More Text-To-Speech Transcription!

Our platform provides a client with the ability to transcribe and translate content to/from a number of languages, as discussed here. Recently, we added a number of additional languages specific to Text-To-Speech transcription. These are, (a) French (Canadian), (b) Portuguese (Brazilian), (c) Spanish, (d) Swedish, and (e) Turkish.

In total, Text-To-Speech transcription now has the below set of languages available. Please note each language has multiple dialects, and gender specific voices are available.

In the below description, we show you how to use the additional languages, by overlaying audio into a video. It should be noted, transcription can be used in two ways, (a) Speech-To-Text, and (b) Text-To-Speech. This post is focused on the second option, Text-To-Speech.

Steps

1. Please direct your browser to videotranslator.ai, and then click on the Login button. On successfully logging into the application, you should see an interface similar to the below. Select Template, and using the highlighted button, Edit Template: myTemplate.

   

2. Originally myTemplate has only one component. This is the video component. We are going to Add Audio component. On addition, you can see the Template with both Video and Audio components. The point is to have somewhere to use our Text-To-Speech AI.

   

   

3. To recap, we edited the template to have both video and audio components. Save and Exit to the file system.

   

4. Click on our now modified myTemplate, and create a new item, big_bunny_2. The next step is to upload our old friend, the sample video.

   

   

5. But what about our Audio Overlay, at this point we create it and are just going to add it in shortly. Scroll down to the Audio component, and instead of uploading a *.mp3, we instead add some text (Hello! My name is Big Bunny!) and click Add Caption. We are going to get the AI to say, ‘Hello! My name is Big Bunny!’

   

6. Now we have some text, (a) Speech-To-Text transcribe, and (b) add an Audio Overlay. As shown below, we transcribe, but only the second component as this is where we need the voices - the plan is to use a British sounding AI voice.

   

7. Once complete, in the video component (a) Mute Original audio, (b) add in the Audio Overlay. Please note, we have set it to play between 2 -> 5 seconds, and used the +.

   

8. This gives us the final product. Please note (a) original audio has been muted, (b) new audio has been added, in this case the robotic voice of the AI. Please note, there is no requirement to use the AI, a human recorded audio codec is often preferable, depending on the target audience - click play below to have a listen.

Conclusion

In this blog post we have covered how to add an audio overlay into your underlying content. Specifically, (a) we used an AI voice to simulate a person speaking UK English, (b) muted the original audio, (c) added the new audio onto the video to produce a new piece of video content.

This ability to add content can be across any of the above languages. We have used the example of English to keep it simple.

Please connect with us on LinkedIn, YouTube or Facebook for any comments, questions, or just to keep up to date with the work we do!

We are very grateful for your support!

Should you have any questions, or just want to drop us a note saying hello, please feel free to send us an email at hello@videotranslator.ai.