Google Cloud provides powerful and industry-leading cloud computing services for developers all around the world. It offers numerous solutions for AI, big data, machine learning, OCR, speech-to-text and more. However, you need some beginner programming skills before calling these APIs. So how people who never learn programming languages could use these amazing capabilities empowered by Google?
Here, in this article, I will show you how to use Google Speech to Text API without any programming skills and load it in EasySpeech2Text.
Step 1. Create your own Google Cloud Account.
Firstly, you need a Google Cloud Account. You can use your Gmail account directly or register a new one. If you are new to Google Cloud, you will get a $300 Google cloud free credit. It means you can:
#1 Recognize your audio files for more than 12,500 minutes by Google Speech-to-Text API.
Note, in the current version, we use Speech Recognition (without Data Logging – default) and Standard Models.
#2 Convert 75,000,000 characters to audio by Google Text-to-Speech API.
Step 2. Create your first project.
Now, you need to create the first Google Cloud speech-to-text and text-to-speech project.
Step 3. Choose the credential type.
Click “Create Credentials” -> “Service Account Key”.
Step 4. Set the account role.
You need to set the role of the account. Choose “Project Owner”.
Step 5. Download the JSON credential file.
Step 6. Enable API capabilities.
Search and enable Google Speech-to-Text and Text-to-Speech API.
Step 7. Load the JSON credential file.
Now you can load the JSON credential file and process your speech-to-text and text-to-speech in your computer.
Read the following post: