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

Stephen G. Pope
10 Mar 202414:26

TLDRIn this informative video, Steven Pope, founder of the Content Engine, demonstrates how to transform old videos into new content for social media using AI technology. The process involves overlaying a new voice track generated by 11 Labs onto an existing video. The project is orchestrated through a combination of Airtable, Make.com, and Json.video.com. Pope guides viewers step by step, from setting up an Airtable base to creating an automation on Make.com that triggers the creation of an audio file from text. The audio is then uploaded to Google Drive and made publicly accessible. Finally, Json.video.com is utilized to combine the video and audio into a new video ready for social media. The video concludes with a successful demonstration of the process, showcasing the power of AI and automation in content creation.

Takeaways

  • 🎬 The video demonstrates how to repurpose old videos into new ones for social media using AI.
  • 📝 AI is used to generate a new voice track from text with the help of 11 Labs, an audio AI platform.
  • 🔄 The process involves overlaying the new voice track onto an old video, creating a fresh piece of content.
  • 🚀 Steven Pope, the founder of Content Engine, guides viewers through the process, showcasing his expertise in content system automation.
  • 📂 An Airtable base is used to organize and manage the project, with fields for document IDs and text for the voice-over.
  • 🔗 The Google Drive folder 'Json to video' contains the b-roll video and other necessary files for the project.
  • 🗂 Airtable's share settings are configured for public access to facilitate the automation process.
  • 🔊 11 Labs is used to convert the text into audio, which is then combined with the video using Json to video.
  • 🤖 Make.com is the platform used to automate the entire process, connecting different services and actions.
  • 📈 The video emphasizes the efficiency and scalability of using AI and automation for content creation.
  • 📹 The final product is a new video, ready to be posted on social media, created entirely through the automated workflow described.

Q & A

  • What is the main purpose of the video?

    -The video demonstrates how to repurpose old videos into new ones for social media by overlaying a new voice track generated from text using AI.

  • Which AI platform is used to generate the voice track?

    -The AI platform used to generate the voice track is called ElevenLabs.

  • What is the role of Airtable in this process?

    -Airtable is used to create a base where the video and text information are stored and organized, which is then connected to Make.com for automation.

  • How does the video demonstrate the use of Json Video?

    -The video shows how to combine the original video and the AI-generated audio into a new video using Json Video by making an HTTP POST request with the necessary JSON data.

  • What is the significance of making the video and audio files publicly available on Google Drive?

    -Making the files publicly available ensures that the Json to Video service can access them to combine into a new video during the automation process.

  • How does the automation process trigger?

    -The automation process is triggered by a new row in the Airtable base, which is monitored by Make.com for new records.

  • What is the name of the content engine's founder featured in the video?

    -The founder of the content engine featured in the video is Steven Pope.

  • How does the video ensure the success of the automation process?

    -The video includes steps to test each part of the process, such as generating audio, uploading to Google Drive, and making HTTP calls to Json Video, with checks for success codes.

  • What is the final step of the automation process?

    -The final step of the automation process is to save the newly created video from Json Video back to Google Drive and update the Airtable base with the video URL.

  • Why is a delay added in the automation process?

    -A delay is added to allow Json Video to process and generate the video after the HTTP POST request has been made.

  • What is the benefit of using Make.com for this project?

    -Make.com is used to automate the entire process, from generating the voice track to combining it with the video and uploading the final product, saving time and increasing efficiency.

Outlines

00:00

📚 Introduction to Repurposing Old Videos with AI

Steven Pope introduces a project on how to transform old videos into new content for social media using AI. He outlines the use of an audio AI platform called 11 Labs to overlay a new voice track onto an old video. The process involves using Airtable, Make.com, 11 Labs, and Json.video.com. The video serves as a tutorial on setting up the automation from scratch, starting with creating an Airtable base and configuring necessary platforms.

05:01

🔄 Automating the Audio Generation and Video Repurposing

The video script details the step-by-step process of creating an automation on Make.com that triggers when a new row is added in an Airtable base. It involves connecting to 11 Labs to generate audio from text, uploading the audio file to Google Drive, and making it publicly available. The process continues with an HTTP POST request to Json.video to combine the video and audio into a new video. The video also covers how to parse JSON data and handle API keys for the automation.

10:03

🚀 Finalizing the Video and Updating Airtable

The final steps in the video script involve saving the newly created video back to Google Drive and updating the Airtable with the final video URL. It discusses the importance of making both the video and audio files publicly available for Json.video to access them. The script also mentions a potential improvement to the automation process by using separate automations for video creation and processing. Finally, it shows how to parse JSON data to extract the necessary values for uploading the video and updating the Airtable record.

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 this technology to repurpose old video content by adding a new AI-generated voiceover, making the content suitable for social media platforms.

11 Labs

11 Labs is an audio AI platform mentioned in the video that is used to generate the voice track for the new video. The platform utilizes advanced AI algorithms to synthesize human-like voice from text, which is a key component in the video's demonstration of repurposing video content.

Airtable

Airtable is a cloud-based database that allows users to organize and manage data through a spreadsheet-like interface. In the context of the video, Steven uses Airtable to store and manipulate the information needed for the automation process, such as the text for the voiceover and the Google Drive document ID.

Make.com

Make.com is a platform for creating automation workflows. It is used in the video to connect different services and actions required to automate the process of creating a new video with an AI-generated voiceover. The automation triggers when a new row is added to an Airtable base, coordinating the sequence of steps to generate and overlay the voiceover onto the video.

Json Video.com

Json Video.com is a platform that is experimented with in the video for creating videos. It is used in conjunction with the other tools to combine the original video footage with the AI-generated audio to produce a new video. The platform requires JSON data, which includes all the necessary information for video creation.

Google Drive

Google Drive is a cloud storage service used in the video to store the original video file and the AI-generated audio file. It is also where the final video is saved after being created through the automation process. The video script mentions creating a folder in Google Drive and using its sharing capabilities to make the files publicly accessible.

Automation

Automation in the video refers to the process of setting up a series of actions to be performed automatically without manual intervention. Steven Pope demonstrates how to automate the creation of a new video by linking various online services and tools through Make.com, which simplifies the workflow and saves time.

Content Repurposing

Content repurposing is the practice of using existing content and adapting it for use in a new context or format. In the video, old video footage is repurposed by adding a new voiceover generated by AI, making it suitable for posting on social media platforms. This extends the life and reach of the original content.

Social Media

Social media refers to digital platforms that allow users to create and share content or participate in social networking. In the context of the video, the newly created video with the AI voiceover is intended to be posted on social media, showcasing how old content can be repurposed and given new life for these platforms.

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, JSON is used to structure the data required by Json Video.com to create the new video, including information about the video's dimensions, quality, and scenes.

Publicly Available

When the video mentions making a file 'publicly available', it refers to setting permissions so that anyone with the link can access the file without needing a login or special access. This is important for the automation process as it allows the services involved to access and use the video and audio files to create the final product.

Highlights

Steven Pope demonstrates how to repurpose old videos with AI-generated voice tracks for social media.

The audio voice is generated by the AI platform 11 Labs, a popular choice for online content.

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

An Airtable base is configured to manage the project, including a field for the Google Drive document ID.

Text for the voice-over is added to the Airtable base and will be converted into audio using 11 Labs.

A Google Drive folder is used to store the b-roll video and the AI-generated audio file.

Make.com is used to create an automation that triggers off a new row in the Airtable base.

The automation connects to 11 Labs to generate the audio from the text in Airtable.

The generated audio file is written back to Google Drive and made publicly available.

A JSON structure is used to contain all the information needed by Json.video to create a new video.

The original video and the AI-generated audio are combined into a new video using Json.video.

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

The final video URL is added back to the Airtable base for easy access and sharing.

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

Steven Pope emphasizes the efficiency gains from using Airtable, Make.com, and 11 Labs for content automation.

The video serves as a tutorial on leveraging AI and automation tools for content creation.

The content engine, founded by Steven Pope, has helped numerous personal brands and agencies automate their content systems.

A walkthrough of setting up the automation is provided, including connecting various platforms and configuring settings.

The video concludes with a demonstration of the final video, showcasing the successful integration of text, audio, and video.