Create an AI-Powered Podcast & Avatars with Your Own Voice! | Control the Conversation
ฝัง
- เผยแพร่เมื่อ 25 ธ.ค. 2024
- In this tutorial, learn how to create an AI-powered podcast using your voice and ChatGPT Advanced Voice.
Unlike NotebookLM, where AI directs the conversation, you’ll be in control, guiding the entire process. From crafting the perfect prompt to editing with avatars, this tutorial will walk you through everything you need to create a professional podcast that blends human creativity with AI technology.
Check out the sample video: • Demo for AI-Powered Po...
What You'll Learn:
How to create a custom prompt to guide your AI conversation.
How to record your voice interacting with ChatGPT Advanced Voice.
Separating audio speakers and generating SRT caption files with PocketAI Speaker Separation Tool.
How to bring your conversation to life with HeyGen AI avatars.
Tips for editing in Adobe Premiere Pro for a polished result.
How to upload your podcast to TH-cam, Yuja, or any platform you choose.
Software Used:
ChatGPT Advanced Voice (on Phone App)
PocketAI Speaker Separation Tool & SRT Generator: Free Tool - efit.software/...
HeyGen Avatar Generator heygen.com/?si... (affiliate link)
Adobe Premiere
TH-cam, Yuja, etc.
By the end of this tutorial, you'll have all the tools to create your own AI-powered podcast, using your voice and controlling the entire conversation. Ready to take your podcast game to the next level? Let’s get started!
Awesome video. Separating the tracks of 2 speakers in an audio file is something many people are looking for. It is tedious process to do it manually. This video will be helpful to people who want this get done.
@@VenkatachalamRavindran Thanks! Yeah, separating the audio manually would be such a pain. I'm glad to see my audio separation tool saving time and effort !
@@GenerativeAIEducation Hey Tim, PLease check your Audio separation tool website. It's not working. Can you please confirm when it will come back online?
@@GenerativeAIEducation Can you check if your audio separation tool website working or not? Is this a subscription?
@@SamplingSpace I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
@@fliu5282 I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience! It's currently free.
Thank you for this tool. I just tested it today and it worked perfectly. Thanks!
@@Shark-Savvy Great! You're welcome!
🎯 Key points for quick navigation:
00:00 *🎙️ Introduction to AI-Powered Podcasting*
- Overview of creating an AI-powered podcast with innovative tools,
- Mention of using chaty PT and avatars to enhance the experience.
00:54 *📝 Crafting the Perfect Podcast Prompt*
- Detailed instructions for generating a prompt for the podcast,
- Importance of defining roles and instructions for chaty PT,
- Use of voice mode on the chat GPT app for interaction.
03:40 *🎧 Recording and Splitting Audio*
- Steps to record podcast audio using a phone screen recorder,
- Guidance on splitting the audio into two tracks for speaker differentiation,
- Highlight on syncing audio lengths for clarity.
05:02 *💡 Creating SRT Files with Assembly AI*
- Instructions for generating SRT files with speaker labels,
- Explanation of acquiring a free API key from Assembly AI,
- Benefits for the hearing impaired and differentiation in audio-only productions.
08:04 *🎥 Using HeyGen for Avatar Creation*
- Overview of HeyGen pricing and capabilities for generating avatars,
- Step-by-step process of uploading audio files to create avatars,
- Information on free and paid options to match audio length needs.
10:28 *🎬 Editing and Combining Avatar Videos*
- Instruction on combining avatar files using Adobe Premiere,
- Tips for synchronizing crop effects to ensure seamless visual transition,
- Explanation on exporting the final video for distribution.
13:04 *📹 Uploading to TH-cam with Captions*
- Steps for uploading the final podcast video to TH-cam,
- Process of adding captions using the SRT file with speaker labels,
- Importance of publication settings for video accessibility.
Made with HARPA AI
@@matrixsurfers Thanks for sharing!
Great video and thank you for the audio separation tool. This is a game changer. Earned a sub. Keep up the good work.
@@peterenslin Thank you! Much appreciated!
This is great I have been looking for a tool to separate my podcast audio but couldn’t find any. This is awesome
Thanks! I'm glad you'll find it useful!
Awesome tutorial. I've been searching since yesterday for something like this. Also 1 thing I learned in my search which you may find helpful: remember to click Ai content in details as you're uploading.
@@Meloyadina Thank you! Glad you found it.
Could you please clarify what you mean by click AI content?
@@GenerativeAIEducation sure, when you're uploading, on the details page, as you scroll down below 'this content is not for kids' there's a show more button, and there's a question about whether your content contains Ai generated anything. Click yes, as it will not affect your video ranking, but TH-cam wants to know. I hope that helps.
@@Meloyadina Yes, I've never noticed that. Thanks!
Awesome Guide Tim :) Thanks for taking the extra time to create this! New genre? Hybrid Podcasting? :)
You're welcome! Yes, I like the term! :)
Very good and systematic explanation. Your voice is perfect and the way you explain is reminiscent of a teacher. I subscribed to your channel upon listening to your presentation, quarter-way thru. 👍
@@steps-awareness_rewired Thank you very much, I appreciate your message! I've been a college professor since '93, so I'm glad you picked up on my teaching background 😊
@@GenerativeAIEducation i have been looking for this tool over 12 hours none-stop search. So I can scale the Notebook Podcast LM
Hi there, I love your content. I don’t want to step on your toes but I do believe that you don’t have to necessarily read the whole prompt into the advanced voice mode. You can just copy and paste into custom instructions under settings --> personalization and enable for new chats. Then just remember to turn it off or erase when you’re done.
Thanks for sharing!
You are awesome i have been looking for a tool like this. Thank you
@@Kountry615 Thanks! Glad you found it!
Nice video! Tried you PocketAI Speaker Separation Tool today,great tool but the final mp3 was very low.Regardless still a good tool to have .Cheer!!
Thank you! When you say low, do you mean low volume or low quality? Thanks!
@@GenerativeAIEducation Quality is fine .It was the volume very low compared to the original mp3 i uploaded.I paced both the old and new in my logic pro for edit,I could bearly hear the new mp3.Waves were low too.
@@alltestiaro2391 Thanks for your feedback. I've not had that experience. The volume was the same as the input file every time I did it. Have you tried it again with the same result?
Thanks for the video. I wanted to ask if you can keep the same Avatar (Poscast host) with different guests avatar? If so how to do so?
@@yagelbh You're welcome. Yes, you can keep the same podcast host by selecting the same one in Heygen.
Hello Tim ... I think this is a great idea and a cool tool. Unfortunately, it doesn’t work for me at all. One file is entirely filled with both voices, and the second file is empty. Could it be that this is because my file is in German and the tool only works with English?
Best regards,
Thomas
any updates when the server issues with the speaker separator tool would be fixed? I know it said it would take 48 hrs on the pop up but its been like that for days. Its just such a great tool hope you fix it soon.
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
So you just leave the contents of the interview entirely up to the LLM? As opposed to directing the content?
With this method, you can easily direct the content. Anytime the AI goes off track, you can politely interrupt and steer the conversation back on course.
Hey Tim, your Audio separation tool website not working. Please confirm when it will come back online, thanks
@@GuillermoLinares1967 Hi, it will be back. Having some temporary server issues that are being working on. Sorry for the inconvenience.
@@GenerativeAIEducation Thanks !
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
This is awesome, but I'm getting a 'File upload error'. Any idea why?
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
Great Video. You earned a subscriber :-). Just tried your PocketAI Speaker separation tool but unfortunately it's giving an error. The error says "Invalid CSRF token" - could you please help me with this. Thanks
Thanks! Glad to have you as a subscriber! Please empty your browser cache. After restarting your browser, it should work for you.
@@GenerativeAIEducation Thanks a lot. It worked 🙂
@@CineMagicRewind You're welcome! Glad it's working for you!
What happened to your Audio separation tool? It's not working. Can you please fix that
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
@@GenerativeAIEducation Oh, I can see that. That's a Great Step. But please keep it Free, as you said in your Video!
why does speaker separation TOOL show errors ( Invalid CSRF token.) on my api input now after using 5 times.. I did add billing and more credit. The support chat box is blank.
@@bestholidayresortsports please try clearing your browser cache and restarting your browser
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
tried but keep getting the same error, file upload error, any suggestions, any limits as the file works and is 5 minutes long
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
@@GenerativeAIEducation tried again with NotebookLM file and got this error: Gateway Timeout
The gateway did not receive a timely response from the upstream server or application
It give file upload error continusely. How to overcome from this error please guide.
There are some temporary server issues that are currently being worked on. Sorry for the inconvenience.
@@GenerativeAIEducation look buddy, you should start charging people. i don't find any thing like this on the internet.
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
@@fliu5282 Thanks! Eventually, I'll need to start charging. I just had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/.
For 2 days now your Speaker Separation tool is giving File upload error.
There are some server issues that are working on getting resolved. Sorry for the inconvenience.
I had to get a new server to handle all the processing. I also moved it to a new domain - PodScribeAI.com/. Sorry for the inconvenience!
Lol, it takes a lot of step just to get the subtitle
@@deepdivesessions-dds If all you want is a subtitle, it is as simple as uploading your audio file here: efit.software/podcast2video/transcribe_audio.php