Debian Accessibility Project
Summary
Speech Synthesis
Debian Accessibility Speech Synthesis

This metapackage will install packages which are useful for Speech Synthesis and related APIs or applications.

Description

For a better overview of the project's availability as a Debian package, each head row has a color code according to this scheme:

If you discover a project which looks like a good candidate for Debian Accessibility to you, or if you have prepared an unofficial Debian package, please do not hesitate to send a description of that project to the Debian Accessibility mailing list

Links to other tasks

Debian Accessibility Speech Synthesis packages

Official Debian packages with high relevance

daisy-player
player for DAISY Digital Talking Books
Versions of package daisy-player
ReleaseVersionArchitectures
buster11.6.2.1-2amd64,arm64,armhf,i386
stretch10.3-3amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
trixie13.0-4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,s390x
bookworm13.0-4amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bullseye12.1-1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
sid13.0-4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
jessie9.0.0-1amd64,armel,armhf,i386
Debtags of package daisy-player:
interfacetext-mode
roleprogram
scopeutility
soundplayer
uitoolkitncurses
uselearning, playing
works-withaudio
works-with-formatmp3
Popcon: 4 users (2 upd.)*
Versions and Archs
License: DFSG free
Git

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.

Screenshots of package daisy-player
eflite
Festival-Lite ベースの emacspeak 音声サーバ
Versions of package eflite
ReleaseVersionArchitectures
bullseye0.4.1-12amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bookworm0.4.1-13amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
trixie0.4.1-13amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
sid0.4.1-13amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
jessie0.4.1-6amd64,armel,armhf,i386
stretch0.4.1-8amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
buster0.4.1-9amd64,arm64,armhf,i386
Debtags of package eflite:
accessibilityspeech
roleplugin
suiteemacs
works-withaudio
Popcon: 5 users (1 upd.)*
Versions and Archs
License: DFSG free
Git

EFlite は Emacspeak および他のスクリーンリーダ向け音声サーバで、CMU Speech Center にて Festival の後継として開発されているフリーのテキスト読み上げエン ジンである Festival Lite と連携できます。

バックエンドの制限により、現在のところ EFlite は英語にのみ対応しています。

espeak
多言語ソフトウェア発話シンセサイザ
Versions of package espeak
ReleaseVersionArchitectures
buster1.48.04+dfsg-7+deb10u1amd64,arm64,armhf,i386
bullseye1.48.15+dfsg-2amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bookworm1.48.15+dfsg-3amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
sid1.48.15+dfsg-3amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
trixie1.48.15+dfsg-3amd64,arm64,armel,armhf,i386,mips64el,ppc64el,s390x
jessie1.48.04+dfsg-1amd64,armel,armhf,i386
stretch1.48.04+dfsg-5amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
Debtags of package espeak:
interfacecommandline
roleprogram
soundspeech
works-withaudio
Popcon: 258 users (113 upd.)*
Versions and Archs
License: DFSG free
Git

eSpeak は、英語および他の言語向けのソフトウェア音声合成プログラムです。

eSpeak は、高品質な英語音声を生成します。オープンソースの他のテキスト音声合成 (text to speech - TTS) エンジンとは別の合成手法を使っているため、まったく 異なる音声になります。もしかしたらあまり自然でなかったり、 "滑らか" でないかもしれませんが、発音がはっきりしていて長時間聞きやすいと 感じる方もいます。

コマンドラインプログラムとして実行し、ファイルまたは標準入力からテキストを 与えて発声できます。

  • 様々な声色が含まれます。声の特性は変更できます。
  • 発話結果を WAV ファイルとして出力できます。
  • テキストから音素符号に変換できます。他の音声合成エンジンへの フロントエンドとして組み合わせて使えます。
  • 他の言語への拡張可能性があります。40 以上の言語が含まれます。
  • コンパクトなサイズ。プログラムとデータを含めて約 350 k バイト。
  • C++ で書かれています。
flite
小型のランタイム音声合成エンジン
Versions of package flite
ReleaseVersionArchitectures
bullseye2.2-2amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
jessie1.4-release-12amd64,armel,armhf,i386
sid2.2-6amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
stretch2.0.0-release-3amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
trixie2.2-6amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
bookworm2.2-5amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
buster2.1-release-3amd64,arm64,armhf,i386
Debtags of package flite:
accessibilityspeech
interfacecommandline
roleprogram
scopeutility
works-withaudio
Popcon: 31 users (74 upd.)*
Versions and Archs
License: DFSG free
Git

Flite は小型で速いランタイム音声合成エンジンです。エジンバラ大学の Festival Speech Synthesis System やカーネギーメロン大学の FestVox プロジェクトをはじ めとする、フリーソフトウェアによる合成ツールスイートの新製品で、合成音声を 作るためのツール、スクリプトおよびドキュメントです。ただ、flite 自体は実行 にそのいずれかのシステムを必要とするわけではありません。

現状、英語とインド語派のみをサポートします。

このパッケージには実行ファイルとドキュメントが含まれます。

speech-dispatcher
音声合成プログラムへの共通インタフェース
Versions of package speech-dispatcher
ReleaseVersionArchitectures
bookworm0.11.4-2amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
experimental0.12.0~rc3-1amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
sid0.11.5-4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
trixie0.11.5-4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,s390x
bookworm-backports0.11.5-4~bpo12+1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bullseye-backports0.11.4-2~bpo11+1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bullseye0.10.2-2+deb11u2amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
buster0.9.0-5+deb10u1amd64,arm64,armhf,i386
stretch0.8.6-4+deb9u1amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
jessie0.8-7amd64,armel,armhf,i386
Debtags of package speech-dispatcher:
accessibilityspeech
interfacedaemon
networkserver
roleprogram
works-withaudio
Popcon: 79338 users (13023 upd.)*
Versions and Archs
License: DFSG free
Git

Speech Dispatcher は、音声合成のためのデバイス独立レイヤを提供します。 バックエンドとしてさまざまなソフトウェアとハードウェアの音声合成プログラムを サポートし、その異なるバックエンドを介して音声合成し PCM データを再生して アプリケーションに返すための汎用レイヤを提供します。

音声のエンキューや中断、アプリケーション固有のユーザー設定といった さまざまな高レベルの概念がデバイスに依存しない方法で実装されているので、 アプリケーションプログラマは車輪の再設計をする必要がありません。

このパッケージには Speech Dispatcher 自体が含まれています。

speech-tools
Edinburgh Speech Tools - user binaries
Versions of package speech-tools
ReleaseVersionArchitectures
bookworm2.5.0-13amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
sid2.5.0-13amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
bullseye2.5.0-11amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
buster2.5.0-5amd64,arm64,armhf,i386
stretch2.4~release-5amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
jessie2.1~release-8amd64,armel,armhf,i386
trixie2.5.0-13amd64,arm64,armel,armhf,i386,mips64el,ppc64el,s390x
Debtags of package speech-tools:
accessibilityspeech
fieldlinguistics
interfacecommandline, text-mode
roleprogram
scopeutility
uitoolkitncurses
useplaying
Popcon: 12 users (1 upd.)*
Versions and Archs
License: DFSG free
Git

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.

Official Debian packages with lower relevance

festvox-ru
Russian male speaker for Festival
Versions of package festvox-ru
ReleaseVersionArchitectures
bookworm0.5+dfsg-6all
trixie0.5+dfsg-6all
sid0.5+dfsg-6all
jessie0.5+dfsg-3all
stretch0.5+dfsg-3all
buster0.5+dfsg-4all
bullseye0.5+dfsg-5all
Debtags of package festvox-ru:
accessibilityspeech
culturerussian
roleapp-data
soundspeech
Popcon: 0 users (0 upd.)*
Versions and Archs
License: DFSG free
Git

This package provides Russian support to Festival speech synthesis system.

freetts
音声合成システム
Maintainer: Bdale Garbee
Versions of package freetts
ReleaseVersionArchitectures
stretch1.2.2-3all
sid1.2.2-7all
trixie1.2.2-7all
bookworm1.2.2-7all
bullseye1.2.2-7all
buster1.2.2-6all
jessie1.2.2-3all
Debtags of package freetts:
accessibilityspeech
roleprogram
Popcon: 10 users (1 upd.)*
Versions and Archs
License: DFSG free
Git

FreeTTS は全て Java(TM) プログラミング言語で書かれた音声合成システムです。 カーネギー・メロン大学により開発された小規模なランタイム音声合成エンジン、 Flite をベースにしています。Flite は、エジンバラ大学の Festival Speech Synthesis System と、カーネギー・メロン大学の FestVox プロジェクトから 派生したものです。

gespeaker
GTK+ front-end for eSpeak and mbrola
Maintainer: Fabio Castelli
Versions of package gespeaker
ReleaseVersionArchitectures
stretch0.8.6-1all
buster0.8.6-1all
jessie0.8.5-1all
Debtags of package gespeaker:
accessibilityspeech
interfacex11
roleprogram
scopeapplication
soundspeech
uitoolkitgtk
useentertaining
works-withaudio, text
x11application
Popcon: 3 users (0 upd.)*
Versions and Archs
License: DFSG free
Svn

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
English text speech synthesizer
Versions of package recite
ReleaseVersionArchitectures
jessie1.0-8.2amd64,armel,armhf,i386
Debtags of package recite:
accessibilityspeech
interfacecommandline
roleprogram
scopeutility
works-withtext
Popcon: 0 users (0 upd.)*
Versions and Archs
License: DFSG free

Recite is a program to do speech synthesis. The quality of sound produced is not terribly good, but it should be adequate for reporting the occasional error message verbally.

Given some English text, recite will convert it to a series of phonemes, then convert the phonemes to a sequence of vocal tract parameters, and then synthesise the sound a vocal tract would make to say the sentence. Recite can perform a subset of these operations, so it can be used to convert text into phonemes, or to produce an utterance based on vocal tract parameters computed by another program.

saytime
サウンドカードから現在の時間を発音
Maintainer: Holger Levsen
Versions of package saytime
ReleaseVersionArchitectures
bookworm1.0-35amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
buster1.0-30amd64,arm64,armhf,i386
trixie1.0-35amd64,arm64,armel,armhf,i386,mips64el,ppc64el,s390x
jessie1.0-26amd64,armel,armhf,i386
sid1.0-35amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
stretch1.0-27amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
bullseye1.0-34amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
Debtags of package saytime:
accessibilityspeech
interfacecommandline
roleprogram
scopeutility
soundplayer
usetimekeeping
works-withaudio
Popcon: 4 users (1 upd.)*
Versions and Archs
License: DFSG free
Git

現在の時間をサウンドカードを通じて発音します。音声出力可能なデバイスが 必要です。

Screenshots of package saytime
sonic
音声を速くしたり遅くしたりするシンプルなユーティリティ
Versions of package sonic
ReleaseVersionArchitectures
sid0.2.0-13amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
buster0.2.0-7amd64,arm64,armhf,i386
bullseye0.2.0-10amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bookworm0.2.0-12amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
trixie0.2.0-13amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
stretch0.2.0-4amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
jessie0.1.17-1.1amd64,armel,armhf,i386
Debtags of package sonic:
roleprogram
scopeutility
useediting
works-withaudio
Popcon: 5 users (0 upd.)*
Versions and Archs
License: DFSG free
Git

Sonic は wav ファイルを読み書きするとてもシンプルな ユーティリティで、小さい歪みで速くしたり遅くしたりします。 他のライブラリに対して Sonic の新しい重要な特徴は 2 倍を超える速さでのとても高い品質です。

Screenshots of package sonic
speech-dispatcher-festival
Festival support for Speech Dispatcher
Versions of package speech-dispatcher-festival
ReleaseVersionArchitectures
bullseye0.10.2-2+deb11u2amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bullseye-backports0.11.4-2~bpo11+1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bookworm0.11.4-2amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bookworm-backports0.11.5-4~bpo12+1amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
trixie0.11.5-4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,s390x
sid0.11.5-4amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
jessie0.8-7amd64,armel,armhf,i386
stretch0.8.6-4+deb9u1amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
buster0.9.0-5+deb10u1amd64,arm64,armhf,i386
experimental0.12.0~rc3-1amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
Debtags of package speech-dispatcher-festival:
accessibilityspeech
rolemetapackage
works-withaudio
Popcon: 1 users (0 upd.)*
Versions and Archs
License: DFSG free
Git

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.

Debian packages in contrib or non-free

cicero
French and English Text-To-Speech for MBROLA
Versions of package cicero
ReleaseVersionArchitectures
buster0.7.2-4 (contrib)all
stretch0.7.2-3 (contrib)all
jessie0.7.2-3 (contrib)all
Debtags of package cicero:
accessibilityspeech
culturebritish, french
roleprogram
Popcon: 5 users (0 upd.)*
Versions and Archs
License: DFSG free, but needs non-free components
Git

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.

gnome-speech-dectalk
GNOME text-to-speech library (Fonix DECtalk engine support)
Versions of package gnome-speech-dectalk
ReleaseVersionArchitectures
jessie0.4.25-5 (contrib)i386
stretch0.4.25-6 (contrib)i386
Debtags of package gnome-speech-dectalk:
accessibilityspeech
Popcon: 0 users (0 upd.)*
Versions and Archs
License: DFSG free, but needs non-free components
Svn

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.

gnome-speech-ibmtts
GNOME text-to-speech library (IBMTTS engine support)
Versions of package gnome-speech-ibmtts
ReleaseVersionArchitectures
stretch0.4.25-6 (contrib)i386
jessie0.4.25-5 (contrib)i386
Debtags of package gnome-speech-ibmtts:
accessibilityspeech
Popcon: 0 users (0 upd.)*
Versions and Archs
License: DFSG free, but needs non-free components
Svn

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.

gnome-speech-swift
GNOME text-to-speech library (Cepstral swift engine support)
Versions of package gnome-speech-swift
ReleaseVersionArchitectures
stretch0.4.25-6 (contrib)amd64,i386
jessie0.4.25-5 (contrib)amd64,i386
Debtags of package gnome-speech-swift:
accessibilityspeech
Popcon: 0 users (0 upd.)*
Versions and Archs
License: DFSG free, but needs non-free components
Svn

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.

libttspico-utils
Small Footprint TTS (binaries)
Versions of package libttspico-utils
ReleaseVersionArchitectures
stretch1.0+git20130326-5 (non-free)amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
bullseye1.0+git20130326-11 (non-free)amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
buster1.0+git20130326-9 (non-free)amd64,arm64,armhf,i386
trixie1.0+git20130326-14.1 (non-free)amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
sid1.0+git20130326-14.1 (non-free)amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
bookworm1.0+git20130326-13 (non-free)amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
jessie1.0+git20130326-3 (non-free)amd64,armel,armhf,i386
Debtags of package libttspico-utils:
roleprogram
Popcon: 44 users (20 upd.)*
Versions and Archs
License: non-free
Git

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
Multilingual software speech synthesizer
Maintainer: Samuel Thibault
Versions of package mbrola
ReleaseVersionArchitectures
stretch3.01h+2-3 (non-free)amd64,armel,armhf,i386
jessie3.01h+1-2 (non-free)amd64,armel,i386
buster3.02b+dfsg-4 (contrib)amd64,arm64,armhf,i386
buster-backports3.3+dfsg-4+deb11u1~bpo10+1 (contrib)amd64,arm64,armel,armhf,i386,mips,mips64el,mipsel,ppc64el,s390x
bullseye3.3+dfsg-4+deb11u1 (contrib)amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
bookworm3.3+dfsg-9 (contrib)amd64,arm64,armel,armhf,i386,mips64el,mipsel,ppc64el,s390x
trixie3.3+dfsg-9 (contrib)amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
sid3.3+dfsg-9 (contrib)amd64,arm64,armel,armhf,i386,mips64el,ppc64el,riscv64,s390x
Debtags of package mbrola:
roleprogram
soundspeech
Popcon: 179 users (11 upd.)*
Versions and Archs
License: DFSG free, but needs non-free components
Git

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.

*Popularitycontest results: number of people who use this package regularly (number of people who upgraded this package recently) out of 237615