# huggingface/parler-tts

Inference and training library for high-quality TTS models.

Repository: https://github.com/huggingface/parler-tts
Canonical: https://ross.abutalabs.com/products/parler-tts
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-12-10T08:28:12+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 66
- inputs: {"age_days": 932, "days_push": 631, "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 5586, forks 588 (observed 2026-08-28T04:09:22.600376+00:00)

## What it is
Parler-TTS is a lightweight text-to-speech library from Hugging Face that generates high-quality, natural-sounding speech controllable via text descriptions of speaker style. It includes both inference and training code, with fully open datasets, weights, and training pipeline.

## Use cases
- generate speech from text with a described voice style
- train a custom text-to-speech model on my own data
- convert text to natural sounding audio in Python
- control gender, pitch, and speaking style of synthesized speech
- run fast TTS inference with flash attention on GPU
- build an audiobook narration generator

## When to choose
- you need fully open-source TTS with permissive licensing
- you want text-prompt control over voice characteristics
- you plan to fine-tune or train your own TTS model
- you want lightweight dependencies and Hugging Face ecosystem integration

## When to avoid
- you need zero-shot voice cloning from a short audio sample
- you need streaming real-time TTS for production voice assistants
- you want a plug-and-play GUI without writing code

## Facets
- artifact type: library
- maturity: active
- function: tts, machine-learning, llm-training
- domain: speech-processing, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: text-to-speech, huggingface, open-source-models, voice-cloning, audio-generation, gpu

## Member repositories
- huggingface/parler-tts (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:22.600376+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 2026-08-29T17:55:32.305936+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/parler-tts (fetched 2026-08-28T04:09:22.600376+00:00, sha d0266e6ef230)
- Data as of 2026-08-30T08:39:29.467469+00:00.