Hotel Industry Recruitment Ad: A Second Take Using Multilingual AI Audio

Introducing the #AISummer2023 series, a continuation of the original #30DayAIChallenge in Spring. As the field of AI evolves, this series delves deeper into the latest advancements in AI tools and capabilities. It represents not just my practical tinkering over the Summer, but a metaphorical ‘summer’ of AI growth and evolution.

There have been some interesting developments in the field of AI audio recently. For example, Meta just released a new multimodal model for speech translation. Meta’s Seamless M4T is an AI framework that can combine text, images, and code to create new content. It is trained on a massive dataset of multimodal data, and can be used for a variety of tasks, with the potential to revolutionize the way we create and consume content. At roughly the same time, ElevenLabs released Eleven Multilingual v2, a speech synthesis model that can generate human-quality speech in nearly 30 languages.

I wanted to test the multi-lingual speech generation in particular, so for this experiment I continued the theme of hospitality industry recruitment ads…this time from a global POV.

Here’s the final product:

How I Did It

Here are the tools and techniques used:

• Scriptwriting – The ideation and scriptwriting (including the narration) was done using ChatGPT.
• Visuals – The base visuals were all created on MidJourney.
• Sound – I used ElevenLabs for the multi-lingual audio narration and got the background music track from YouTube Studio.
• Editing – As usual, I used Final Cut Pro X…though pretty much any video editing tool would work equally well.

That’s it! The one thing I’m curious about is whether ChatGPT got the non-English languages right in terms of translation and context…while I understand a couple of the languages, I don’t know all of them well enough. I’d love for native speakers to weigh in on the quality of the audio and if the meaning is conveyed as intended. Please leave a comment or DM to let me know! (Thank you)