Context sensitive avatar captions

1. A method comprising:

presenting, by a messaging application, a first avatar and a caption entry region proximate to the first avatar, the avatar being associated with a first user;

populating, by the messaging application, the caption entry region with a text string comprising one or more words received as input by a first user device of the first user;

adding a second avatar associated with a second user for display together with the first avatar; and

modifying display of the caption entry region to curve around the first and second avatars as the one or more words in the text string are received as input by the first user device.

2. The method of claim 1 , further comprising:

receiving input that selects an option to generate a message using an avatar with a caption; and

determining, by the messaging application, context based on the one or more words in the text string by detecting a symbol in the text string that indicates a reference to the second user of the messaging application.

3. The method of claim 2 , further comprising:

modifying, by the messaging application, an expression of the first avatar based on the determined context.

4. The method of claim 2 , further comprising:

receiving input comprising a first word of the one or more words;

determining that the first word corresponds to a first context; and

causing the first avatar to be presented with a first expression that corresponds to the first context.

5. The method of claim 4 , further comprising:

after receiving input comprising the first word, receiving input comprising a second word of the one or more words;

determining that the second word corresponds to a second context that is different from the first context; and

changing the expression of the first avatar from the first expression to a second expression that corresponds to the second context.

6. The method of claim 1 , further comprising:

storing a database that associates different contexts with respective expressions; and

retrieving from the database an expression associated with a determined context.

7. The method of claim 1 , further comprising:

receiving a request to access a caption tool; and

in response to the request, presenting a menu comprising a plurality of textual entry types, wherein one of the plurality of textual entry types comprises the avatar with a caption textual entry type.

8. The method of claim 1 , further comprising transmitting a message to a computing device of the second user, the message comprising the first and the second avatars and an image or video captured by the first user device.

9. The method of claim 1 , further comprising:

determining that the first user is currently engaged in a conversation with a third user when the input is received;

in response determining that the first user is currently engaged in a conversation with the third user, retrieving a third avatar associated with the third user;

presenting the first avatar associated with the first user and the third avatar associated with the third user; and

presenting the caption entry region proximate to the first and third avatars.

10. The method of claim 1 , further comprising:

presenting a conversation interface comprising a plurality of messages exchanged between the first and second users;

receiving input that selects a camera option from within the conversation interface;

enabling the first user to capture an image using a camera in response to receiving the input that selects the camera option; and

receiving input that selects an option to generate the message after the image is captured.

11. The method of claim 1 , further comprising:

determining context of a conversation by processing one or more words in the conversation; and

modifying expressions of the first and second avatars based on the one or more words in the conversation.

12. The method of claim 1 , further comprising:

determining a first context that is associated with the first user based with a word of the one or more words in the text string;

determining a second context that is associated with the second user based with a different word of the one or more words in the text string; and

presenting the first avatar with a first expression corresponding to the first context together with the second avatar with a second expression corresponding to the second context.

13. The method of claim 12 , further comprising:

identifying a plurality of contexts based on the one or more words in the text string;

ranking the plurality of contexts based on relevance; and

selecting, as the determined first context, the context in the plurality of contexts associated with a highest rank.

14. The method of claim 1 , further comprising:

launching an image capture component of the messaging application in response to receiving a user selection of a reply with camera option in a conversation, wherein the avatar and the caption entry region are presented in response to launching the image capture component.

15. The method of claim 1 , further comprising sending the first and second avatars to one or more designated recipient computing devices.

16. A system comprising:

a processor configured to perform operations comprising:

presenting, by a messaging application, a first avatar and a caption entry region proximate to the first avatar, the avatar being associated with a first user;

populating, by the messaging application, the caption entry region with a text string comprising one or more words received as input by a first user device of the first user;

adding a second avatar associated with a second user for display together with the first avatar; and

modifying display of the caption entry region to curve around the first and second avatars as the one or more words in the text string are received as input by the first user device.

17. The system of claim 16 , wherein the operations further comprise:

receiving input that selects an option to generate a message using an avatar with a caption; and

determining, by the messaging application, context based on the one or more words in the text string by detecting a symbol in the text string that indicates a reference to the second user of the messaging application.

18. The system of claim 17 , wherein the operations further comprise:

modifying, by the messaging application, an expression of the first avatar based on the determined context.

19. A non-transitory machine-readable storage medium that includes instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

presenting, by a messaging application, a first avatar and a caption entry region proximate to the first avatar, the avatar being associated with a first user;

populating, by the messaging application, the caption entry region with a text string comprising one or more words received as input by a first user device of the first user;

adding a second avatar associated with a second user for display together with the first avatar; and

modifying display of the caption entry region to curve around the first and second avatars as the one or more words in the text string are received as input by the first user device.

20. The non-transitory machine-readable storage medium of claim 19 , wherein the operations further comprise:

receiving input that selects an option to generate a message using an avatar with a caption; and

determining, by the messaging application, context based on the one or more words in the text string by detecting a symbol in the text string that indicates a reference to the second user of the messaging application.