Open Source Python Text to Speech Software - Page 5

WavTokenizer is a state-of-the-art discrete acoustic codec designed specifically for audio language modeling, capable of compressing 24 kHz audio into just 40 or 75 tokens per second while preserving high perceptual quality. It is built to represent speech, music, and general audio with extremely low bitrate, making it ideal as a front-end for large audio language models like GPT-4o and similar architectures. The model uses a single-quantizer design together with temporal compression to achieve extreme compression without sacrificing reconstruction fidelity. Its architecture incorporates a broader vector-quantization space, extended contextual windows, and improved attention networks, combined with multi-scale discriminators and inverse Fourier transform blocks to enhance waveform reconstruction. Extensive experiments show that WavTokenizer matches or surpasses previous neural codecs across speech, music, and general audio on both objective metrics and subjective listening tests.

WaveRNN is a PyTorch implementation of DeepMind’s WaveRNN vocoder, bundled with a Tacotron-style TTS front end to form a complete text-to-speech stack. As a vocoder, WaveRNN models raw audio with a compact recurrent neural network that can generate high-quality waveforms more efficiently than many traditional autoregressive models. The repository includes scripts and code for preprocessing datasets such as LJSpeech, training Tacotron to produce mel spectrograms, training WaveRNN on those spectrograms (with optional GTA data), and finally generating audio. A quick_start.py script allows users to immediately synthesize example sentences from a pretrained model and inspect both generated audio and attention plots. For custom TTS, the project guides you through training Tacotron, forcing GTA spectrogram export when desired, training WaveRNN with or without GTA, and then running joint generation.

WhisperSpeech is an open-source text-to-speech system created by “inverting” OpenAI’s Whisper, reusing its strengths as a semantic audio model to generate speech instead of only transcribing it. The project aims to be for speech what Stable Diffusion is for images: powerful, hackable, and safe for commercial use, with code under Apache-2.0/MIT and models trained only on properly licensed data. Its architecture follows a token-based, multi-stage pipeline inspired by AudioLM and SPEAR-TTS: Whisper is used to produce semantic tokens, EnCodec compresses the waveform into acoustic tokens, and Vocos reconstructs high-fidelity audio from those tokens. The repository includes notebooks and scripts for inference, long-form synthesis, and finetuning, as well as pre-trained models and converted datasets hosted on Hugging Face. Performance optimizations like torch.compile, KV-caching, and architectural tweaks allow the main model to reach up to 12× real-time speed on a consumer RTX 4090.

YandexStation is a Home Assistant custom component that integrates Yandex-branded smart speakers and other devices with Alice into a unified smart home automation environment. It supports both local and cloud control, depending on the device type, with Yandex speakers often supporting both modes and third-party speakers typically limited to cloud control. The integration exposes playback and volume controls, as well as text-to-speech capabilities that send spoken messages in Alice’s voice directly to the speakers. It also lets you send arbitrary text commands as if you were talking to Alice, enabling scenarios such as “play my music,” launching routines, or querying information via Home Assistant automations. In local control mode, the component can read back what is currently playing, including album art, and supports seeking and track skipping, which is more limited in cloud-only mode.

uListen is a TTS(Text To Speech) application. It can TALK you the web pages, chm files, pdf files and word files and plain text files.

vits_chinese is an implementation of the VITS end-to-end text-to-speech (TTS) architecture tailored for Chinese (and possibly multilingual) speech synthesis. VITS is a model combining variational autoencoders (VAEs), normalizing flows, adversarial learning, and a stochastic duration predictor — a design that enables generation of natural, expressive speech, capturing variations in rhythm and prosody. By customizing or porting VITS for Chinese, this project aims to produce high-quality TTS outputs in a language that can be challenging due to tones, pronunciation variability, and prosody. The repository offers full training and inference pipelines: preprocessing, mel-spectrogram generation, training scripts, and audio synthesis. For users who don’t train their own models, the project provides pre-trained checkpoints (or instructions) and expects integration with a vocoder during speech synthesis.

wukong-robot is a Chinese voice assistant / smart speaker project built to let makers and hackers design highly customizable voice-controlled devices. It combines wake-word detection, automatic speech recognition, natural language understanding, and text-to-speech into a single framework aimed at the Chinese-speaking ecosystem. The project is positioned as a simple, flexible, and elegant platform that can run on devices like Raspberry Pi and other Linux-based boards, making it suitable for DIY smart speakers and home-automation hubs. It supports multi-turn conversational capabilities powered by ChatGPT or other large language models, letting users have continuous dialogues rather than one-shot commands. The project emphasizes extensibility: there is a plugin ecosystem (wukong-contrib) where developers can add new skills such as controlling smart-home devices, querying services, or performing custom actions.