# canopyai/Orpheus-TTS

Towards Human-Sounding Speech

Repository: https://github.com/canopyai/Orpheus-TTS
Canonical: https://ross.abutalabs.com/products/orpheus-tts
Homepage: https://canopylabs.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llm, tts, realtime
Last push: 2025-12-05T19:01:02+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 55, release rhythm 35, longevity 38
- inputs: {"age_days": 543, "days_push": 271, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6314, forks 535 (observed 2026-08-28T04:09:41.686009+00:00)

## What it is
Orpheus TTS is an open-source text-to-speech system built on a Llama-3b backbone that produces human-sounding speech with emotion control and zero-shot voice cloning. It supports low-latency streaming (~200ms) for realtime applications and includes pretrained, finetuned, and multilingual model releases.

## Use cases
- generate natural-sounding speech from text
- clone a voice without fine-tuning
- build a realtime voice assistant with low latency
- control emotion and intonation in synthesized speech
- fine-tune a TTS model for a new language
- stream audio for a voice chatbot

## When to choose
- you need expressive, human-like TTS with emotion tags
- you want zero-shot voice cloning without training data
- you need low-latency streaming speech for realtime apps
- you want an open-source LLM-based TTS you can fine-tune yourself

## When to avoid
- you need a lightweight TTS without GPU hardware
- you only need simple robotic TTS for embedded devices
- you require production support for many languages beyond the released set

## Facets
- artifact type: library
- maturity: active
- function: tts, llm-inference, speech-recognition, machine-learning
- domain: speech-processing, large-language-models, deep-learning, artificial-intelligence
- platform: python, cloud
- tags: text-to-speech, voice-cloning, streaming, llama-backbone, multilingual, realtime-audio, gpu, docker

## Member repositories
- canopyai/Orpheus-TTS (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:41.686009+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:46:12.708190+00:00, confidence not recorded.
  - readme: https://github.com/canopyai/Orpheus-TTS (fetched 2026-08-28T04:09:41.686009+00:00, sha f1d0aaab9469)
  - homepage: https://canopylabs.ai (fetched 2026-08-29T08:42:39.549462+00:00, sha 355652bd2d69)
- Data as of 2026-08-30T08:39:29.467469+00:00.