Qwen3 TTS Two-Person/Single-Person Dialogue Audio Generation (Supports Uploading Voice Cloning or Generating Voice Based on Text Description)

Each role has two options to choose from【Generate voice based on text description】/【Use uploaded voice】:

Option 1: Generate voice based on your text description and then speak the lines you provide
Option 2: Clone the voice you upload and then speak the lines you provide

AI application:

AI application can be selected through the dropdown options. After choosing one option, the parameters for the other option will become invalid and can be ignored.

Workflow:

In the workflow, control the options via the pink switch;
The fluorescent green nodes are input parameters, adjust them as needed, other nodes do not need modification.

It takes less than one minute, and single-person speech is also supported.
The final output is a segment of audio.

Note: The character names in the complete lines must match the names you assign to each character.

👇Qwen3 TTS Dialogue Audio Generation for 8 or fewer people (Supports Uploading Voice Cloning or Generating Voice Based on Text Description)
https://www.runninghub.cn/post/2017578327875264513?inviteCode=ishbfzc1

👇(Used in combination) LTX2.0 First and Last Frame Video V3 Audio-Driven Version_Three-Time Sampling (Upload audio independently)

https://www.runninghub.cn/post/2017697617920135169?inviteCode=ishbfzc1

Qwen3 TTS Two-Person/Single-Person Dialogue Audio Generation (Supports Uploading Voice Cloning or Generating Voice Based on Text Description)

Each role has two options to choose from

Option 1: Generate voice based on your text description and then speak the lines you provide

Option 2: Clone the voice you upload and then speak the lines you provide

AI application:

AI application can be selected through the dropdown options. After choosing one option, the parameters for the other option will become invalid and can be ignored.

Workflow:

In the workflow, control the options via the pink switch;

The fluorescent green nodes are input parameters, adjust them as needed, other nodes do not need modification.

👇(Used in combination) LTX2.0 First and Last Frame Video V3 Audio-Driven Version_Three-Time Sampling (Upload audio independently)

Qwen3 TTS 2-person/single-person dialogue audio generation (supports uploading voice cloning or text description to generate voice) 5722

Audio Generation

Qwen3 TTS Two-Person/Single-Person Dialogue Audio Generation (Supports Uploading Voice Cloning or Generating Voice Based on Text Description)

Qwen3 TTS Two-Person/Single-Person Dialogue Audio Generation (Supports Uploading Voice Cloning or Generating Voice Based on Text Description)

Qwen3 TTS 2-person/single-person dialogue audio generation (supports uploading voice cloning or text description to generate voice)
57
2
2