SpeechTech

Question: Text-To-Speech

To create an offer we will need following specifications:

If you desire verification through a password or a speech

Rough estimation of verified individuals (size of the database) and number of verifications per day

Verification via telephone channel or other form (format and data quality)

Do you require connection to your own IVR or you`d like to use SpeechTech´s one

Voluntarily more quotation details (technical limitations, required structure, output acces via API etc.)

Question: MegaWord

To create an offer we will need following specifications:

If you desire verification through a password or a speech

Rough estimation of verified individuals (size of the database) and number of verifications per day

Verification via telephone channel or other form (format and data quality)

Do you require connection to your own IVR or you`d like to use SpeechTech´s one

Voluntarily more quotation details (technical limitations, required structure, output acces via API etc.)

Inquiry: Voice Biometrics

To create an offer we will need following specifications:

If you desire verification through a password or a speech

Rough estimation of verified individuals (size of the database) and number of verifications per day

Verification via telephone channel or other form (format and data quality)

Do you require connection to your own IVR or you`d like to use SpeechTech´s one

Voluntarily more quotation details (technical limitations, required structure, output acces via API etc.)

Inquiry: Voice dialogue systems

To create an offer we will need following specifications:

If you desire verification through a password or a speech

Rough estimation of verified individuals (size of the database) and number of verifications per day

Verification via telephone channel or other form (format and data quality)

Do you require connection to your own IVR or you`d like to use SpeechTech´s one

Voluntarily more quotation details (technical limitations, required structure, output acces via API etc.)

Inquiry: Videoarchive processing

To create an offer we will need following specifications:

If you desire verification through a password or a speech

Rough estimation of verified individuals (size of the database) and number of verifications per day

Verification via telephone channel or other form (format and data quality)

Do you require connection to your own IVR or you`d like to use SpeechTech´s one

Voluntarily more quotation details (technical limitations, required structure, output acces via API etc.)

Inquiry: Phone call analysis

To create an offer we will need following specifications:

If you desire verification through a password or a speech

Rough estimation of verified individuals (size of the database) and number of verifications per day

Verification via telephone channel or other form (format and data quality)

Do you require connection to your own IVR or you`d like to use SpeechTech´s one

Voluntarily more quotation details (technical limitations, required structure, output acces via API etc.)

Inquiry: Subtitling

To create an offer we will need following specifications:

If you desire verification through a password or a speech

Rough estimation of verified individuals (size of the database) and number of verifications per day

Verification via telephone channel or other form (format and data quality)

Do you require connection to your own IVR or you`d like to use SpeechTech´s one

Voluntarily more quotation details (technical limitations, required structure, output acces via API etc.)

Support

I found an error in you product...

Please send as a discription of the error via the form for technical support above. Thank you!

I use TTS in a form of DDL library and I need to install/uninstall it on my new computer.

For entering the library you need to have a license (or activation) number, activation name and confirmation number. If your license allows it, you can use these details to activate the library.

I have a file by MegaWord or TTS prepared for offline activation. Where can I activate?

Please follow the instructions in the application. Using the file you can activate the application here.

I would like to use MegaWord for transcription of calls recorded via dictaphone. Unfortunately it is not possible to try it in DEMO. I am afraid that it will not work well because there is often background sound like wind or insects recorded as well and it lowers the quality of the record.

The transcription of record in MegaWord is possible to use for record of dictation of one person with the same style of speech you use for dictating directly in MegaWord. It is necessary to dictate for example punctuation in a silent environment, advantageously with well set headset microphone. According to your description, your records do not match these criteria therefore I would not recommend the full version. You can theoretically try it in DEMO version without function of transcription of the record if you create trial testing interview with another person which you would record closely to the microphone (placed same as a Dictaphone) with MegaWord in use.

I updated the dictionary to a new version. Can I delete the old one?

In the section for choosing user and complete, just place your cursor on the dictionary and use right mouse button. It will give you the delete option. The delete option is not available for the dictionary in current use.

What does "LITE version" in the complete menu mean?

The LITE version allows you to edit you files which are saved in a MegaWord format (format LVCSR). The LITE version is not purposed for recognition and therefore it is missing a real control panel. The LITE version does not need a license but it can be used for editing files which were dictated by somebody else on a different computer which holds a full license.

Can I dictate letters from another alphabet other than English?

If these letters are parts of whole words it is necessary to add them to the dictionary. Independent letters can be also saved in the dictionary for example α [alfa sign], β [beta sign] etc.

There is no recognition after the start of dictation.

Primarily, check the microphone reaction on a right side of the control panel. After that, check the status bar at the bottom of the application for the right type of microphone in use. You can adjust the connection of a correct audio peripheries in the option “microphone settings” or “application settings” in the “other” section. You can prevent any issues with acoustic peripheries by using recommended devices.

MegaWord general dictionary
Demo version	30 days	0 Kč	30 days DEMO
Subscription	1 month	500 Kč	Buy
Full version	unlimited	10 000 Kč	Buy

MegaWord specialized dictionary
Advocacy, justice, representation, phoniatry, gynecology, histology, surgery, internal, cardiology, neurosurgery, oncology, ENT, orthopedics, pediatrics, pathology, psychiatry, radiology, forensic medicine, ...	Send question

Text-to-speech
Demo version	30 days	1 voice (Jan)	0 Kč	30 days DEMO
Full verison	unlimited for noncommercial use	5x CZ voice, 1x SK voice	2 500 Kč/voice	Buy
For Android	unlimited for noncommercial use	5x CZ voice, 1x SK voice	49 Kč/voice	Google Play
Commercial application	unlimited	5x CZ voice, 1x SK voice	49 Kč/voice	Send question

About us

Since the year 2000 our company SpeechTech, s.r.o. helps its clients with implementing voice technology which is based mainly on transcription of speech to text, text to speech and phone call analysis. We are able to provide everything from basic modules for voice technology to complex solutions adapted specifically to customer`s needs including consulting and technical support.

Our voice dictation transcribtion technology serves its user in many fields especially as a much appreciated feature in medicine for medical record writing, in justice and company minutes.

From the year 2015 we have been providing subtitles for live streaming of television programs and shows for example, Otazky Vaclava Moravce, Hyde Park, selected sport programs etc, which you can watch on Ceska televise or teletext page 888.

Our main partners:

Výzkum a vývoj je prováděn v úzké spolupráci s Fakultou aplikovaných věd Západočeské univerzity v Plzni v rámci rámcové smlouvy o spolupráci, společných projektů a objednávek smluvního výzkumu.

Current project

TTS-TEACH2

Development of advanced TTS system

Projekt ve spolupráci s firmou Lingea s.r.o. se zabývá výzkumem a vývojem nových metod počítačové syntézy řeči využívajících metody hlubokého učení (tzv. deep learning) pro generování hlasu pomocí neuronových sítí ke zkvalitnění výuky cizích jazyků. Potenciál uměle vygenerovaných hlasů je v projektu napřen do zkvalitnění českého, ale šířeji středoevropského jazykového vzdělávání. Zároveň reagujeme na soudobý příklon k e-learningu a potřebě pracovat s kvalitními hlasy rodilých mluvčích.

Question: Text-To-Speech

Question: MegaWord

Inquiry: Voice Biometrics

Inquiry: Voice dialogue systems

Inquiry: Videoarchive processing

Inquiry: Phone call analysis

Inquiry: Subtitling

Inquiry

Text to speech

SpeechTech Products

MegaWord

Archive

Text-to-speech

Voice biometrics

Analytics

Subtitling

Voice dialogue
systems

Are you not sure, which product is optional for you?

Services

Support

Downloads

Manuals and documentations

About us

TTS-TEACH2

Contact

SpeechTech, s.r.o.

Kancelář Technická

Kancelář Morseova