20250225 Update and Integration

MaskGCT

Workflow Name: Audio Workflow Integration
【Workflow Introduction】
Four built-in plugins for audio production:
The first is voice cloning from recorded audio. First, you need to upload an audio clip, then input the text that perfectly matches the audio. In the CosyVoiceNode node, select "3-Second Fast Cloning" and then run it.
The second is text-to-speech. You only need to input the text description, select a pre-trained voice in the CosyVoiceNode node, and then run it to generate speech.
The third is Chat TTS text-to-speech. After inputting the text description, run it directly to generate speech.
The fourth is speech-to-text. Upload an audio clip, then run it, and the system will automatically convert it into text.

【Usage Scenarios】
If you have a recorded speech audio clip and want to convert it into a text record, you can use the fourth plugin. Or, if you want to generate speech from a specific text, you can choose the second plugin and create rich and diverse speech effects by selecting different pre-trained voices. If you already have a text description and want to quickly generate speech, you can use Chat TTS text-to-speech.

【Key Nodes】
Chat TTS, CosyVoiceNode