# Orpheus TTS Review

> Orpheus TTS review: The 'LLM-as-TTS' approach under Apache-2.0 - expressive and clonable, but repo activity has slowed since mid-2025. Verified pricing.

![Orpheus TTS logo](https://www.versusref.com/logos/orpheus.png)

The 'LLM-as-TTS' approach under Apache-2.0 - expressive and clonable, but repo activity has slowed since mid-2025.

Among the 46 text-to-speech tools we track, Orpheus TTS has the 30th-widest language coverage.

See pricing · Open source · facts verified Jul 20, 2026

## What we know about Orpheus TTS

Orpheus TTS sits in the text-to-speech apis category, where it is the 'LLM-as-TTS' approach under Apache-2.0 - expressive and clonable, but repo activity has slowed since mid-2025. We keep this Orpheus TTS profile grounded in primary sources, each fact dated to when we last confirmed it.

Orpheus TTS does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Orpheus TTS quote, it is the fastest way for us to close that gap.

On capabilities, Orpheus TTS covers streaming audio output, instant voice cloning, emotion / style controls, and self-host / on-prem option. Each of those is verified against Orpheus TTS's own docs or dashboard, not marketing copy.

Among the 46 text-to-speech tools in our matrix, Orpheus TTS leads with the 30th-widest language coverage; the fact sheet below has the raw numbers behind that placement.

In total we track 12 verified facts for Orpheus TTS today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Orpheus TTS fact sheet below.

## Fact sheet

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Streaming audio output | ✓  Yes | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |
| Instant voice cloning | ✓  Yes | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |
| Languages supported | 8 languages | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |
| Emotion / style controls | ✓  Yes | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |
| Model weights license | Apache-2.0 | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | vLLM (GPU), llama.cpp (CPU), Python package | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | 3B | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |
| Hardware to self-host | GPU inference via vLLM; CPU inference possible via llama.cpp | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |
| Hosted API available | Yes | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |
| Project maintenance status | dormant | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS/commits/main) |
| GitHub stars | 6,200 stars | Jul 20 | [source](https://github.com/canopyai/Orpheus-TTS) |

Source: https://www.versusref.com/tts/tools/orpheus/