Open Source Linux Speech Software

eGuideDog project develops free software for the blind. Currently, we focus on WebSpeech, Ekho TTS and WebAnywhere.

Wrapper for vendors to simplify usage of the Java Speech API (JSR 113). Note that the spec is an untested early access and that there may be changes in the API.

A modular, extensible Hebrew text-to-speech engine tuned for Standard Israeli Hebrew, and associated tools.

Audacity Policial (aka Audacity Police) is an extension of Audacity sound editor that was created to help police and justice investigations based on phone call and environmental recordings, supporting audio analysis and transcription.

Free Open Source VoiceXML editor programmed in Java (Swing). The VoiceXML document is regularly parsed, a tree view is built and syntax errors are reported in a specific table.

QWave: Qt-based waveform display and audio playback class library.

Talkbox is a program wich makes your computer talk "with" you. It has a AI based on ALICE program C and uses Festvial speech engin along with speechd to produce voice synthisis. You input text by typeing there is no support for voice reconition.

GRANULE is a flashcards program based on Leitner cardfile methodology for learning new words. It features long-term memory training capabilities with scheduling, integrated pictures, sound, and full-screen mode.

To provide basic text-to-speech capability on as many platforms and for as many spoken languages as possible by formant synthesis from an International Phonetic Alphabet representation.

Hidden Markov Model based voice models of Austrian German for the Festival speech synthesis system.

See TTS demo at: http://rslp.racai.ro/index.php?page=tts This is an entirely written in JAVA project which includes a set of tools and methods designed to enable Multilingual Text-to-Speech (TTS) synthesis. We currently support English and Romanian but we will soon train more models and make them available for download. If you want to read more about our other NLP and TTS tools check out http://nlptools.racai.ro.

DTW is intended to be a Voice in -> Pictures + Text out program written in java using Sphinx from CMU. This is intended to be useful to people who have good oral/visual literacy skills but poor written literacy skills.

A subtitle agent, which developed on Java, helps to create, modify, and operate subtitle files easily. Also providing Java packages for developing subtitle agents conveniently. Moreover, they're free and open-sourced, based on GPL lisence.

GUI for Festival tts Пользовательский Графический Интерфейс для синтезатора речи Festival ориентированный на русскоговорящий контингент

Sound and speech editor. Sound data analysis and transform tool. Used for speech analysis, labelling and speech synthesis inventory creation.

Intercom is a flexible, configurable voice communication utility.

JeSpeak is a Java library that bridges eSpeak, which is a compact open source software speech synthesizer. JeSpeak uses JNI to make native call to libespeak.

Intended eventually to be a live CD, LinVision allows the blind to use a computer to: 1) Organise books & read aloud. 2) Organise & play music. 3) Teach & test keyboard skills. 4) Write & save or email work. 5) Browse Internet.

The MRCPv2 protocol is designed to allow client devices to control media processing resources, such as speech recognition engines. MRCP4J provides a Java API that encapsulates the MRCPv2 protocol and can be used to implement MRCP clients and/or servers.

Matsig is an object-oriented signal class library (Toolbox in MATLAB lingo) for MATLAB 6.5 and later. It implements a signal class, simplifying operations and manipulations common in audio signal processing and speech processing.

A Simple Nepali Voice Synthesis Project

The Pawn will make it possibly for you to tell the computer exactly what you would like it to do. Fiction. No its reality now. The highly customizable slackware will be the base for Pawn.

PHP-VOX is the Text To Speech(TTS) binding for PHP.

Portable GUI Ogg/Speex/FLAC audio encoder/player that can encode wave file and provides additional functionality such as audiofile tagging, html-album generator, cd-ripping, etc. Targeted to be used on Freebsd, Linux and win32 platforms and the frontends

Regulus is a Prolog-based toolkit for building spoken dialogue systems.