CPC G10L 13/047 (2013.01) | 20 Claims |
1. A method comprising:
detecting an instruction to perform a text-to-speech conversion;
sending text to a server;
downloading, from the server, first audio data that are based on the text;
continuing to download the rest of the first audio data when the first frame is downloaded within a preset duration; and
synthesizing, when the first frame is not downloaded within the preset duration, the audio signal into second audio data, wherein the second audio data comprises an audio signal in an offline database and that corresponds to the text.
|