Abstract: An electronic device may operate in different modes of operations. In a first mode of operation, the electronic device may receive user speech via a microphone, generate audio data that represents the user speech, and then send the audio data to one or more remote computing device for analysis. In a second mode of operation, the electronic device may receive user speech via the microphone, generate audio data that represents the user speech, and then analyze the audio data using speech processing. In some instances, the electronic device may operate in the first mode of operation and/or the second mode of operation based on whether the electronic device is receiving power from an external source.

Abstract: An electronic device may operate in different modes of operations. In a first mode of operation, the electronic device may receive user speech via a microphone, generate an audio signal that represents the user speech, and then send the audio signal to one or more remote computing device for analysis. In a second mode of operation, the electronic device may receive audio data from a peripheral device and then output audible content represented by the audio data. In some instances, the electronic device may operate in the first mode of operation and/or the second mode of operation based on whether the electronic device can communicate with the one or more computing devices over a wide-area network.

Abstract: A portable music device may operate in response to user speech. In situations in which the music device is operating primarily from battery power, a push-to-talk (PTT) button may be used to indicate when the user is directing speech to the device. When the music device is receiving external power, the music device may continuously monitor a microphone signal to detect a user utterance of a wakeword, which may be used to indicate that subsequent speech is directed to the device. When operating from battery power, the device may send audio to a network-based support service for speech recognition and natural language understanding. When operating from external power, the speech recognition and/or natural language understanding may be performed by the music device itself.