Plain-AyI
← All projects
Speech & audio

Orpheus TTS

An open text-to-speech model that aims to sound human, with emotion control and voice cloning.

New this week

What it does

Orpheus TTS turns written text into spoken audio. It is built on a Llama language model, and its makers say its speech has natural tone, emotion and rhythm.

You can guide emotion with simple tags, and it can stream audio quickly enough for live conversation. It can also copy a voice from a sample without extra training.

There are English models plus a research preview of models for other languages, and guides for training your own version.

Who it's for

Developers building voice assistants, audio content or other speech features.

Can I use it without coding?

Developers only. It runs from Python code; there are online notebooks for trying it. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux, Cloud
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 (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it