Displaying 1 to 20 from 42 results

tacotron - A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model

  •    Python

We train the model on three different speech datasets. LJ Speech Dataset is recently widely used as a benchmark dataset in the TTS task because it is publicly available. It has 24 hours of reasonable quality samples. Nick's audiobooks are additionally used to see if the model can learn even with less data, variable speech samples. They are 18 hours long. The World English Bible is a public domain update of the American Standard Version of 1901 into modern English. Its original audios are freely available here. Kyubyong split each chapter by verse manually and aligned the segmented audio clips to the text. They are 72 hours in total. You can download them at Kaggle Datasets.

deepvoice3_pytorch - PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

  •    Python

Audio samples are available at https://r9y9.github.io/deepvoice3_pytorch/. NOTE: pretrained models are not compatible to master. To be updated soon.

aeneas - aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

  •    Python

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment). aeneas automatically generates a synchronization map between a list of text fragments and an audio file containing the narration of the text. In computer science this task is known as (automatically computing a) forced alignment.

Talkie - Text-to-speech browser extension button

  •    Javascript

Talkie is a Text-to-speech browser extension button. It lets you listen to the selected text on any part of a page — short snippets or entire news articles. Just highlight what you want to hear read aloud and hit play. Automatically detects the text language per-page, and chooses a voice in the same language to match it. Support is available for Chrome and Firefox.

dc_tts - A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

  •    Python

I implement yet another text-to-speech model, dc-tts, introduced in Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention. My goal, however, is not just replicating the paper. Rather, I'd like to gain insights about various sound projects. I train English models and an Korean model on four different speech datasets.

WP7 Text-to-Speech Tool & Translation Library


Windows Phone Text-to-Speech (wpTTS) produces speech from text strings. wpTTS also provides real-time translation between a select list of languages. (AppID required.)



A simple tray application which will speak incoming Lync instant messages.

node-picotts - PicoTTS wrapper for NodeJS

  •    Javascript

PicoTTS wrapper for NodeJS. PicoTTS is being used by Android and it's extremely lightweight and fast yet produces very natural voices.

amazon-polly-sample - Sample application for Amazon Polly

  •    Python

This app allows you to easily convert any publicly available RSS content into audio Podcasts, so you can listen to your favorite blogs on mobile devices instead of reading them.You will need an AWS account and an RSS feed. Some technical experience is required to setup your own instance of the app, but you don't have to write any code. Once setup, it can be used by anyone using a standard Podcast player.

ivona-node - Ivona Cloud (via Amazon services) client library for Node

  •    Javascript

Node client library for IVONA Speech Cloud API. Yes, this is up-to-date and uses the most recent AWS Signature 4 scheme (thanks to aws4). All you need is your Ivona access and secret (the one only given to you once upon creating it) keys. No current documentation, as the entire extent of the API can be viewed below.

node-tts-api - Simple API to get TTS

  •    CoffeeScript

This is a simple module to access tts-api.com. Enjoy the usage. You can email me at yamil.asusta@upr.edu for any bugs.

spoken-word - Spoken Word

  •    Javascript

Add text-to-speech (TTS) to content, with playback controls, read-along highlighting, multi-lingual support, and settings for rate, pitch, and voice. Add text-to-speech (TTS) to content, with playback controls, read-along highlighting, multi-lingual support, and settings for rate, pitch, and voice.

sonus-electron-boilerplate - Example of sonus running in electron

  •    Javascript

Example of Sonus running in electron for OSX and Linux. What you get: customizable offline hotword detection and streaming recognition for your stand-alone desktop application.

node-ivona - IVONA Text-to-Speech SaaS client library for Node.js

  •    Javascript

ivona is a client library for IVONA Text-to-Speech SaaS written in Node.js. The client automatically handles token authentication therefore the following API calls can be made right away.

node-neospeech - NeoSpeech TTS client library for Node.js

  •    C++

neospeech is a client library for NeoSpeech TTS written in Node.js. Refer to Installing FFmpeg section for more details.

yandex-speech - node.js module for Yandex speech systems (ASR & TTS)

  •    Javascript

node.js module for Yandex speech systems (ASR & TTS)