Description

OpenVoice is a Hugging Face Space by myshell-ai that lets you type text and upload a brief audio sample of a speaker.

The app creates a new audio file in the same voice as the sample, with optional emotion controls visible in the page description.

How we innovate

What sets OpenVoice apart is its simple workflow: a short text input and a brief reference audio sample are enough to generate speech in a matching voice, with emotion controls also available in the app description.

Use Case / Scenario

1. Voice-based audio generation

Use OpenVoice to turn written text into audio spoken in a sampled voice.

2. Speaker voice matching

Provide a short sample of a speaker so the generated audio can follow that voice.

3. Optional emotion styling

Use the app’s emotion options when you want the output to carry a different vocal expression.

Visit Website