Everybody who lived during 2020 will remember when things changed. How our lives change. They called it “unprecedented times.” We called it our worst nightmare. When the governments around the world issued us to wear medical masks or any homemade masks we could find, we saw the disappearance of the human lips. We realize that the human lips and lip reading were our lifelines when our hearing aids and cochlear implants failed to fill the gaps.
So when the face mask came on. We tried to push for clear face masks on others. And when that couldn’t happen, we stared and listened to sounds that no longer made sense anymore. Our minds started playing tricks that we no longer could comprehend our native language because the lips were part of our comprehension without realizing. Who knew that lipreading could be such an integral part of our communication?
So during the pandemic, the demand for voice-to-text, speech-to-text or automated voice recognition apps has increased more than ever before. When face masks became a norm, lipreading and hearing people speak were harder. While heading to the doctor’s office, picking up groceries, or chatting amongst friends, frustration was felt across the hard-of-hearing community. The Deaf community had the luxury of continuing to communicate with sign language without much disturbance but Deaf lip readers joined the frustration too.
Android users had Google Live Transcribe as their free choice and found a sense of relief and let others with hearing loss know. iPhone users were left trying to find their own solution. Some iPhone users took another route and used Google Meets by using their internet browser on their smartphone to get a similar effect. Finally, now iPhone users have the option of getting their own captioning on the devices.
What is needed to be the best voice-to-text app? Here are a few key things are worth mentioning to understand what makes a great app to have.
Works without the internet
Using apps outside of your home can get very costly unless you have an unlimited data plan. Many of the speech-to-text apps require WiFi. Apps like Google Meets or Google Live Transcribe (at one time) required WiFi or internet connectivity to work.
The transcription work is not done on the phone, and WiFi or a data plan, for some apps, is needed. So instead, the voice transcription work is done remotely in a private space on the internet. This occurs because it takes a lot of energy to do the voice transcription work, and it’s best to save battery power on a smartphone.
Most people desire to use speech-to-text apps outside of the home. But, without realizing it, free often comes at a cost or an extra cost depending on how frequent you are using the app. So apps that you can download and run on your phone without internet connectivity are cost-effective.
Better accuracy through sharing data
The accuracy of the voice-to-text translation is best when more people are using it, the audio data is not private and freely shared through WiFi. When you are using a voice-to-text app, voice data is sent remotely behind the scenes to be processed and transcribed to you.
Some of the voice data is saved on the company’s virtual computer. That enabled them to collect a lot of audio data to improve the quality and accuracy of the app. In addition, some of the data can be saved for the company to repurpose and improve the app to learn different voices and annunciations. More data makes the app better over time. There are some companies that designed new technologies to make your voice data private.
You might find that your company or someone asks you not to use the app for privacy concerns. There are existing laws that protect your data from being shared. Our banking or health records are already legalized to be private, and these apps break the rules that many companies want to avoid.
Accuracy for all speech
When apps are not built with inclusivity in mind, poor accuracy shows. Many apps are created by men with similar speaking abilities. This is why not all apps are inclusive of people with disability, people of different nationalities, speaking abilities or gender at times. As we are deaf and hard of hearing, many of us have a slight or profound deaf accent. An app that has been trained with varied speech would work well for us.
Accuracy on unfamiliar words
Apps should understand specific conversations. Typically apps work well with basic vocabulary. However, if you are a neuroscientist or an archaeologist, the app may not have all the jargon or terminology used in your field. If you are allowed to add new vocabulary to the app, it could help improve the accuracy and enable you to follow the conversation a bit better.
Improving the Economic Power of Deaf and Hard of Hearing Communities
Most people like the idea of free things. But nothing is ever free. You may be paying for it indirectly unless it is from a charity. Most likely, you paid for the free item by buying a device, paying your taxes, or through other interactions.
Choosing brands from lived experiences
Behind the scenes of these apps, we are about to share are people who devote time because of lived experiences. All of them provide a paid version of some sort. By paying a fee, you’re not only helping the deaf and hard of hearing community, but you are showing what’s important to you.
Creating employment for people with hearing loss
Investing in apps designed by people with lived experiences, allow you to advancement the community. People with hearing loss are often unemployed because companies create systems that make it difficult for people with disabilities to advance in life or create generational wealth within the deaf community.
Lack of career advancement
Lack of advancement in skills or leadership roles means deaf and hard of hearing people can’t control access to better wages in comparisons to hearing people or a chance to improve their overall livelihood. Some will never be able to be in leadership positions. How many executive leaders can you count in tech, finance, or communications at major companies that have a hearing loss?
Seeing others like us in the community
With more people in our community seen in leadership roles, the more others can see themselves as leaders. It is like the story of Sir Roger Bannister. He was the first man to run a mile under four minutes. Many people seventy years ago believed that it wasn’t humanly possible. Not until Sir Roger proved that it could be done. Today, many athletes can easily run a mile in 4 minutes without a thought.
Our best voice to text app for iPhone
The rest of the article aims to let you know the options for iPhone users. iPhone users pay a premium for good quality smartphones, and with the highest quality smartphone, iPhone users expect quality apps to complement their smartphone devices. Therefore, we reviewed a few of the top and most popular voice-to-text apps built by the deaf community for the deaf community. In addition, we looked across the internet for feedback on each of the app where we can. Some of the apps below are in beta and we limited our review to the app features. However, these are thoughts from people with hearing loss just like you. We hope with this insight, you can decide which app to download and try today.
- This is not made by Google or the same as the Google Live Transcribe app
- Needs a quiet environment for this app to work
- Poor transcription with fast talkers
- Works best when one speaker is talking to follow along
- Cost for weekly, monthly, and annually usage after a 1-week trial
- Easy to run the app for 1-on-1 conversations
- When other people speak, they will need to use their phone and a QR code for better accuracy in group conversations.
- Transcription may be slow in a group setting
- Requires the WiFi or data connection for the app to work
- Better transcription comes with premium services or attaching an external microphone.
- After 40 mins free service every month, cost for monthly and annually usage
- Suitable for voice conversations but best in-person
- The app needs to be near the person speaking to work well. Lecture hall may not be ideal
- Not ideal for transcribing from other sound speakers from the computer, radio or tv.
- Requires WiFi Connection
- Good at picking up female voices
- A one-time fee
- App currently in beta
- The app can identify different voices
- Available using a web browser (WiFi and data connection required). It will have iOS and Android version in the future
- The cost is up to 6 hours free and a monthly fee after that.
- Comes with a color-coded microphone to caption all speakers
- The app can identify different speakers in a group setting
- Can use at a conference settings or a family gathering
- Device and app are available for testing
Other Apps Worth Mentioning
- Used only for phone calls or conference calls without an interpreter
- Read what the person on the line had said
- Can call a landline and mobile phones using voice or text
- Free up to 20 minutes each month, then pay per 100 minutes or an one-time annual fee
- Can type or speak to others
- There can be a noticeable delay
- Captions your conversation for incoming and outcoming calls
- Reach landlines and mobile phones using voice or text
- Free when others have Rogervoice app
- Pay monthly or annually and priced on the hour.
- App comes with multicolor text and background
- Can use with an LED light display (Hat, face mask, badge or signage) as well
- LED would ideally be worn by another person who is speaking
- Ideal for a business setting
- Allows you to communicate with others by typing back and forth
- Fully equipped computer screen and keyboard for you and other person to communicate
- Text communication that not automatic but typed manually by the speakers
- Ideal for a business setting where you are at a service counter
- Used originally for managing meetings
- Can pick up conversation 8ft away in the office (quiet environment)
- It can work well to transcribe audio from a computer
- You have the option of saving the conversation for reference later
- There’s a monthly and annual subscription after 600 minutes of free
- A free app already installed on iPhone for dictation
- Many users complain of poor captioning
- Limitations for long conversations or listening
We are sorry that this post was not useful for you!
Let us improve this post!
Tell us how we can improve this post?