Debian Accessibility Speech Synthesis packages

Daisy-player is a command-line player for talking books based on the Digital Accessible Information System protocol. It is comparable in functionality, features, and ease of use with commercial players, and has a simple user interface appropriate for Braille terminals.

EFlite is a speech server for Emacspeak and other screen readers that allows them to interface with Festival Lite, a free text-to-speech engine developed at the CMU Speech Center as an off-shoot of Festival.

Due to limitations inherited from its backend, EFlite does only provide support for the English language at the moment.

eSpeak é um software sintetizador de voz para Inglês, e alguns outros idiomas.

eSpeak produz fala em Inglês de boa qualidade. Ele usa um método de síntese diferente de outros motores "texto para fala" (text to speech - TTS) de código aberto, e soa bastante diferente. Ele talvez não seja tão natural ou "suave", mas para alguns a articulação é clara e fácil de se ouvir por longos períodos.

Ele pode ser executado em linha de comando para ditar texto de um arquivo ou da entrada padrão.

• Inclui diferentes Vozes, cujas características podem ser alteradas.
• Pode produzir saída de fala como um arquivo WAV.

• Pode traduzir texto para códigos fonéticos, sendo então adaptado como uma interface para outros motores de síntese de voz.

• Potencial para outras línguas. Mais de 40 línguas inclusas.

• Tamanho compacto. O programa e seus dados totalizam 350 kbytes.
• Escritos em C++.

Flite is a small fast run-time speech synthesis engine. It is the latest addition to the suite of free software synthesis tools including University of Edinburgh's Festival Speech Synthesis System and Carnegie Mellon University's FestVox project, tools, scripts and documentation for building synthetic voices. However, flite itself does not require either of these systems to run.

It currently only supports the English and Indic languages.

This package contains the executables and documentation.

Speech Dispatcher fornece uma camada independente de dispositivo para síntese de voz. Ele suporta, como mecanismo, diferentes sintetizadores de voz em software e hardware e fornece uma camada genérica para síntese de voz e reprodução de dados PCM através desses diferentes mecanismos para aplicativos.

Vários conceitos de alto nível como enfileiramento versus voz interrompida e configurações do usuário da aplicação específica são implementados de maneira independente do dispositivo, portanto, liberando o programador do aplicativo de ter que, mais uma vez, reinventar a roda.

Este pacote contém o próprio Speech Dispatcher.

This package contains the various highly useful utility programs that use and accompany the Edinburgh Speech Tools Library. Audio software and some basic signal processing software is included in this package.

The following programs are available: na_play: generic playback program for use with net_audio and CSTR ao. ch_wave: Waveform file conversion program. ch_lab: label file conversion program. ch_track: Track file conversion program. wagon: a CART tree build and test program

See /usr/share/doc/speech-tools/README for detail list of programs available.

This package provides Russian support to Festival speech synthesis system.

FreeTTS is a speech synthesis system written entirely in the Java(TM) programming language. It is based upon Flite, a small run-time speech synthesis engine developed at Carnegie Mellon University. Flite in turn is derived from the Festival Speech Synthesis System from the University of Edinburgh and the FestVox project from Carnegie Mellon University.

Gespeaker is a GTK+ frontend for eSpeak and mbrola. It allows one to play a text in many languages with settings for voice, pitch, volume, speed and word gap.

Since version 0.6 it can use mbrola package and voices to obtain a more realistic text reading experience.

Recite é um programa para executar síntese de voz. A qualidade do som produzido não é excessivamente boa, mas ela deve ser adequada para relatar verbalmente as mensagens de erro ocasionais.

Ao receber algum texto em Inglês, recite irá convertê-lo em uma série de fonemas, então converterá esses fonemas em uma sequência de parâmetros de aparelho vocal, e então sintetizará o som que um aparelho vocal faria para dizer a sentença. Recite pode realizar um subconjunto dessas operações, então ele pode ser usado para converter texto em fonemas, ou para produzir uma expressão vocal baseada em parâmetros de aparelho vocal computados por outro programa.

Fala a hora atual através da sua placa de som. Requer que você tenha um dispositivo de saída de som disponível.

Sonic is a very simple utility that reads and writes wav files, and speeds them up or slows them down, with low distortion. The key new feature in Sonic versus other libraries is very high quality at speed up factors well over 2X.

Speech Dispatcher provides a device independent layer for speech synthesis. It supports various software and hardware speech synthesizers as backends and provides a generic layer for synthesizing speech and playing back PCM data via those different backends to applications.

Various high level concepts like enqueueing vs. interrupting speech and application specific user configurations are implemented in a device independent way, therefore freeing the application programmer from having to yet again reinvent the wheel.

This package contains dependencies on packages necessary for running Speech Dispatcher with Festival.

This Text-To-Speech (TTS) engine speaks French; a preliminary English support is also offered. The engine uses context-sensitive rules to produce phonemes from the text. It relies on MBROLA to generate actual audio output from the phonemes. The TTS engine is implemented using the Python programming language.

The upstream authors have come up with this TTS to try and meet their own needs as blind users. It's designed to be plugged as output to some screen-review software, firstly with BRLTTY. They favor speed and intelligibility over perfect pronunciation. Cicero is aimed to have a quick response time, the ability to quickly shut-up and skip to another utterance, intelligibility where it counts (not perfect pronunciation), the ability to track speech progression, relative simplicity (hackability) and relative small code size.

The GNOME Speech library gives a simple yet general API for programs to convert text into speech, as well as speech input.

This package provides the source code required to compile a driver for the commercial DECtalk software speech synthesis engine and voices from Fonix (http://www.fonix.com/). Upon installation, it will automatically attempt to compile and install the dectalk-synthesis-driver binary required to use GNOME Speech with dectalk.

This package is only useful if the dectalk engine is already installed on the system.

The GNOME Speech library gives a simple yet general API for programs to convert text into speech, as well as speech input.

This package provides the source code required to compile a driver for the commercial IBMTTS speech synthesis engine available from http://ttsynth.com/. Upon installation, it will automatically attempt to compile and install the voiavoice-synthesis-driver binary required to use GNOME Speech with IBMTTS.

This package is only useful if the IBMTTS (TTSynth) engine is already installed on the system.

The GNOME Speech library gives a simple yet general API for programs to convert text into speech, as well as speech input.

This package provides the source code required to compile a driver for the commercial swift speech synthesis engine and voices from Cepstral (http://www.cepstral.com/). Upon installation, it will automatically attempt to compile and install the swift-synthesis-driver binary required to use GNOME Speech with swift.

This package is only useful if the swift engine is already installed on the system.

The SVOX Pico engine is a software speech synthesizer for German, English (GB and US), Spanish, French and Italian.

SVOX produces a clear and distinct speech output made possible by the use of Hidden Markov Model (HMM) algorithms.

This package contains binary files including pico2wave.

Mbrola is Thierry Dutoit's phonemizer for multilingual speech synthesis. The various diphone databases are distributed on separate packages, but they must be used with and only with Mbrola because of license matters. Read the copyright for details.

Mbrola itself doesn't provide full TTS. It is a speech synthesizer based on the concatenation of diphones. It takes a list of phonemes as input, together with prosodic information (duration of phonemes and a piecewise linear description of pitch), and produces speech samples on 16 bits (linear), at the sampling frequency of the diphone database.

Use Mbrola along with Freephone, cicero or espeak to have a complete text-to-speech in English.