Plain-AyI
← All projects
Speech & audio

Amphion

A research toolkit for making speech, singing, music and sound with AI.

Research-backedNew this week

What it does

Amphion is a toolkit for research on AI-made audio. It covers turning text into speech, making singing voices, changing one voice to sound like another, changing accents and turning text into sound effects. Text-to-music is in development.

It also includes vocoders (the part that turns model output into real sound), ways to measure audio quality, and large speech datasets. Its makers say it aims to help newer researchers get started in this field.

Who it's for

Researchers and engineers studying speech and audio generation.

Can I use it without coding?

Developers only. It is a research codebase meant for people comfortable with Python and AI models. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it