摘要 |
<p>A method of generating video data with an audio soundtrack includes: receiving 204 video (image) data relating to a product or service; obtaining 208, 210 descriptive data relating to the product or service, for example performing image analysis 208 on at least one frame of video data to find an identifier, such as a vehicle number plate or license plate; generating 214, 216 audio data based on the descriptive data; adding 218 the audio data as a soundtrack to at least part of the video data; and storing 220 and/or playing the video data with the added soundtrack. Obtaining descriptive data may include searching a database of vehicles using the identifier and retrieving information (e.g. a model specification) matching the identifier. If no identifier is found by image analysis, manual input 210 may be used. Text or a sentence may be produced 214, and used to generate audio (speech) data. When the video and combined audio data is saved, it may have a file name including at least some of the descriptive data. Sets of audio data may include different languages or marketing messages.</p> |