Skip to content
SPECIFICTION
Get listed

Parler-TTS

github.com

WebSelf-hosted
Visit github.com
Spec score 7.3 #177 of 223 in Text-to-Speech Software

Spec sheet

Purpose
Parler-TTS is a lightweight text-to-speech model that generates natural-sounding speech in a requested speaker style.Read 9 Oct 2026 · github.com
Platforms
self_hostedRead 20 Sep 2026 · github.com
Integrations
The model cards provide Transformers usage examples and links to Google Colab and Kaggle notebooks.Read 9 Oct 2026 · huggingface.co
License
The repository identifies its license as Apache-2.0, and the model card also lists Apache-2.0.Read 8 Oct 2026 · github.com
Commercial use
YesRead 20 Sep 2026 · github.com
Export formats
WAVRead 20 Sep 2026 · github.com
Inference features
The inference guide documents SDPA and Flash Attention 2, model compilation, batch generation, and audio streaming.Read 8 Oct 2026 · github.com
Inference optimization
The project describes support for SDPA, torch.compile, batching and streaming to improve inference speed.Read 9 Oct 2026 · github.com
Installation
The library can be installed from the GitHub repository with pip and run locally using Python.Read 8 Oct 2026 · github.com
Languages
1Read 20 Sep 2026 · github.com
Local installation
The library can be installed from the GitHub repository using pip.Read 9 Oct 2026 · github.com
Model license
The Mini v1 and Large v1 model cards identify the license as Apache 2.0.Read 9 Oct 2026 · huggingface.co
Model sizes
The Mini v1 model has about 0.9 billion parameters and the Large v1 model has about 2 billion parameters.Read 9 Oct 2026 · huggingface.co
Open source
The project says its datasets, preprocessing, training code and model weights are publicly released under permissive licenses.Read 9 Oct 2026 · huggingface.co
Platform requirement
The repository says Apple Silicon users need a nightly PyTorch build for bfloat16 support.Read 9 Oct 2026 · github.com
Prompt controls
Text prompts can control speech characteristics including gender, speaking rate, pitch, background noise and reverberation.Read 9 Oct 2026 · huggingface.co
Provider availability
The Mini v1 and Large v1 model pages state that neither model is deployed by an Inference Provider.Read 9 Oct 2026 · huggingface.co
Related project
The project is designed to accompany Data-Speech, a repository for speech dataset annotation.Read 8 Oct 2026 · github.com
Speaker choices
The Mini v1 checkpoint was trained on 34 named speakers to support speaker consistency across generations.Read 8 Oct 2026 · huggingface.co
Speaker consistency
The Mini v1 and Large v1 checkpoints were trained on 34 named speakers for consistent voice generation.Read 9 Oct 2026 · huggingface.co
Training
The repository includes guides and code for training or fine-tuning a Parler-TTS model.Read 9 Oct 2026 · github.com
Training data
The Mini v1 and Large v1 models were trained on 45,000 hours of audio data.Read 9 Oct 2026 · huggingface.co
Voice controls
Prompts can control characteristics such as gender, speaking rate, pitch, background noise, and reverberation.Read 8 Oct 2026 · huggingface.co

Where Specifiction places it

Alternatives to Parler-TTSAll alternatives →