INSANE AI Voice-Over Automation With Make.com & ElevenLabs

Stephen G. Pope
10 Mar 202414:26

TLDRIn this video, Steven Pope, founder of the Content Engine, demonstrates how to transform old videos into new ones for social media using AI voice-over technology. The process involves using an audio AI platform called ElevenLabs to generate a new voice track from text. The project is built from scratch, utilizing Airtable, Make.com, ElevenLabs, and Json.video.com. The video showcases how to automate the creation of a new video by overlaying the generated audio onto an existing video, and then sharing the final product on social media platforms. The tutorial is aimed at personal brands and content agencies looking to streamline their content systems.

Takeaways

  • 🎬 The video demonstrates how to repurpose old videos into new ones for social media using AI voice-over.
  • 📄 AI-generated voice track is created from text using the audio AI platform called ElevenLabs.
  • 🔄 The process involves building the project from scratch with tools like Airtable, Make.com, ElevenLabs, and Json.video.com.
  • 📑 An Airtable base is set up to organize the project, including fields for document ID and text for voice-over.
  • 🔗 A Google Drive folder is used to store the video file and make it accessible for the automation process.
  • 🗂️ The video and text are combined using Json to video, which is automated through Make.com.
  • 🔊 ElevenLabs is used to convert the text into an audio file, which is then uploaded to Google Drive.
  • 🔗 The public share link of the audio file from Google Drive is used in the Json to video platform to create the new video.
  • 📊 Json to video requires specific information like video dimensions, quality, and source URLs for both video and audio.
  • 📡 An HTTP POST request is made to the Json to video API, passing the necessary JSON data to generate the new video.
  • 🕒 A delay is added to allow Json to video to process the video before attempting to download it.
  • 📁 The final video generated by Json to video is saved back to Google Drive and the URL is updated in the Airtable base.

Q & A

  • What is the main topic of the video?

    -The video is about repurposing old videos into new ones for social media using AI, specifically with the help of platforms like Airtable, Make.com, ElevenLabs, and Json.video.com.

  • Who is the founder of the Content Engine mentioned in the video?

    -Steven Pope is the founder of the Content Engine.

  • What is the purpose of creating a new Airtable base in the video?

    -The new Airtable base is used to organize and manage the data required for the automation process, including the document ID from Google Drive and the text to be converted into audio.

  • How is the text converted into an audio track in the video?

    -The text is converted into an audio track using ElevenLabs, an audio AI platform.

  • What does Json.video.com do in the process described?

    -Json.video.com is used to combine the original video and the newly created audio track into a new video that can be posted on social media.

  • Why is the video and audio made publicly available on Google Drive?

    -The video and audio are made publicly available on Google Drive so that Json.to.video can access them to combine them into a new video.

  • What is the role of Make.com in this process?

    -Make.com is used to create and manage the automation that triggers the conversion of text to audio and the subsequent creation of the new video.

  • How does the video demonstrate the use of AI for content creation?

    -The video demonstrates the use of AI for content creation by using AI-generated audio from text and automating the process of combining this audio with video to create new content for social media.

  • What is the significance of the 'created time' field in the Airtable base?

    -The 'created time' field is used to track when new records are added to the Airtable base, which is essential for triggering the automation process in Make.com.

  • How long does the video suggest waiting before checking if the video has been processed by Json.to.video?

    -The video suggests waiting for 120 seconds after the request to Json.to.video has been made to allow time for the video processing.

  • What is the final step shown in the video for completing the automation process?

    -The final step shown is updating the Airtable record with the URL of the final video that has been uploaded to Google Drive.

  • Why is the video considered valuable for personal brands and content agencies?

    -The video is valuable for personal brands and content agencies because it shows how to automate and streamline content creation, which can save time and increase efficiency.

Outlines

00:00

📚 Introduction to Repurposing Old Videos with AI

Steven Pope introduces the video's purpose: to demonstrate how to transform old videos into new ones for social media using AI. He mentions the use of an audio AI platform called 11 Labs to overlay a new voice track onto an old video. The process involves utilizing Airtable, Make.com, 11 Labs, and Json.video.com. He outlines the initial steps, including setting up an Airtable base, creating a Google Drive folder, and preparing the necessary text and video files.

05:01

🔗 Automating the Process with Make.com

The video continues with the creation of an automation on Make.com that triggers when a new row is added to the Airtable base. It details the process of connecting Make.com with Airtable and Google Drive, generating audio from text using 11 Labs, and uploading the audio file to Google Drive. The focus is on setting up the automation correctly to monitor for new rows, process the text into audio, and handle the output successfully.

10:03

🚀 Combining Video and Audio with Json to Video

Steven explains the final steps of the process, which involve making an HTTP POST request to Json.video.com to combine the original video and the newly generated audio into a new video. He discusses setting up the request with the correct URL, headers, and JSON body, which includes details about the video and audio sources. The video concludes with a demonstration of the successful creation of the new video, its upload to Google Drive, and the update of the Airtable base with the final video URL.

Mindmap

Keywords

💡AI Voice-Over Automation

AI Voice-Over Automation refers to the process of using artificial intelligence to generate a voice track from a text script, which can then be overlaid onto a video. In the video, Steven Pope uses an old video and overlays a new voice track generated by an AI platform called ElevenLabs, demonstrating how to repurpose old videos with AI technology.

💡ElevenLabs

ElevenLabs is an audio AI platform mentioned in the video that is used to generate voice tracks from text. Steven Pope uses ElevenLabs to create a voice-over for the old video, selecting the 'Atom' voice model, which is a popular choice for online content due to its widespread use and natural sound.

💡Airtable

Airtable is a cloud-based platform for organizing and managing data through a combination of a database and a spreadsheet. In the script, Steven uses Airtable to create a new base for the project, configure fields, and manage the data needed for the video automation process.

💡Make.com

Make.com is a platform for building automation workflows. Steven utilizes Make.com to create and execute the automation that connects various services, such as Airtable and ElevenLabs, to generate the AI voice-over and integrate it with the video.

💡Json Video.com

Json Video.com is a new platform that Steven Pope is experimenting with in the video. It is used to combine the original video with the AI-generated audio to create a new video. The platform requires a JSON object containing all the necessary information to generate the video.

💡Google Drive

Google Drive is a cloud storage service used in the video to store and manage files. Steven creates a folder in Google Drive for the project and uses it to store the original video and the AI-generated audio file before combining them into a new video.

💡B-roll

B-roll refers to supplementary footage that is edited into a video production to enhance the main footage. In the script, Steven uses an old b-roll video of himself sitting at a desk, which is sped up and used as the visual component for the new video.

💡Automation

Automation in the context of the video refers to the process of setting up a series of actions to be performed automatically by a computer system or software. Steven demonstrates how to automate the creation of a new video from an old one by integrating various online services and platforms.

💡Content Engine

The Content Engine is the company founded by Steven Pope, which helps personal brands and content agencies automate and streamline their content systems. The video showcases one of the methods used by the Content Engine to repurpose content using AI and automation.

💡Social Media

Social Media platforms are online channels used for sharing content, where the video's final product will be posted. Steven mentions that the newly created video with the AI voice-over can be posted on social media, indicating the practical application of the automation process.

💡JSON

JSON (JavaScript Object Notation) is a lightweight data-interchange format that is easy for humans to read and write and easy for machines to parse and generate. In the video, Steven uses JSON to structure the data needed for Json Video.com to create the new video.

Highlights

Steven Pope demonstrates how to repurpose old videos using AI voice-over automation.

The process involves overlaying a new voice track generated from text onto an old video.

11 Labs, an audio AI platform, is used to generate the voice track.

The project is built from scratch using Airtable, Make.com, 11 Labs, and Json.video.com.

A new Airtable base is configured to manage the content and automate the process.

Google Drive is used to store the b-roll video and other project files.

Text for the voice-over is input into Airtable and later converted into audio by 11 Labs.

Make.com is used to create and run the automation that handles the conversion and video creation.

The video and audio are combined into a new video using Json to Video.

A publicly accessible link for the audio file is created to be used in the video creation process.

An HTTP POST request is made to Json to Video to start the video creation process.

The final video is processed and made publicly available on Google Drive.

Airtable is updated with the final video URL for easy access and sharing.

The entire process is automated to streamline content creation for social media.

Steven Pope has helped numerous personal brands and content agencies automate their content systems.

The video demonstrates the power of AI and automation in repurposing content efficiently.

Make.com's automation capabilities are showcased for content creation and management.

Json to Video is used to combine video and audio tracks into a new, shareable video format.

The process results in a new video ready for posting on social media platforms.