# Orpheus TTS

> Orpheus TTS is a 3B-parameter speech LLM built on Llama-3.2-3B-Instruct, with English finetuned voices, emotive tags like \<laugh\> and \<sigh\>, about 200ms streaming latency, and a multilingual research preview. Code is Apache-2.0; weights are tagged Apache-2.0 on Hugging Face but are gated and list a Llama base model. Main inference uses vLLM; a llama.cpp path runs without a GPU. Zero-shot cloning is claimed but the cloning notebook is still on the to-do list.

- Repository: https://github.com/canopyai/Orpheus-TTS
- Official docs: https://github.com/canopyai/Orpheus-TTS#readme
- Checked: 2026-10-15

## What it replaces
- ElevenLabs: Speech generation, Voice cloning (partial). Expressive streaming speech with preset voices and emotion tags. Zero-shot cloning is claimed, but the README lists fixing the voice cloning notebook as unfinished.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, GPU via vLLM, or CPU via the llama.cpp-based orpheus-cpp | https://github.com/canopyai/Orpheus-TTS/blob/main/additional_inference_options/no_gpu/README.md | 2026-10-15 |
| Code licence | Confirmed | Apache-2.0 | https://github.com/canopyai/Orpheus-TTS/blob/main/LICENSE | 2026-10-15 |
| Model weights licence | Partial | Tagged Apache-2.0 on Hugging Face, but weights are gated and list meta-llama/Llama-3.2-3B-Instruct as a base model, whose own licence may also apply | https://huggingface.co/canopylabs/orpheus-3b-0.1-ft | 2026-10-15 |
| Commercial use | Partial | Likely yes under Apache-2.0, but check the Llama 3.2 base-model terms and the model card's misuse rules | https://huggingface.co/canopylabs/orpheus-3b-0.1-ft | 2026-10-15 |
| Paid services needed? | Partial | None required; Baseten hosted deployment is offered as an optional extra | https://github.com/canopyai/Orpheus-TTS#one-click-deployment-on-baseten | 2026-10-15 |
| Hardware | Partial | GPU path via vLLM; a no-GPU path via llama.cpp is documented; no VRAM or RAM numbers stated | https://github.com/canopyai/Orpheus-TTS/blob/main/additional_inference_options/no_gpu/README.md | 2026-10-15 |
| Operating systems | Partial | CPU path documents Linux, Windows and Apple Silicon macOS; OS support for the main vLLM path is not stated | https://github.com/canopyai/Orpheus-TTS/blob/main/additional_inference_options/no_gpu/README.md | 2026-10-15 |
| Setup effort | Confirmed | Medium, pip install orpheus-speech (uses vLLM, may need vllm==0.7.3) plus Hugging Face access to the gated weights | https://github.com/canopyai/Orpheus-TTS#streaming-inference-example | 2026-10-15 |

GitHub: 6356 stars, 537 forks, last push 2025-12-05, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/orpheus-tts). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.