Drama-3

What is Drama-3

Drama-3 is an open-source speech synthesis and emotional voice generation model released by Fish Audio. It supports generating natural speech with dramatic emotion from text.

Key features

• Generate natural speech with dramatic emotion from text
• Supports multiple speech generation and control methods including Surprise, Clone, Design and Give a note
• Can use preset voices, upload audio clips or microphone input for voice cloning
• Supports designing voices through text descriptions
• Provides a Workflow canvas to build generation pipelines visually

Who it is for

Suitable for developers, content creators and researchers who need to generate emotionally rich, dramatic speech.

How to get started

1. Visit https://huggingface.co/spaces/fishaudio/Drama-3
2. Duplicate in Spaces using ZeroGPU hardware
3. Enter text, select a voice and provide performance direction to generate speech

Compiled from public descriptions on the tool's official website / README / launch page. Pricing and user numbers have not been verified; please check the official website. Some sections were drafted with AI assistance. Written in Chinese and English; other languages are machine-translated.