Abstract: Indexing application actions for voice-based execution is provided. An indexer of a device receives, from an application executed by the device, an indication of an action and a deep link corresponding to the action declared by the application via an application programming interface. The indexer accesses an index stored in the memory of the device that is accessible to a plurality of applications. The indexer inputs, into a location in the index, the action and the deep link with a cryptographic token that prevents access to the deep link by unauthorized applications. A digital assistant of the device receives a voice query detected by a microphone and parses the voice query to determine the action. The digital assistant identifies in the index the deep link corresponding to the action. The digital assistant invokes, with the cryptographic token, the deep link to cause the application to perform the action.

Abstract: A language translation application on a user device includes a user interface that provides relevant textual and graphical feedback mechanisms associated with various states of voice input and translated speech.

Abstract: A language translation application on a user device includes a user interface that provides relevant textual and graphical feedback mechanisms associated with various states of voice input and translated speech.

Abstract: A language translation application on a user device includes a user interface that provides relevant textual and graphical feedback mechanisms associated with various states of voice input and translated speech.

Abstract: A language translation application on a user device includes a user interface that provides relevant textual and graphical feedback mechanisms associated with various states of voice input and translated speech.

Abstract: A language translation application on a user device includes a user interface that provides relevant textual and graphical feedback mechanisms associated with various states of voice input and translated speech.

Abstract: A data processing apparatus receives data indicating a movement of a client device by a first user. The apparatus determines that the movement of the client device is a delimiter motion for switching between a first mode, in which the client device is configured to (i) provide a first interface for a first user speaking in a first language and (ii) perform speech recognition of the first language, and a second mode, in which the client device is configured to (i) provide a second interface for a second user speaking in a second language and (ii) perform speech recognition of the second language, the second interface being different from the first interface. Based on determining that the movement is a delimiter motion, the apparatus switches between the first mode and the second mode without the second user physically interacting with the client device.