This site uses different types of cookies, including analytics and functional cookies (its own and from other sites). To change your cookie settings or find out more, click here. If you continue browsing our website, you accept these cookies.
In this post, I want to share tools that can recognize speech from audio file to text and then translate into other languages.
We don't think it's easy to find a custom speech recognition tool at Alteryx. So, me and the team (special thanks to @wellyLiyanto) created this potential tool using the Google service API in Python.
In the attachment, you will get two tools: Speech to Text & Translate Tool, like this:
1. Speech to Text
This tools is developed by Python Code using Google Speech to Text API which can be seen in the following documentation
Inside the tool, you need to specify :
This is a Google Service Account Credentials JSON file. Detailed information on how to create this JSON file can be seen in the following post :
b. Bucket Name
Enter the bucket name of Google Cloud Storage Platform which is used to store audio files.
Enter the language used in the audio speech file.
d. File Path (From Local)
Find the speech audio file that will be recognized. In this option, Your file will be uploaded into Google Cloud Storage and deleted automatically.
e. Blob Name (From GCS)
Specify the blob name of the speech audio file from your google cloud storage. In this option, the API will recognize your speech audio file directly from your GCS platform.
2. Translate Tool
In the Translate Tool, you just need to specify the source and destination language. Source language is an optional, you can choose None to detect your transcript language automatically.