TensorSpeech/TensorFlowTTS
A TensorFlow 2 library for real-time text-to-speech synthesis using state-of-the-art models including Tacotron-2, FastSpeech, FastSpeech2, and neural vocoders.
Not currently ranked — collecting fresh signals.
star history
TensorFlowTTS provides real-time speech synthesis implementations of deep learning models such as Tacotron-2, FastSpeech, and FastSpeech2, along with neural vocoders including Melgan and Multiband-Melgan. The library supports multi-speaker and multilingual TTS for English, French, Korean, Chinese, and German, with optimization via quantization and pruning for faster-than-real-time inference. It offers TensorFlow Lite export for mobile and embedded deployment.
Frequently asked
- What is TensorSpeech/TensorFlowTTS?
- A TensorFlow 2 library for real-time text-to-speech synthesis using state-of-the-art models including Tacotron-2, FastSpeech, FastSpeech2, and neural vocoders.
- Is TensorFlowTTS open source?
- Yes — TensorSpeech/TensorFlowTTS is open source, released under the Apache-2.0 license.
- What language is TensorFlowTTS written in?
- TensorSpeech/TensorFlowTTS is primarily written in Python.
- How popular is TensorFlowTTS?
- TensorSpeech/TensorFlowTTS has 4k stars on GitHub.
- Where can I find TensorFlowTTS?
- TensorSpeech/TensorFlowTTS is on GitHub at https://github.com/TensorSpeech/TensorFlowTTS.