vsref
Orpheus TTS logo

Orpheus TTS

OSS

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

Facts verified Jul 20, 2026Website →

What we know about Orpheus TTS

Orpheus TTS is a text-to-speech apis platform: the 'LLM-as-TTS' approach under Apache-2.0 - expressive and clonable, but repo activity has slowed since mid-2025. This profile tracks what we have verified about Orpheus TTS, each fact linked to a primary source and dated.

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.

In total we track 12 verified facts for Orpheus TTS today, and add coverage as the ingestion pass revisits it. Where a number is a vendor claim rather than our own measurement, it is labeled as such on the Orpheus TTS fact sheet below, and each row links the primary source it came from so you can check our work.

Whether Orpheus TTS is the right call depends on your use case more than any single spec, which is why the head-to-head verdicts below score it per scenario rather than crowning one overall winner. Use the fact sheet for the raw numbers, and the matchups for how Orpheus TTS actually fares against the platforms buyers most often weigh it against.

Fact sheet

Capabilities
Capabilities facts
Streaming audio output✓ YesJul 20
Instant voice cloning✓ YesJul 20
Languages supported8 languagesJul 20
Emotion / style controls✓ YesJul 20
Compliance & trust
Compliance & trust facts
Self-host / on-prem option✓ YesJul 20
Model weights licenseApache-2.0Jul 20
Build experience
Build experience facts
Official SDKsvLLM (GPU), llama.cpp (CPU), Python packageJul 20
Commercial
Commercial facts
Model size (parameters)3BJul 20
Hardware to self-hostGPU inference via vLLM; CPU inference possible via llama.cppJul 20
Hosted API availableYesJul 20
Project maintenance statusdormantJul 20
GitHub stars6,200 starsJul 20

Considering a switch? Best Orpheus TTS alternatives →