Orpheus TTS
Open-source Llama-based speech model with emotion tags and voice cloning.
About Orpheus TTS
Orpheus is an open-source speech model from Canopy Labs built on a 3B Llama backbone and trained on more than 100,000 hours of English speech. It accepts inline tags such as <laugh>, <sigh>, <cough> and <gasp>, so you can write those sounds into the script. Streaming output starts in about 200 ms, or around 100 ms with input streaming. The pretrained model can clone a voice zero-shot from text and audio pairs in the prompt, and fine-tuning a new speaker takes about 50 to 300 samples. English ships with eight preset voices, and a set of multilingual models is out as a research preview. Install with pip (orpheus-speech); inference runs through vLLM, so you need a capable GPU.
Key Features
💰 Pricing
Free and open source (Apache-2.0). Self-hosted on your own GPU.
Frequently Asked Questions
Is Orpheus TTS free?
What is Orpheus TTS used for?
What platforms does Orpheus TTS work on?
What are the best alternatives to Orpheus TTS?
Reviews
Loading reviews...
Questions & Answers
Questions submitted will appear here soon
Join the community to share knowledge about Orpheus TTS
📊 Comparison vs Alternatives
| Feature | ||||
|---|---|---|---|---|
| Pricing | Free | Free | Freemium | Paid |
| Rating | — | ⭐ 4.4 | ⭐ 4.5 | ⭐ 5.0 |
| Free Tier | ✅ | ✅ | ✅ | ❌ |
| Popularity | 45% | 82% | 80% | 80% |
Are you the creator of Orpheus TTS?
Claim this listing to get a verified badge, edit tool details, and respond to reviews. You’ll sign in and confirm a work email so we can verify ownership.
Claim this listingQuick Stats
Categories
Orpheus TTS Alternatives
The Weekly AI Tools & Skills Digest
Launching soon: trending agent skills, new tools, and what's actually worth trying. Sign up to get the first issue.
Free forever. Unsubscribe anytime.