoothly, but the mobile Speech-Enabled Augmented Reality framework could make such behavior in the future anything but suspicious. The SEAR framework uses flexible, scalable vision-based localization techniques to offer the technician a seamless multimodal user interface. The interface juxtaposes a graphical augmented-reality view with a context-sensitive speech dialogue concerning industrial equipment in the technician?s immediate vicinity.