Acapela tts for windows

Acapela TTS for Windows Server

Software Development toolkit designed to give a voice to your telephony and server-based services on Windows Server.

Deliver 24/7 real-time vocal information to your customers

Developer benefits

Acapela TTS for Windows Server targets telecom and server-based applications, from single host solutions to distributed architectures. Scalable and client server architecture.

Market apps and services

For voice assistants, IoT, contact centers, IVR, CRM, notification systems, ATM vocal assistants, passenger information, navigation, web-reading, e-learning, digital learning, audio books, etc.

Key benefits

Client-server Architecture
Designed for network telecom applications, from single host solutions to distributed architectures.

High Density performance
Efficient TTS server, offering lower hardware investment with maximum efficiency.

Scalability and multi-processor
Multi-channel engine, optimized for mono and multi-processor systems

Reliable and manageable
Designed to run 24/7, remotely administrable and load balanced to ensure perfect availability of TTS resources for applications.

Standard Compliance
Can be used as a TTS resource in any Voice XML platform with the IETF MRCP v1 and MRCP v2 protocol layer and the support of W3C SSML.

About MRCP

The Media Resource Control Protocol (MRCP) is an Internet Engineering Task Force (IETF) specification that describes a standard interface for media processing resources providing capabilities such as automatic speech recognition (ASR), speech synthesis (text to speech or TTS), speaker identification and speaker verification (SI/SV). The key benefit of this technology is that it allows VoiceXML browsers to inter-operate with third party ASR, TTS, and SI/SV servers using an open, standardized protocol. Interoperability of this nature allows a given VoiceXML solution to be comprised of components from multiple vendors, benefiting technology providers by adding value to their products, while placing greater flexibility and choice in the hands of customers.

About Acapela MRCP add-on 2.400
This new architecture is based on the award winning UniMRCP open source project. Acapela MRCP add-on 2.0 is a plugin to the UniMRCP server stack which implements MRCP 2.0 and 1.0 protocols.

Available for Windows Server 2008/2008 R2/2016 and Linux RHEL ES 6, and 7 Debian 6 & above, Ubuntu 12 & above.

Technical Specifications

Pricing info

The Acapela TTS for Windows Server consists of two parts:

Источник

Голосовой модуль Acapela Alyona (Русский) HQ TTS (2009) скачать бесплатно

Название: Acapela Alyona (Русский)
Версия: HQ TTS
Дата выхода: 2009
Разработчик: Acapela-Group
Платформа: PC x86

Язык интерфейса: Английский
Перевод: Не требуется
Таблетка: Присутствует

Назначение: «Голос для чтения электронных книг»

Системные требования: Windows XP, Vista, 7

Популярные раздачи за последние 48 часов :

Windows 10 20H2 (19042.870) x64 Home + Pro + Enterprise (3in1) by Brux v.03.2021 [Ru]

Windows 10 20H2 (x64) 16in1 +/- Office 2019 by Eagle123 (03.2021) [Ru/En]

Windows 10 Home 20H2 Build 19042.867 x64 ru by SanLex (edition 2021-03-28) [Ru]

Advanced SystemCare Pro 14.3.0.240 (2021) PC

MInstAll v.21.03.2021 By Andreyonohov (ISO) [Ru]

TV+ HD v1.1.15.22 AdFree + clone (2021) Android

IObit Driver Booster PRO 8.4.0.420 (2021) PC | RePack & Portable by TryRooM

Wise Care 365 Pro 5.6.5 Build 564 (2021) PC | + Portable

Источник

Virtual Speaker

Easily voice animate your content, produce your voice recordings from your PC, 24/7.

Easily produce your High Quality audio files, in over 30 languages

Through a user-friendly interface, operators can easily produce the voice files they need. Free from speaker and recording studio logistics constraints. Using one of Acapela’s standard voices or one that is custom made.

The power and naturalness of Acapela voices at your fingertips. You provide the texts and choose the voice, Virtual Speaker will immediately create audio files with voice recordings, using the high quality, multilingual, text to speech from Acapela Group.

Developer benefits

Based on the latest and highest quality text to speech technology by Acapela Group, Virtual Speaker can instantly convert any text into sound with a natural and pleasant voice using the language, the voice and the output file format that fits your needs.

All recordings made with Virtual Speaker originate from a simple text file containing the text to be spoken. Recording a new message or updating an existing message is as simple as editing a text file and pressing the record button.

Market apps and services

IVR, e learning, public announcements, passenger information and much more.

Key benefits

Voices & languages
More than 120 voices available in the standard portfolio. Some of the voices provide additional emotional variants (sad/happy) and attitudes (shouting/whispering).

Friendly interface
With powerful features like search and replace, colour syntax, intuitive menus and buttons, real time highlighting of texts synthesized, Virtual Speaker is a powerful and easy to handle editor.

Voice properties
Adjustable voice settings such as speaking rate, voice tone, volume and pause length for punctuation.

Audio file formats
choice of audio output formats: 8 kHz, 11 kHz, 16 kHz, 22 kHz, 44 kHz, PCM, A-law, µ-law, vox, MP3.

Technical Specifications

Pricing

Virtual Speaker is based on a limited time volume (pre-paid packages of speech hours), adapted to your project and the text volumes you need to generate.
First pre-paid package (5 hours): 1500 euros.

Tutorials

Getting started and how to convert a text file into audio

Convert several files at once using Batch mode

How to use the Change pronunciation feature

Frequently Asked Questions

1. What is Virtual Speaker?

Virtual Speaker is a stand-alone application that allows you to create sound files from text files using text to speech.

2. What is the difference between Virtual Speaker and the developer SDKs?

The SDKs are typically integrated and redistributed with some other software, while Virtual Speaker is a stand-alone solution that is part of our off-the-shelf products and ready to use with no particular technical knowledge.

3. How do I purchase Virtual Speaker?

Use the Contact link on this website and send us a description of what you want to achieve and an estimation of the volume of audio that you plan to generate, and we’ll get back to you with more information.

4. I only need to create a few sound files right now, what should I do?

We also have a cloud application called acapela-box that allows you to purchase and generate a small number of audios immediately, directly in the browser.

5. What is the pricing model of Virtual Speaker?

While the application is free, you pay for the amount of audio that you want to generate, by purchasing pre-paid packages of time and using it until your time credit is exhausted or you decide to renew it.

If you purchase a package of 5 hours of time credit and then you create audio files lasting for a total of 45 minutes, you will have 4 hours and 15 minutes left on your account.

The amount of time purchased can be used with any language and voice.

6. Can I change the way a sentence is pronounced by Virtual Speaker?

There are different ways to control and refine the way the TTS will read your input. For complete information please visit the TTS optimization page.

Источник

Acapela tts for windows

Acapela TTS для Android была разработана для Android устройств с высоким качеством синтеза речи специально адаптированного для удовлетворения своих потребностей.

Пользователи Android теперь могут легко добавить вокальные измерение, на многих языках, для всех своих приложений.

Простая интеграция голоса, интуитивно понятный интерфейс
Очень естественный и приятный голос
Многоязычность: 25 Языков
Выбор голосов: 51 голосов
Android Market Совместимые бизнес модели
Acapela для Android была разработана как для «мобильной» программной среды, так и для Java программистов
Благодаря высокому API Level написаны на Java, разработчики смогут быстро и легко интегрировать синтез речи в свое приложение для Android.
Аудио интеграции позволяют пользователям эффективно работать с музыкальными приложениями.

Компанией Acapela Group под операционную систему Android были портированы несколько десятков её синтезаторов речи, среди которых есть и широко известный русский голос Алёна. В целом по качеству синтеза речи данное коммерческое решение находится на довольно высоком уровне, но продукт не лишён и ряда недостатков, хотя, ради справедливости, стоит отметить, что на момент написания обзора он имеет статус beta.

Во-первых, весь движок крайне нестабилен и склонен к ошибкам на всех поддерживающихся версиях Android, после которых его приходится перезапускать.

Во-вторых, у Алёны наблюдается распространённая ошибка с отсутствием произношения отдельно стоящих русских беззвучных букв, таких как мягкий и твёрдый знаки.

В-третьих, голос склонен к проглатыванию окончаний фраз, особенно на границе кириллического и латинского текстов, что можно заметить в вышеприведённом примере.

Из положительных особенностей можно выделить то, что это высококачественный голос, который одновременно с этим подходит не только для разовых задач по озвучиванию текста, но и постоянной работы в программах экранного доступа, так как обладает более быстрым откликом чем движки SVOX и не имеет их проблем с чтением отдельно стоящих латинских букв.

Чтение текста, написанного латинскими буквами, осуществляется по правилам английского языка, хотя с произношением, крайне далёким от правильного.

Максимальная скорость Алёны не очень велика, поэтому любители быстрой работы, скорей всего, будут разочарованы.

Чтобы приступить к работе, сначала из Play Market следует скачать общий движок Acapela TTS Voices, в меню которого следует выбрать интересующий голос. Далее в открывшемся меню нажать на кнопку «Buy» и пройти стандартную процедуру покупки, после чего снова открыть меню этого голоса и подгрузить синтезатор, нажав на кнопку «Download».

Русский голос АПК будет? Для ББ давно уже есть
Говорят глючит, и функционал не на высоте, но качество изумительное.

Сводная таблица существующих русскоязычных синтезаторов речи под Android OS, в которой отражены такие характеристики как качество голоса, применяемые правила чтения латинского текста и максимальная скорость речи.

Синтезатор Качество голоса Чтение латиницы Максимальная скорость речи

Acapela TTS Voices Очень высокое по правилам английского языка Средняя
Captin TTS Engine Низкое По правилам латыни Высокая
eSpeak TTS Очень низкое По правилам английского языка Низкая
Milena из Mobile Accessibility RU Высокое По правилам английского языка Высокая
SVOX Classic TTS Высокое По правилам латыни с искажениями Средняя
TTS Online Высокое По правилам латыни с искажениями Очень низкая

Источник

Voice Tuning

Fine-tune the voice output, add voice smileys, sounds, exclamations and more to breathe life into your message!

Optimize voice output with advanced features

While the main technology is Text-To-Speech (TTS), which converts any written text into an audio result using pleasant and natural HQ voices, other technologies such as Concept To Speech can also be used to optimize the audio result.

A wide palette of features is available to optimize the result of the vocalization.

Here are some examples of fine-tuning that can be easily done.

Phonetic Tags

Nestle is pronounced \prn= n E1 s l EI \ when you’re talking about the Swiss brand.

Speed Tag

You can change \rspd=60\ the speed of the voice.

Voice Shaping Tag

You can make the voice \vct=90\ seem older, \vct=100\ or if you like, \vct=110\ younger as well.

Speed Tag + VCT tag

The speed tag can come in handy, as the \vct=110\ higher pitch increases the speed, so we can \rspd=80\ counter that effect using the speed tag.

Spelling Tag

The spelling tag will say every single \rms=1\ letter \rms=0\ in the word.

Word by Word Tag

The \rmw=1\ word by word \rmw=0\ tag speaks for itself.

Pause Tag

Sometimes a short pause \pau=300\can improve the voice output

Alternative Selection Tag

You can change the intonation of a word if you think it doesn’t \sel=alt\ sound right.

Audio Tag

You can insert sounds, like, “Sending email to John” \aud=“pathway+filename”\

Voice switch tag

“You have a new message from John Smith. Do you want Rod to read it?

\vce=speaker=Rod\ Hey Dave, Really Sorry, but I need to cancel our meeting this afternoon. I’ll call you later to reschedule. Cheers, John

\vce=speaker=Lily\ Would you like to respond?”

Exclamations

Most of our voices include exclamations like: “Please try again!” Or “Goodbye!”

Voice smileys

Expressive voices

A few of our voices come with additional emotional states, like sadness, or happiness.

For example, my friend Will, can be quite emotional. \vce=speaker=Will\

Hello, My name is Will. \vce=speaker=Will-Sad\

Sometimes I get a little bit down. #CRY01# \vce=speaker=Will-Happy\

But I can also be the life of the party! #LAUGH03#

Frequently Asked Questions

1. How can I add Pauses to finetune intonation and rhythm of the generated output?

An efficient way to improve the output of a TTS is to tune your text with pauses in order to modify the intonation and/or the rhythm of the generated output.

Let’s take the following example:

You wish to talk with a counselor concerning dental, optical or hospital reimbursements, press 2.

Pauses can be inserted in different ways:

The first one is simply the use of punctuation marks. This will automatically include pauses where you put a punctuation mark.

You wish to talk with a counselor, concerning dental, optical, or hospital reimbursements, press 2.

A potential problem of punctuation marks is that the duration of the pause could be too long. Another way is to insert a \pau=XXXX\ tag instead of a punctuation.

You wish to talk with a counselor \pau=100\ concerning dental, optical \pau=50\ or hospital reimbursements, press 2.

Punctuation marks not only introduce a pause but they also locally change the intonation of the sentence. A comma causes a rising intonation, a full stop a downward one.

You wish to talk with a counselor \pau=100\, concerning dental, optical or hospital reimbursements, press 2.

You wish to talk with a counselor \pau=100\. concerning dental, optical or hospital reimbursements, press 2.

2. How can I combine speed and pauses tags to make the important information stand out?

When you create a message with a TTS, some parts of the message contain the relevant information that has to be understood. The relative speed tag (\rspd=XXX\) combined with a pause tag (\pau=XXX\) is a good way to make the important information stand out.

Please call 911 monday through friday from 9 AM to 8 PM.

Please \pau=200\ \rspd=80\ call 911 \rspd=100\ \pau=200\ monday through friday from 9 AM to 8 PM.

Please \pau=200\ \rspd=80\ call 911 \rspd=100\ \pau=200\ monday through friday \pau=300\ from 9 AM to 8 PM.

When you use the \rspd tag, don’t forget to close it when it’s no longer needed. To close it use \rspd=100\.

3. How can I use alternative selection tags to finetune the default output according to my expectations?

When the default output of the TTS does not completely match your expectations, you can get alternative outputs by using the alternative selection tag. This gives you the opportunity to get different output for the same words, group of words or sentences. This tag has to be used before each word you would like to get in a different way.

Please hold on for more information.

Please hold on for more \sel=alt2\ information.

\sel=alt1\ Please hold on for more \sel=alt2\ information.

\sel=alt20\ Please hold \sel=alt20\ on for more \sel=alt20\ information.

4. How can I make sure I am using the right format (for hours, date, etc.)?

An important thing to keep in mind when you are using a TTS system is to keep in mind the formats that are accepted by the system for different kinds of information like hours, date, numbers … Those can be found in the language manual.

Here are some examples of time formats: Time

5. How can I use the pronunciation editor to create a specific entry of a word such as a proper name?

A typical issue you meet when using TTS is the wrong pronunciation of a word.

Most of the time this occurs on proper names. Indeed, proper names often do not follow standard pronunciation rules.

The best way to solve this kind of problem is to use the pronunciation editor and to create an entry in the user lexicon with the proper name and the appropriate phonetic transcription.

A phonetic tag could also be used if the pronunciation needs to be changed locally only. The different phonetic alphabets can be found in the language manual.

6. How can I use alternative transcriptions – allophone- for full satisfaction?

Sometimes the official transcription of a word does not give full satisfaction. Using alternative transcriptions constructed with the use of ‘allophones’ can be helpful.

Here is a set of examples of phoneme replacements for American English.

Normally, /t/, /p/, /k/ are aspirated if followed by an accented vowel. This is not always the case but forcing aspiration can change the pronunciation.

They \prx= aU t_h w EI1\ you.

The hurricane uprooted the trees.

The hurricane \prx= V p_h r u1 t @ d\ the trees.

The democrats voted today.

The \prx= d E1 m @ k_h r < t s\ voted today.

“Flapping” is a reduction of /t/ frequent in American English, mainly between stressed and unstressed vowels. It can be changed to a /t/ (sounds a bit more British).

The city comes to life.

The \prx= s I1 (t) i\ comes to life.

A /t/ in American English can also be “swallowed” into a glottal stop. Which in turn can be replaced by a flap.

Clinton was president of the United States.

\prx= k l I1 n t @ n\ was president of the United States.

Climb up the mountaintop.

Climb up the \prx= m aU1 n 4 n= n t O1 p\.

Climb up the \prx= m aU1 n t n= n t O1 p\.

A user can enhance the /N/ sound by adding /g/ after it.

Simple replacements:

I like chatting with you.

He’ll join the army.

He’ll \prx= d Z OI1 n\ the army.

A nice toothy grin.

A nice \prx= t u1 D i\ grin.

The smooth surface.

The \prx= s m u1 T\ surface.

\prx= dZ E n r= EI1 S @ n\.

\prx= s w O1 t \ team.

\prx= s I1 4 I\ traffic.

\prx= s i1 4 i\ traffic.

That’s wasting time.

That’s \prx= u EI1 s t I N\ time.

It’s in my \prx= I1 r d r @ m\.

He had a good education.

He had a good \prx= E dZ u k EI1 S @ n\.

The \prx= r U1 m \ is big.

He hit \prx= p E1 j \ dirt.

He hit \prx= p E1 i \ dirt.

The \prx= t A j f u1 n\ hit.

The \prx= t A i f u1 n\ hit.

He heard a strange noise there.

He heard a strange \prx= n O1 j z\ there.

He heard a strange \prx= n O1 i z\ there.

1. What are Sounds?

Sounds are produced by the speakers’ voice. This include laughing, breathing, sneezing, coughing and other sounds our voices can produce to mimic sounds we make in our daily lives. Sounds are always between two hashtag signs #LAUGH01# in capital letters and sometimes followed by a number if there are more than one of the same sound. The children’s voices have more sounds than adult voices because, as you well know, children are way more playful :-).

2. What are Exclamations?

Exclamations were a bit trickier to select and we only kept the most commonly used ones. Exclamations are always followed by an exclamation mark (!) – quite obviously – but without a blank between the word and the sign. If there is a blank left in between, the exclamation will be ignored. You may have noticed that in some cases certain exclamations in the document are doubled by the same exclamation in brackets (“), this is simply to avoid extended pauses.

3. How do I use them?

In both cases you simply need to insert sounds and exclamations into your text and they will be expressed be uttered correctly if you are using the right voice.

Please note, not all voices have sounds and exclamations. In some cases we can make additional recordings, in some cases we can provide substitutes (that’s when (S) is written after the text string, don’t copy this of course). Unfortunately, sometimes we can’t process the voice further.

Can I change voice and/or language automatically within my text?

Yes, do voice switching by using this tag: \vce=speaker\ as in the following example: “Good morning, ladies and gentlemen, \vce=speaker=Julie\ Bonjour mesdames et messieurs.”
Just pick the name of the voice that you want to use and the text-to-speech will immediately switch to the new voice after the tag. For special voices, like the voice containing emotions or variants of a specific voice, you need to type the name without any space, parenthesis or underscore.
For example Will (LittleCreature): \vce=speaker=willlittlecreature\. Enjoy!

Источник