
Qwen3 TTS Audio Generation for Conversations with 8 People or Less (Supports Uploading Voice Cloning or Text Description to Generate Voice)
Each character has two options to choose from [Voice generated by text description]/[Using uploaded voice]:
- Option 1: Generate voice based on your text description, then speak out the lines you provide
- Option 2: Clone the voice based on the one you upload, then speak out the lines you provide
AI application:
- AI application can be selected through the dropdown options. After choosing one option, the parameters of the other option will be invalid and can be ignored.
Workflow:
- The workflow can control the options through the pink switch;
- The fluorescent green nodes are input parameters and can be adjusted, while other nodes do not need modification.
It takes about 3 minutes and also supports conversations with any number of people under 8.
The final output is an audio clip.
Note: The character names used in the complete lines must match the names you assign to the characters.
๐Qwen3 TTS Audio Generation for Conversations with 2 People/Single Person (Supports Uploading Voice Cloning or Text Description to Generate Voice)
https://www.runninghub.cn/post/2018391521661292545?inviteCode=ishbfzc1
๐(For combined use) LTX2.0 Video Frame-by-Frame Generation V3 Audio-Driven Version_Triple Sampling (Upload Audio Manually)
https://www.runninghub.cn/post/2017697617920135169?inviteCode=ishbfzc1
Qwen3 TTS Audio Generation for Conversations with 8 People or Less (Supports Uploading Voice Cloning or Text Description to Generate Voice)
Each character has two options to choose from [Voice generated by text description]/[Using uploaded voice]:
- Option 1: Generate voice based on your text description, then speak out the lines you provide
- Option 2: Clone the voice based on the one you upload, then speak out the lines you provide
AI application:
- AI application can be selected through the dropdown options. After choosing one option, the parameters of the other option will be invalid and can be ignored.
Workflow:
- The workflow can control the options through the pink switch;
- The fluorescent green nodes are input parameters and can be adjusted, while other nodes do not need modification.
It takes about 3 minutes and also supports conversations with any number of people under 8.
The final output is an audio clip.
Note: The character names used in the complete lines must match the names you assign to the characters.
๐Qwen3 TTS Audio Generation for Conversations with 2 People/Single Person (Supports Uploading Voice Cloning or Text Description to Generate Voice)
https://www.runninghub.cn/post/2018391521661292545?inviteCode=ishbfzc1
๐(For combined use) LTX2.0 Video Frame-by-Frame Generation V3 Audio-Driven Version_Triple Sampling (Upload Audio Manually)
https://www.runninghub.cn/post/2017697617920135169?inviteCode=ishbfzc1