All models
realtime

Orpheus TTS

Apache-2.0 declaration; upstream Llama terms

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.

Hear Orpheus TTS

English Orpheus 3B 0.1 fine-tune · Same three scripts across the directory.

Run it yourselfTry your own text

Best for: Expressive English dialogue with preset voices and emotion tags.

Commercial conditions: The official checkpoint declares Apache but identifies Llama-3.2-3B-Instruct as a base. Review the inherited Llama terms and gated access agreement for the exact stack; do not treat the Apache tag as removing upstream obligations.

Code: Apache-2.0. Weights: Apache-2.0 tag; Llama 3.2 base-model dependency. License sources checked 2026-09-20. Source 1Source 2Source 3

Before you choose: These samples use the English 3B 0.1 fine-tune. Other language releases are separate checkpoints. Local inference has a heavier GPU setup than Kokoro.

The catalog’s 12 GB figure is an estimate. Follow the author’s vLLM and CUDA requirements for the chosen checkpoint.

Details reviewed 2026-09-14. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →
CosyVoice 2Listen side-by-side →XTTS v2Listen side-by-side →Fish Speech 1.5Listen side-by-side →

Choose an alternative to hear both models together.

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.”

Run Orpheus TTS

pip install orpheus-speech

Sources & setup details

Orpheus TTS FAQ

Do I need a GPU to run Orpheus TTS?

The directory lists roughly 12 GB of VRAM as a historical estimate. Check the model documentation for your checkpoint and runtime.

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 declaration; upstream Llama terms 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.

Is there a hosted Orpheus TTS API?

Yes. OpenSpeech Cloud offers Orpheus TTS in its paid English preset-voice studio and API, using prepaid credits. See the Cloud documentation for current availability.