Tools I Use: Text to Speech

text to speech

Previously, I wrote about dictation and transcription services I use for speech-to-text.

Now imagine getting anything on your computer read back to you.

There is a little-known tool available on most computers called text to speech.

Why do I use this little-known tool meant for accessibility? I am not illiterate nor blind, but I do use this often because my ears are available more than my eyes are.

This is the same reason I listen to audiobooks and podcasts. Ears can take constant input. Eyes are needed for many things to see around you, guide you and also read.

If I need to “read” an online article, email or document (like an ‘exciting’ contract), this will read aloud all text as-is. Your computer may have multiple voices to choose from to read this text Verbatim.

  1. Find ‘text to speech’ in your system preferences.
  2. Select a voice you want to read the text and the rate of speed for the machine to read it to you.
  3. Memorize the hot keys to hit to activate this function
  4. Select some text on your internet browser or within a document.
  5. Hit the hot keys.

It will read just about any text to you so you don’t miss it.

Yes, you can control the rate of how fast or slow you want text read to you.

I use this text to speech to do the first passes of editing and proofreading of my eBooks.

Audio is faster than typing or reading (I speak fast too). This is the same reason why I recently adopted and use an Amazon Echo Dot. I can ask Alexa any of its 15,000+ different ‘skills’ which includes continuing an audio book from Audible.

Some apps call it ‘read aloud’ feature. Adobe Acrobat has this feature to read PDFs back to you as well.

Have you tried using text to speech to save yourself time?

Tools I Use: Transcription

Speech2Text

Over the past few years, I have found that converting speech to text has a lot of value.

Speech recorded or otherwise is not very searchable without a transcript.

In 2013, I ran a successful Kickstarter project to transcribe over 100 audio podcasts into written word and create an ebook out of these transcriptions.

In 2016, I created three other podcast series. As an experiment, I wanted to see which was more valuable. Audio alone or audio with transcripts. Guess which one was viewed more? Hint: the series with transcripts was viewed/listened to a lot more.

People value the transcripts. Enough to make an eBook out of them.

I have used a variety of tools for transcripts.

I tried Dragon Speak Naturally by Nuance a while back which is trained to your voice, but I kept forgetting I had it available to me. Now there is similar technology on my laptop (when connected to the web).

If you prefer to have your voice transcribed, most Apple, Chrome, and Windows-based computers now have the option of activating speech-to-text (aka dictation) where you turn on this feature (with a hotkey) and start talking as you watch your words appear on your page. If you can talk, your computer can write for you quite literally. Helps for brainstorming and writing any stream of consciousness. Some tools work better than others. Just don’t forget to edit the text later since we speak differently than we read.

When it comes to transcribing audio recordings, I used one online vendor for a successful Kickstarter project. This same vendor did a great job back then. However, after while they began to deliver slower (1 week+), less consistently and results were not as accurate as I had previously seen. This did not just happen once or twice. This caused me to look elsewhere within the free market for similar transcription services.

No transcripts are 100% accurate due to nuances in language and even audio recordings, so you need to check the transcripts received against the audio you sent. I do.

In 2016, I started to use Rev and now get transcripts for my audio recordings in less than 12 hours.

I also found a few contractors from Upwork who do transcription well but are much slower which is okay when it is not time sensitive, but you have to hunt for them because they get a lot of work from around the world.

UPDATE:

In 2018, I started using Temi to get transcripts from my audio recordings within a few minutes. Yes, that’s right…transcripts in minutes, not hours nor days. Faster and less expensive. Game changer! A 16-minute audio file gets transcribed in less than half that time thanks to machine-generated transcription which seems to improve every time I use it. Temi costs a fraction of the price of human-generated transcription. Accuracy is very close to human-generated transcription, however, I review every transcript I get back from humans or machines since there are specific words and context that most would miss if I did not.

Now back to creating more eBooks based on audio interviews recorded and transcribed.

Tools I Use: Podcasts

podcast-icon-1322239_960_720.png

Podcasts I listen to

I listen to a lot of podcasts, including:

The Economist

The Mentee Podcast

99% Invisible

Seeking Wisdom

The Tim Ferriss Show

Why listen to podcasts?

Your ears are more available than your eyes. You can use headphones or earbuds.

Unless you need dead air (silence), why not consume some audio content?

If you are waiting (commuting, traveling, in line) somewhere, why not learn something new instead of vegetating in place?

Do you like good content? Pick a topic. There is a podcast about it.

Do you like good content that is free to download and consume? How much of your content is free vs. paid for? All podcasts worth listening to are free.

Podcasts of my own

Another DAM Podcast

Podcast about Digital Asset Management

Tagging.tech

Podcast comparing human-generated information to computer-generated information

Rights.tech

Podcast about Rights Management

There is another series coming in January 2017