Audio firewall
An audio firewall system has a microphone that generates audio data. A speech-to-text engine converts the audio data to text data. The text data is parsed for a service wake word and corresponding content data. The service wake word identifies one of a local security system and a remote assistant server. A text-to-speech engine converts the service wake word and the corresponding content data to converted audio data. The converted audio data is provided to the remote assistant server. The content data is provided to the local security system. The audio firewall system receives a response from the remote assistant server or the local security system and outputs an audio signal corresponding to the response.
1. A method comprising:
accessing, at an audio firewall system, first audio data including at least a request and a wake word generated with a microphone of the audio firewall system;
determining whether the first audio data is directed at a local security system or a server by determining whether the first audio data identifies a local device that is locally connected to the local security system; and
in response to determining that the first audio data is directed at the server, and not at the local security system, converting a text of the first audio data including the request and the wake word to second audio data, and providing the second audio data to the server.
2. The method of claim 1 , wherein the request includes a command directed at the local device.
3. The method of claim 2 , further comprising:
determining whether the first audio data is directed at the server based on the wake word.
4. The method of claim 3 , wherein the wake word is associated with the server.
5. The method of claim 1 , further comprising:
converting the first audio data to text data;
parsing the text data for the wake word and the request; and
in response to determining that the first audio data is directed at the local security system, providing the request in the text data to the local security system.
6. The method of claim 1 , further comprising:
receiving a response from the server in response to providing the second audio data to the server; and
outputting an audio signal corresponding to the response with a speaker of the audio firewall system.
7. The method of claim 1 , further comprising:
in response to determining that the first audio data is directed at the local security system and not the server, providing the first audio data to the local security system;
receiving a response from the local security system in response to providing the first audio data to the local security system; and
outputting an audio signal corresponding to the response with a speaker at the audio firewall system.
8. The method of claim 1 , further comprising:
adjusting at least one of a pitch or a speed of the first audio data to generate the second audio data.
9. The method of claim 1 , wherein the audio firewall system is configured to communicate with a plurality of remote servers, each remote server having a corresponding wake word.
10. An audio firewall system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, configure the audio firewall system to perform operations comprising:
accessing, at an audio firewall system, first audio data including at least a request and a wake word generated with a microphone of the audio firewall system;
determining whether the first audio data is directed at a local security system or a server by determining whether the first audio data identifies a local device that is locally connected to the local security system; and
in response to determining that the first audio data is directed at the server and not at the local security system, converting a text of the first audio data including the request and the wake word to second audio data, and providing the second audio data to the server.
11. The audio firewall system of claim 10 , wherein the request includes a command directed at the local device.
12. The audio firewall system of claim 11 , wherein the operations further comprise:
determining whether the first audio data is directed at the server based on the wake word.
13. The audio firewall system of claim 12 , wherein the wake word is associated with the server.
14. The audio firewall system of claim 10 , wherein the operations further comprise:
converting the first audio data to text data;
parsing the text data for the wake word and the request; and
in response to determining that the first audio data is directed at the local security system, providing the request in the text data to the local security system.
15. The audio firewall system of claim 10 , wherein the operations further comprise:
receiving a response from the server in response to providing the second audio data to the server; and
outputting an audio signal corresponding to the response with a speaker of the audio firewall system.
16. The audio firewall system of claim 10 , wherein the operations further comprise:
in response to determining that the first audio data is directed at the local security system and not the server, providing the first audio data to the local security system;
receiving a response from the local security system in response to providing the first audio data to the local security system; and
outputting an audio signal corresponding to the response with a speaker at the audio firewall system.
17. The audio firewall system of claim 10 , wherein the operations further comprise:
adjusting at least one of a pitch or a speed of the first audio data to generate the second audio data.
18. A non-transitory machine-storage medium storing instructions that, when executed by one or more processors of a machine, cause the one or more processors to perform operations comprising:
accessing, at an audio firewall system, first audio data including at least a request and a wake word generated with a microphone of the audio firewall system;
determining whether the first audio data is directed at a local security system or a server by determining whether the first audio data identifies a local device that is locally connected to the local security system; and
in response to determining that the first audio data is directed at the server and not at the local security system, converting a text of the first audio data including the request and the wake word to second audio data, and providing the second audio data to the server.