Google's family of large language models
The purpose of this project is to provide a package for speech processing and feature extraction. This library provides most frequent used speech features including MFCCs and filterbank energies alongside with the log-energy of filterbanks. | It is a unified, developer-friendly API to the best available Speech-To-Text and Text-To-Speech services. |
Mel Frequency Cepstral Coefficients(MFCCs);Filterbank Energies;Log Filterbank Energies | Build voice-enabled chatbot services (for example, IVR systems); Classification of audio file transcriptions; Automated Testing of Voice services with Botium |
Statistics | |
GitHub Stars 884 | GitHub Stars 943 |
GitHub Forks 105 | GitHub Forks 58 |
Stacks 1 | Stacks 7 |
Followers 11 | Followers 21 |
Votes 0 | Votes 0 |
Integrations | |

It can be used to complement any regular touch user interface with a real time voice user interface. It offers real time feedback for faster and more intuitive experience that enables end user to recover from possible errors quickly and with no interruptions.

Amazon Polly is a service that turns text into lifelike speech. Polly lets you create applications that talk, enabling you to build entirely new categories of speech-enabled products. Polly is an Amazon AI service that uses advanced deep learning technologies to synthesize speech that sounds like a human voice.

Google Cloud Text-to-Speech enables developers to synthesize natural-sounding speech with 30 voices, available in multiple languages and variants. It applies DeepMind’s groundbreaking research in WaveNet and Google’s powerful neural networks to deliver the highest fidelity possible.

It is a state-of-the-art automatic speech recognition toolkit. It is intended for use by speech recognition researchers and professionals.

It is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

wav2letter++ is a fast open source speech processing toolkit from the Speech Team at Facebook AI Research. It is written entirely in C++ and uses the ArrayFire tensor library and the flashlight machine learning library for maximum efficiency. Our approach is detailed in this arXiv paper.

It is an on-device speech-to-text engine. By processing voice data locally on the device, it offers private, reliable, fully-customizable, and cost-effective audio transcription experiences. It achieves big tech-level accuracy at a fraction of their costs.

It is more than just a fast and accurate audio to text converter. We go beyond audio transcription to help you get the most out of your content.

It is fully-automated software that can turn any text into a natural lifelike voice-over... In just a few clicks. It can accommodate any business and is perfect for creating voice overs for video sales letters, educational videos, marketing videos, animated videos, podcasts, audio books, and much more!

It is a library for advanced Text-to-Speech generation. It’s built on the latest research, was designed to achieve the best trade-off among ease-of-training, speed, and quality. It comes with pre-trained models, tools for measuring dataset quality and is already used in 20+ languages for products and research projects.