# huggingface/parler-tts

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/huggingface-parler-tts).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

5,579 stars · 590 forks · Python · Apache-2.0

## Links

- GitHub: https://github.com/huggingface/parler-tts
- awesome-repositories: https://awesome-repositories.com/repository/huggingface-parler-tts.md

## Description

Parler-TTS is a library for generating high-quality speech from text, supporting both inference and model training. It combines a transformer-based text-to-speech generator with a mel-spectrogram decoder to convert written text into natural-sounding audio.

The project distinguishes itself through text-conditioned voice control, which allows speaker attributes like gender, pitch, speaking rate, and style to be adjusted via a natural-language description. It also includes speaker embedding selection for maintaining voice identity across multiple generations, and a fine-tuning recipe system that adapts pretrained models to custom datasets with defined data preprocessing, training hyperparameters, and evaluation steps.

Beyond inference, Parler-TTS provides capabilities for training new text-to-speech models or fine-tuning existing ones on user-provided datasets. The library is available as a Python package with documentation covering installation, model usage, and training workflows.

## Tags

### Artificial Intelligence & ML

- [Text-to-Speech](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech.md) — Converts written text into natural-sounding speech using a neural model with controllable voice attributes. ([source](https://cdn.jsdelivr.net/gh/huggingface/parler-tts@main/README.md))
- [Neural Decoders](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-processing/mel-spectrogram-processing/neural-decoders.md) — Ships a neural mel-spectrogram decoder that converts transformer outputs into time-frequency audio representations.
- [Natural Language Conditioners](https://awesome-repositories.com/f/artificial-intelligence-ml/diffusion-conditioning-architectures/voice-conditioning-encoders/natural-language-conditioners.md) — Encodes natural-language descriptions of speaker attributes into conditioning vectors that modulate the decoder output.
- [Fine-tuning Recipes](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-customization/fine-tuning-recipes.md) — Provides structured fine-tuning recipes that define data preprocessing, hyperparameters, and evaluation steps for custom TTS datasets.
- [Attribute Descriptions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-parameter-configurations/voice-parameter-controls/attribute-descriptions.md) — Adjusts speaker characteristics such as gender, pitch, speaking rate, and style via natural-language text descriptions. ([source](https://cdn.jsdelivr.net/gh/huggingface/parler-tts@main/README.md))
- [Speaker Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/speaker-embeddings.md) — Uses speaker embeddings to maintain consistent voice identity across multiple text-to-speech generations.
- [Libraries](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech-models/libraries.md) — Provides a Python library for generating high-quality speech from text with controllable voice attributes, supporting both inference and model training.
- [Transformer Decoders](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-speech/transformer-decoders.md) — Implements a transformer decoder that autoregressively predicts mel-spectrogram frames from text tokens for speech generation.
- [Text-to-Speech Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/model-training-frameworks/text-to-speech-model-training.md) — Supports training new text-to-speech models and fine-tuning existing ones on user-provided datasets.
- [Voice Identity Selections](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/speech-processing/voice-synthesis/modular-voice-configurations/voice-identity-selections.md) — Allows selection from predefined speaker embeddings to maintain consistent voice identity across generations. ([source](https://cdn.jsdelivr.net/gh/huggingface/parler-tts@main/README.md))

### Part of an Awesome List

- [Model Training and Fine-tuning](https://awesome-repositories.com/f/awesome-lists/ai/model-training-and-fine-tuning.md) — Provides tools and scripts for training new TTS models or fine-tuning existing ones on custom datasets. ([source](https://cdn.jsdelivr.net/gh/huggingface/parler-tts@main/README.md))