All models
realtime

Orpheus TTS

Apache-2.0

Llama-3 based, empathetic, low-latency for interactive apps

Orpheus is a Llama-3B-based speech model from Canopy Labs. It generates remarkably human intonation and supports inline emotive tags like laughter and sighs, plus zero-shot voice cloning and low-latency streaming. One of the most natural conversational voices in open source.

Voices

4 voices
Female
Taradefault
american
Emma
american
Male
Dan
american
Josh
american

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install orpheus-speech

Orpheus TTS FAQ

Do I need a GPU to run Orpheus TTS?

For practical speeds, yes — plan on roughly 12 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can Orpheus TTS clone voices?

Yes — Orpheus TTS supports voice cloning from reference audio.

What license is Orpheus TTS released under?

Orpheus TTS is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Orpheus TTS support?

Orpheus TTS supports English, Spanish, French, German, Italian, Portuguese, Hindi, Chinese, Japanese, Korean.

Is there a hosted Orpheus TTS API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to Orpheus TTS and every other model in this directory. No CUDA, Docker, or GPU needed.