Workflow Name: Record Tone Text-to-Speech
【Workflow Introduction】
During the operation process, you first need to upload an audio clip, which is the starting point of the entire process. Next, you need to input a detailed textual description of the audio, allowing the system to better understand the characteristics of the audio and your requirements. After that, carefully input the text description you wish to convert to speech, clearly and accurately expressing your expectations. Once all preparations are complete, simply click run, and you can generate an excellent result of text-to-speech with recorded tone in one click. The entire process is simple and convenient, yet it can bring you surprising outcomes. Give it a try now!

【Usage Scenarios】
When you have a unique speech audio clip and want to replicate the same tone in other content to maintain stylistic consistency, this workflow enables you to achieve this goal easily, allowing the new speech content to possess the same charming tone as the original audio.

【Key Node】
CosyVoiceNode