# edwko/OuteTTS

Interface for OuteTTS models.

Repository: https://github.com/edwko/OuteTTS
Canonical: https://ross.abutalabs.com/products/outetts
Homepage: https://outeai.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: gguf, llama, text-to-speech, transformers, tts
Last push: 2026-03-23T08:31:30+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 73, release rhythm 28, longevity 47
- inputs: {"age_days": 667, "days_push": 163, "days_rel": 471, "gap_med": 34, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1436, forks 117 (observed 2026-08-28T04:04:43.543895+00:00)

## What it is
OuteTTS is a Python interface for running OuteAI's text-to-speech models, supporting multiple inference backends including llama.cpp, Hugging Face Transformers, ExLlamaV2, and vLLM. It also ships an npm package (Transformers.js) for browser-based TTS with the 0.2 model.

## Use cases
- generate speech from text with an open TTS model
- run text-to-speech locally with llama.cpp GGUF models
- clone a voice from a short audio sample
- batch TTS inference on GPU with vLLM or ExLlamaV2
- run TTS in the browser with transformers.js
- convert text to speech on CPU without a GPU

## When to choose
- you want local, open-weight TTS with flexible backends (CPU via llama.cpp or GPU via CUDA/ROCm)
- you need voice cloning or speaker profiles with OuteTTS 1.0 models
- you want batched, high-throughput TTS inference on an NVIDIA GPU

## When to avoid
- you need a managed cloud TTS API with no local setup
- you require non-English/multilingual coverage beyond what OuteTTS models support
- you need production-grade, battle-tested TTS rather than a fast-moving research project

## Facets
- artifact type: library
- maturity: active
- function: tts, llm-inference, speech-recognition
- domain: speech-processing, large-language-models, machine-learning
- platform: python, cross-platform, cli
- tags: text-to-speech, gguf, llama-cpp, transformers, voice-cloning, exllamav2, vllm, transformersjs, audio, gpu

## Member repositories
- edwko/OuteTTS (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.543895+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 2026-08-30T04:36:47.398963+00:00, confidence not recorded.
  - readme: https://github.com/edwko/OuteTTS (fetched 2026-08-28T04:04:43.543895+00:00, sha d19ab3c340f0)
  - homepage: https://outeai.com (fetched 2026-08-29T11:47:46.529663+00:00, sha b40d7549909b)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T11:47:46.539059+00:00, sha bdec26667b98)
  - registry_pypi: https://pypi.org/pypi/outetts/json (fetched 2026-08-29T11:47:46.545077+00:00, sha 2dce5971e34a)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T11:47:46.541052+00:00, sha de6b7a178be5)
  - site_page: https://huggingface.co/huggingface (fetched 2026-08-29T11:47:46.543223+00:00, sha f35969986801)
- Data as of 2026-08-30T08:39:29.467469+00:00.