# neuphonic/neutts

On-device TTS model by Neuphonic

Repository: https://github.com/neuphonic/neutts
Canonical: https://ross.abutalabs.com/products/neutts
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-07-30T14:11:22+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 23
- inputs: {"age_days": 335, "days_push": 34, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6256, forks 655 (observed 2026-08-28T04:09:41.068249+00:00)

## What it is
NeuTTS is a collection of open-source, on-device text-to-speech models built on small LLM backbones, with instant voice cloning from as little as 3 seconds of audio. Models ship in GGUF quantizations for running locally on phones, laptops, and Raspberry Pis.

## Use cases
- run text-to-speech offline on my own device
- clone a voice from a short audio sample
- build an embedded voice assistant or talking toy
- generate speech locally without cloud APIs for privacy compliance
- run a small TTS model on a Raspberry Pi
- synthesize multilingual speech in French, German, or Spanish

## When to choose
- you need private, on-device speech synthesis without sending audio to a cloud API
- you want instant voice cloning with minimal reference audio
- you target resource-constrained hardware like phones or Raspberry Pis
- you need GGUF quantized models for efficient local inference

## When to avoid
- you need the highest possible TTS quality regardless of model size
- you require a fully permissive license - the license is non-standard
- you need extensive language coverage beyond the supported languages
- you prefer managed cloud TTS services with SLAs

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, llm-inference, machine-learning
- domain: speech-processing, artificial-intelligence, large-language-models
- platform: python, cross-platform, embedded
- tags: voice-cloning, on-device-ai, gguf, speech-synthesis, voice-ai, gpu

## Member repositories
- neuphonic/neutts (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:41.068249+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 2026-08-29T17:46:35.187848+00:00, confidence not recorded.
  - readme: https://github.com/neuphonic/neutts (fetched 2026-08-28T04:09:41.068249+00:00, sha e5c3431add03)
- Data as of 2026-08-30T08:39:29.467469+00:00.