You can fill out our contact form here: https://speak-see.com/nl/pages/contact

Or you can email us at hello@speak-see.com

SpeakSee AutoCaption is developed to make digital meetings more accessible. AutoCaption is software that captions the audio output of your Windows tablet or computer in real-time. The software can assist you with online video-meetings, podcasts, radio broadcasts, e-courses and online seminars.

The SpeakSee Microphones are designed to make physical (group) conversations more accessible. The device consists of a charging station and three microphones, together with a software subscription it can be used to transcribe any physical (group) conversation in real-time. The SpeakSee Microphones can be used for business meetings or in educational settings. Besides, you can also use it for 1-on-1 conversations with family members or help you communicate with your doctor. Find out more here: https://speak-see.com/pages/products-speakseemicrophones.

The audio files and transcripts are processed automatically and securely using end-to-end encryption. Third parties do not have access to any of the personal conversations.

AutoCaption automatically live captions all of your digital meetings, independent of the (video-) conferencing platform you are using. Besides that, the software can assist you with online video-content, podcasts, radio broadcasts, e-courses and online seminars. AutoCaption gives you full control over your digital life.

AutoCaption automatically captions the outgoing computer audio of your Windows device. This means when you are speaking on the computer microphone yourself, nothing will happen. You can test the software by playing a video.  

You can create an account via https://my.speak-see.com/account/register. After activating your account and activating your license, you can download the application. Install the application and login with your credentials. You can test AutoCaption by playing a video.

Speaksee AutoCaption is currently available in the following languages:

- Dutch

- Dutch(Belgium)

- English(US)

- English(AU)

- German

- Danish

- Spanish

- French

- Croatian

- Italian

- Polish

- Portugese

- Turkish

- Chinese

Currently, you can only use one language per account. Do you want to use AutoCaption for multiple languages? Create an extra account via https://my.speak-see.com/account/register.

Currently SpeakSee AutoCaption is still in the BETA stage. All testers get free access to the software. After the free trial we will likely add a pricing model to the software. We also expect to still offer a free version with limited capabilities. All users will be informed in time about the subscription possibilities and prices.

Currently SpeakSee AutoCaption allows you to produce live captions on any computer running the Windows 7 or 10 operating system. MacOS is not yet supported..

Currently SpeakSee AutoCaption allows you to produce live captions on devices (computers or tablets) running Windows 7 or Windows 10. There is no app available yet for phones or tablets. Did you know that on Android phones you can activate the Live Caption feature by Google? You can find out more about this here.

Right now it is not possible to save the transcripts, the captions are only shown in realtime.

Yes, via the settings menu of SpeakSee AutoCaption it is possible to connect your custom proxy. See the picture below.

If you need any further support, please contact us by filling in the following form: https://speak-see.com/pages/autocaption-support

You can request a password reset via:  https://my.speak-see.com/account/password-reset-request

You can open the font setting by pressing the ''Aa' button that you can find in the captions box. Below you can find an example'

In the settings menu you can change your preferences at the ''subtitles'' menu.

This can be for several reasons:

- Check that you have entered the correct email address in the form

- Check that the email did not end up in your spam box.

- When you log in to my.speak-see.com, you will get the opportunity to resend the e-mail.

Haven't you received an email after following these steps? Then try to create an account with a different email address.

In contrast to the microphones, AutoCaption doesn't have speaker identification in the application. Most of the videoconferencing platforms have speaker identification build in the platform itself. Below you can find instructions on how to install this for your video platform:

-Google Meet: https://support.google.com/a/users/answer/9850209?hl=en

- Zoom: https://support.zoom.us/hc/en-us/articles/201362323-Changing-the-video-layout-Active-Speaker-View-and-Gallery-View-

- Microsoft Teams currently doesn't have this feature yet.

You can fill in our request quote form here: https://speak-see.com/pages/products-speakseemicrophones

We will reach out to you with more information regarding the price and possibilities.

Currently we don't have any devices available for testing, however via this link you can watch our demo video: https://youtu.be/AOSlVYU1xRQ

SpeakSee works with iOS and Android devices. This includes smartphones and tablets. It would also be possible to use it on your laptop. 

The system can currently have 1 to 9 microphones paired up at a time. 

There are three major differences that sets SpeakSee apart: 

1. SpeakSee uses microphones that are placed near the speaker's mouth to capture speech. This means you won't have to ask everyone in your group to download an app and wait for them to install it and then explain how it works, instead, just hand out the microphones and carry on with the conversation! 

2. SpeakSee works when there is background noise, like in restaurants. Our microphones use sophisticated beam forming algorithms that isolate the speech and leave out background noise. This enhances accuracy of the transcripts, even in noisy environments.

3. SpeakSee can also be streamed to your hearing aid! 

Yes it does. 

Since the speakers position the microphones on their shirt, close to their mouths, SpeakSee’s state of the art microphones, can accurately capture conversations, identify different speakers and transcribe it into text, in real time, even when there’s background noise