TensorFlowTTS

Spec sheet

Purpose

TensorFlowTTS provides real-time speech synthesis architectures built on TensorFlow 2.Read 13 Oct 2026 · github.com

Platforms

Linux,iOS,AndroidRead 20 Sep 2026 · github.com

Deployment

The project supports TFLite conversion, C++ inference, and deployment to mobile devices or embedded systems.Read 13 Oct 2026 · github.com

Integrations

The project documents integration with Hugging Face Spaces and Gradio, and hosting pretrained models on the Hugging Face Hub.Read 13 Oct 2026 · github.com

Support

The README provides project contact email addresses and links to tutorials, notebooks, and Colab examples.Read 13 Oct 2026 · github.com

License

The repository states that its models are licensed under Apache 2.0.Read 13 Oct 2026 · github.com

Architectures

Supported architectures include Tacotron-2, MelGAN, Multiband-MelGAN, FastSpeech, FastSpeech 2, Parallel WaveGAN, and HiFi-GAN.Read 13 Oct 2026 · github.com

Commercial use

YesRead 20 Sep 2026 · github.com

Data compatibility

Its preprocessing is based on ESPnet, and the README says the resulting data can be combined with models from the ESPnet repository.Read 13 Oct 2026 · github.com

Datasets

The documented preprocessing currently supports LJSpeech, KSS, Baker, LibriTTS, Thorsten, and Synpaflex datasets.Read 12 Oct 2026 · github.com

Export formats

WAVRead 20 Sep 2026 · github.com

Installation

The project documents installation with pip or from its GitHub source repository.Read 12 Oct 2026 · github.com

Languages

The README lists Chinese, Korean, English, French, and German support, and says the framework can be adapted for other languages.Read 13 Oct 2026 · github.com

Mobile examples

The README includes an Android example and reports iOS support for FastSpeech 2 and MB MelGAN.Read 13 Oct 2026 · github.com

Model reuse

Pretrained models can be loaded from Hugging Face Hub using the project’s inference API.Read 12 Oct 2026 · github.com

Models

It provides Tacotron-2, MelGAN, Multiband-MelGAN, FastSpeech, FastSpeech 2, Parallel WaveGAN, and HiFi-GAN architectures.Read 12 Oct 2026 · github.com

Requirements

The repository says it was tested on Ubuntu 18.04 with Python 3.7 or later and TensorFlow versions 2.2 through 2.6.Read 13 Oct 2026 · github.com

Supported datasets

The README lists ljspeech, kss, baker, libritts, thorsten, and synpaflex for preprocessing, with reformatting instructions for some datasets.Read 13 Oct 2026 · github.com

Training

Features include mixed-precision training and single- or multi-GPU training and gradient accumulation.Read 13 Oct 2026 · github.com

Use case

The project describes itself as suitable for speech synthesis research, training or fine-tuning TTS models, and deployment.Read 12 Oct 2026 · github.com

Where Specifiction places it

• Text-to-speech tools#194 of 2337.3
• Text-to-Speech Software#190 of 2237.2