Electronic device for providing graphic data based on voice and operating method thereof

1. An electronic device comprising: a display; a camera; an input device;

and a processor, wherein the processor is configured to: obtain a real-time video broadcast or a video call comprising a plurality of images from the camera, obtain a voice signal related to the real-time video broadcast or the video call comprising the plurality of images from the input device and convert the voice signal to text, and extract at least one keyword from the text of the voice signal, determine at least one recommended graphic data corresponding to the at least one keyword, display a user interface including the text and the at least one recommended graphic data on the display, determine a graphic data to be applied among the at least one recommended graphic data, based on: a user input on the at least one recommended graphic data on the display when an automatic combination function has not been previously activated, and a priority of the at least one keyword without any user input when the automatic combination function has been previously activated, select at least one image of the plurality of images, based on a point in time at which a voice corresponding to a keyword that corresponds to the determined graphic data is output, and apply the determined graphic data to the at least one selected image within the real-time video broadcast or the video call.

2. The electronic device of claim 1 , wherein the processor is further configured to add, to the real-time video broadcast or the video call comprising the plurality of images, an indicator indicating the point in time at which the at least one selected image to which the graphic data is applied.

3. The electronic device of claim 2 , wherein the indicator is displayed on a timeline of the real-time video broadcast or the video call.

4. The electronic device of claim 3 , wherein the processor is further configured to add the indicator to the timeline, at the point in time at which the graphic data is applied to the at least one selected image, or at the point in time at which the real-time video broadcast or the video call comprising the plurality of images is stored.

5. The electronic device of claim 3 , wherein the processor is further configured to: when a drag input to the indicator displayed on the timeline is detected, change the point in time at which the at least one selected image to which the graphic data is applied indicated by the indicator on the timeline to a second point on the timeline, based on the drag input, delete graphic data associated with the indicator from at least one image corresponding to the point in time at which the at least one selected image to which the graphic data is applied, and

apply the graphic data associated with the indicator to at least one other image corresponding to the second point.

6. The electronic device of claim 1 , wherein the user input comprises at least one of a touch input, a gesture input, or a voice input.

7. The electronic device of claim 1 , wherein the processor is further configured to:

determine whether the at least one keyword corresponds to a designated class,

if the at least one keyword corresponds to the designated class, determine a sound effect corresponding to the at least one keyword, and

apply the sound effect at the the point in time at which a voice signal corresponding to the at least one keyword is output.

8. An operation method of an electronic device, the method comprising:

obtaining a real-time video broadcast or a video call comprising a plurality of images from a camera; obtaining a voice signal related to the real-time video broadcast or the video call comprising the plurality of images from an input device and converting the voice signal to text; extracting at least one keyword from the text of the voice signal; determining at least one recommended graphic data corresponding to the at least one keyword; displaying a user interface including the text and the at least one recommended graphic data on a display of the electronic device; determining a graphic data to be applied among the at least one recommended graphic data, based on: a user input on the at least one recommended graphic data on the display when an automatic combination function has not been previously activated, and a priority of the at least one keyword without any user input when the automatic combination function has been previously activated; selecting at least one image among the plurality of images, based on a point in time at which a voice corresponding to a keyword that corresponds to the determined graphic data is output; and applying the determined graphic data to the at least one selected image within the real-time video broadcast or the video call.

9. The method of claim 8 , further comprising: adding, to the real-time video broadcast or the video call comprising the plurality of images, an indicator indicating the point in time at which the at least one selected image to which the graphic data is applied, wherein the indicator is displayed on a timeline of the real-time video broadcast or the video call comprising the plurality of images.

10. The method of claim 8 , wherein the user input comprises at least one of a touch input, a gesture input, or a voice input.

11. The method of claim 8 , further comprising: determining whether the at least one keyword corresponds to a designated class; when the at least one keyword corresponds to the designated class, determining a sound effect corresponding to the at least one keyword; and applying the sound effect at the point in time at which a voice signal corresponding to the at least one keyword is output.