As part of Campaign&#x27;s Audio Trends series, we look at the evolution of podcast technology, the impact that new developments are having on creativity and monetisation, and how podcasters can harness these new capabilities to grow their shows.

Campaign Audio Trends: AI will herald a podcast technology renaissance

The story of a British family who bought a private island near Nicaragua and ended up in a battle to reclaim it from local indigenous people is told in The Price of Paradise

British family's dream that became a nightmare: Podcast reveals how Playboy model and her husband who bought a remote Nicaraguan island to 'live in paradise' became cursed by affairs, kidnap and death | Daily Mail Online

Catch up on your favourite BBC radio show from your favourite DJ right here, whenever you like. Listen without limits with BBC Sounds.

Scottish Football Podcast - Stalemate for Gers – Checkmate for Celtic? - Stalemate for Gers – Checkmate for Celtic? - BBC Sounds

Billed as a rival to the Olympic Games, the Enhanced Games, set to take place in 2025, is a sporting event with a difference; athletes will be allowed to dope. Ian Sample talks to chief sports writer Barney Ronay about where the idea came from and how it’s being sold as an anti-establishment ...

Who really wins if the Enhanced Games go ahead? – podcast | Science | The Guardian

MPs voted this week to ban anyone aged 15 or younger in 2024 from buying cigarettes. If the legislation passes and is enacted, it would be a world first. Ben Quinn reports

Can Rishi Sunak create a smoke-free generation? - podcast | News | The Guardian

As both of their stars continue to rise, Travis and Jason Kelce’s massively popular podcast ‘New Heights’ is reportedly being ‘shopped around’ for a new deal

Kelce Brothers' Podcast Is Being ‘Shopped Around’ for New Deal: Report

At Spotify, we want to equip student creators with the tools and resources needed to harness their creativity and shape the future of audio. Our NextGen program, which is sponsored by the Creator Equity Fund (CEF), is designed to infuse, activate, and grow podcast culture on college campuses ...

NextGen Partners With Howard University Professor Nikole Hannah-Jones on Student Podcasting Course — Spotify

Gabriele Parpiglia, will be a new face at Radio Marte. As a journalist, author, host, and producer, he will be at the helm of a program and the podcast section titled «People of Mars»...

Gabriele Parpiglia Joins Radio Marte with 'Gente di Marte' Podcast

From 2021: Flordelis grew up in a Rio favela, but rose to fame after adopting more than 50 children, becoming a hugely successful gospel singer and winning a seat in congress. And now she is on trial for murder. By Tom Phillips

From the archive: Did Brazil’s evangelical superstar have her husband killed? – podcast | News | The Guardian

With thousands of podcasts to choose from, why would anyone ever opt to listen to something produced and distributed by a brand? Well, here are five excellent examples of what happens when a retailer strikes podcasting gold...

5 of the best branded podcasts of all time and why they work | The Drum

Portcast

portcast

Have you ever felt overwhelmed trying to make sense of dense notes or wished you could listen to them like a podcast while on the go? In this article, I’ll share the tool that could help you turn text into engaging audio podcasts; I believe it could help you learn new things faster and more effectively. Why Turning Notes into Podcasts Is a Game-Changer Did you know that over 50% of people prefer podcasts as their primary way of learning? Podcasts are portable, easy to consume, and perfect for multitasking. But creating a podcast used to feel like a daunting task — until now. Whether you’re a student trying to review lecture notes or a professional preparing for a big presentation, converting written material into something engaging takes time and effort. For me, the challenge was turning long, complex notes into something I could review effortlessly. I wanted to take these notes and transform them into a format I could absorb while driving, exercising, or just relaxing. That’s where NotebookLM came in. What Is NotebookLM and How Does It Work? NotebookLM is an AI-powered tool designed to help users simplify, organize, and transform their notes. Think of it as a smart assistant for your learning process. One of its standout features is the ability to convert text into audio — essentially creating podcasts from your notes. Here’s how I used it: 1. Upload your content: I started by uploading my notes, articles, or YouTube video links into NotebookLM. 2. AI Analysis: The AI analyzed the material, breaking it into clear, logical sections. This was great because it identified the key points I needed to focus on. 3. Text-to-Audio Conversion: The tool converted the notes into an audio format. But here’s the cool part: it wasn’t just a robotic reading. The AI added natural pacing, emphasis, and tone, making the audio feel like a professionally narrated podcast. 4. Download and Listen: Within minutes, I had a polished audio file that I could download and listen to anywhere — on my phone, in the car, or even during a walk. You also can get a shareable link that you can open on any device with the internet connection. The process was so intuitive that I barely had to do any editing, which saved me hours of work. Another cool feature is that you can Customize Audio Overview. You can specify the focus and add instructions for your podcast. This means you can focus on a specific aspect of the subject. This is the example of the podcast: https://notebooklm.google.com/notebook/1076c05e-4438-41db-b44c-2335d5859c24/audio Why NotebookLM Is Perfect for Learners and Creators Before NotebookLM, I often felt stuck. My notes would pile up, and the thought of reviewing them felt overwhelming. But now, I can turn my notes into audio, plug in my headphones, and listen to it on the go or before bedtime. This tool has made learning not just easier but enjoyable. I’ve retained more information because I can revisit the audio anytime. This tool isn’t just for people like me who want to review notes on the go. It’s also great for: Students: Simplify your study material into audio for easier revision.
Professionals: Prepare presentations or training sessions while multitasking.
Content Creators: Turn your ideas into podcasts effortlessly, saving time and boosting productivity. NotebookLM bridges the gap between written and spoken content, making it accessible to everyone. Video DEMO: How to Use NotebookLM Podcast https://youtu.be/fPsugPu9lqI?si=CzreDmclFqbwBSVP&embedable=true The most beautiful part is that NotebookLM is entirely free. So give it a shot and share with me your experience. Cheers! Have you ever felt overwhelmed trying to make sense of dense notes or wished you could listen to them like a podcast while on the go? In this article, I’ll share the tool that could help you turn text into engaging audio podcasts; I believe it could help you learn new things faster and more effectively. Why Turning Notes into Podcasts Is a Game-Changer Did you know that over 50% of people prefer podcasts as their primary way of learning? Podcasts are portable, easy to consume, and perfect for multitasking. But creating a podcast used to feel like a daunting task — until now. 50% of people prefer podcasts Whether you’re a student trying to review lecture notes or a professional preparing for a big presentation, converting written material into something engaging takes time and effort. For me, the challenge was turning long, complex notes into something I could review effortlessly. I wanted to take these notes and transform them into a format I could absorb while driving, exercising, or just relaxing. That’s where NotebookLM came in. What Is NotebookLM and How Does It Work? NotebookLM is an AI-powered tool designed to help users simplify, organize, and transform their notes. Think of it as a smart assistant for your learning process. One of its standout features is the ability to convert text into audio — essentially creating podcasts from your notes. NotebookLM NotebookLM Here’s how I used it: Here’s how I used it: 1. Upload your content : I started by uploading my notes, articles, or YouTube video links into NotebookLM. Upload your content 2. AI Analysis: The AI analyzed the material, breaking it into clear, logical sections. This was great because it identified the key points I needed to focus on. AI Analysis: 3. Text-to-Audio Conversion: The tool converted the notes into an audio format. But here’s the cool part: it wasn’t just a robotic reading. The AI added natural pacing, emphasis, and tone, making the audio feel like a professionally narrated podcast. Text-to-Audio Conversion: 4. Download and Listen : Within minutes, I had a polished audio file that I could download and listen to anywhere — on my phone, in the car, or even during a walk. You also can get a shareable link that you can open on any device with the internet connection. Download and Listen The process was so intuitive that I barely had to do any editing, which saved me hours of work. Another cool feature is that you can Customize Audio Overview. You can specify the focus and add instructions for your podcast. This means you can focus on a specific aspect of the subject. This is the example of the podcast: https://notebooklm.google.com/notebook/1076c05e-4438-41db-b44c-2335d5859c24/audio https://notebooklm.google.com/notebook/1076c05e-4438-41db-b44c-2335d5859c24/audio https://notebooklm.google.com/notebook/1076c05e-4438-41db-b44c-2335d5859c24/audio Why NotebookLM Is Perfect for Learners and Creators Before NotebookLM, I often felt stuck. My notes would pile up, and the thought of reviewing them felt overwhelming. But now, I can turn my notes into audio, plug in my headphones, and listen to it on the go or before bedtime. This tool has made learning not just easier but enjoyable. I’ve retained more information because I can revisit the audio anytime. This tool isn’t just for people like me who want to review notes on the go. It’s also great for: Students: Simplify your study material into audio for easier revision. Professionals: Prepare presentations or training sessions while multitasking. Content Creators: Turn your ideas into podcasts effortlessly, saving time and boosting productivity. Students: Simplify your study material into audio for easier revision. Students: Professionals: Prepare presentations or training sessions while multitasking. Professionals: Content Creators : Turn your ideas into podcasts effortlessly, saving time and boosting productivity. Content Creators NotebookLM bridges the gap between written and spoken content, making it accessible to everyone. Video DEMO: How to Use NotebookLM Podcast https://youtu.be/fPsugPu9lqI?si=CzreDmclFqbwBSVP&embedable=true https://youtu.be/fPsugPu9lqI?si=CzreDmclFqbwBSVP&embedable=true The most beautiful part is that NotebookLM is entirely free . So give it a shot and share with me your experience. NotebookLM is entirely free Cheers!

I Turned Notes Into A Podcast: How to Use NotebookLM Podcast DEMO

Podcast content is growing each year, with over 4.5 million active podcasts globally — and nearly 30 million episodes published in 2023 alone — the challenge of discovering relevant content has become increasingly complex. Podyssey emerged as a solution to this challenge, with its AI-driven approach to podcast curation and personalization. Ahmad Saleem, co-founder and CEO of Podyssey aims to set new standards for how listeners find and engage with relevant podcast content. "In the 1980s and 90s, the antidote to a mid-life crisis was starting a suburban band. Now it is starting a podcast.” Historically, the only way to find relevant podcast content was by manually searching through titles of shows and episode descriptions, relying heavily on ratings, reviews, and basic categorization. But these traditional discovery methods have proven insufficient as the volume of content continues to increase. Listeners often find themselves overwhelmed by choices or stuck in content bubbles, missing out on potentially valuable podcasts that fall outside of their usual listening patterns. “As a listener, the task of shifting through this new content is onerous and daunting. In fact, just finding that content you already like is becoming more and more daunting,” comments Saleem. “This is largely because there is more content to sift through; but also because the method for doing so is increasingly outdated.” Podyssey's approach puts curated content discovery at the forefront. At its heart lies a powerful and unique search engine that leverages cutting-edge technology to understand the actual discussions within podcasts. This isn't just an incremental improvement – it's a complete paradigm shift in how listeners find and consume podcast content. "Traditional platforms have to rely on the genre or content classifications applied by the podcaster to their content," explains Saleem. “This approach might have worked in simpler times, but today's podcast landscape defies such basic categorization. Take Joe Rogan's podcast, for instance – trying to pin it down to a single genre is like trying to fit a square peg in a round hole. The reality is that podcast content has become more genre-fluid than ever before, particularly in long-form formats.” The technical innovation behind Podyssey is substantial. The platform employs a sophisticated combination of audio recognition algorithms and natural language processing, utilizing bi-encoders and cross-encoders to analyze user queries. This goes beyond simple keyword matching, allowing the system to understand the intent behind searches and deliver more relevant results, even without exact matches. "There is nothing else like Podyssey out there," according to Saleem. "We are the only podcast platform that allows listeners to curate their listening based on the content being discussed." This means listeners can finally break free from the constraints of genre-based discovery. Podyssey goes beyond search capabilities. By studying listener behavior – from search patterns to engagement rates with specific clips – the platform creates highly detailed user profiles that enable complete personalization. Instead of sitting through a three-hour episode for ten minutes of relevant content, users can enjoy sixty minutes of carefully curated material drawn from various sources, all focused on their specific interests. The company’s journey is about more than just improving podcast discovery – it's about reimagining the entire podcast ecosystem. While traditional platforms have remained relatively unchanged since the industry's inception, Podyssey represents a fundamental shift in how both creators and listeners engage with podcast content. By removing artificial boundaries and putting content relationships at the center of the experience, Podyssey isn't just participating in the podcast revolution – it's leading it. The message is clear: the future of podcast discovery has arrived, and it's time for listeners to break free from the constraints of traditional platforms. Podyssey stands ready to ensure that every listener can find exactly what they're looking for – and discover content they never knew they needed. Podcast content is growing each year, with over 4.5 million active podcasts globally — and nearly 30 million episodes published in 2023 alone — the challenge of discovering relevant content has become increasingly complex. Podyssey emerged as a solution to this challenge, with its AI-driven approach to podcast curation and personalization. Ahmad Saleem, co-founder and CEO of Podyssey aims to set new standards for how listeners find and engage with relevant podcast content. Podyssey "In the 1980s and 90s, the antidote to a mid-life crisis was starting a suburban band. Now it is starting a podcast.” "In the 1980s and 90s, the antidote to a mid-life crisis was starting a suburban band. Now it is starting a podcast.” Historically, the only way to find relevant podcast content was by manually searching through titles of shows and episode descriptions, relying heavily on ratings, reviews, and basic categorization. But these traditional discovery methods have proven insufficient as the volume of content continues to increase. Listeners often find themselves overwhelmed by choices or stuck in content bubbles, missing out on potentially valuable podcasts that fall outside of their usual listening patterns. “As a listener, the task of shifting through this new content is onerous and daunting. In fact, just finding that content you already like is becoming more and more daunting,” comments Saleem. “This is largely because there is more content to sift through; but also because the method for doing so is increasingly outdated.” Podyssey's approach puts curated content discovery at the forefront. At its heart lies a powerful and unique search engine that leverages cutting-edge technology to understand the actual discussions within podcasts. This isn't just an incremental improvement – it's a complete paradigm shift in how listeners find and consume podcast content. "Traditional platforms have to rely on the genre or content classifications applied by the podcaster to their content," explains Saleem. “This approach might have worked in simpler times, but today's podcast landscape defies such basic categorization. Take Joe Rogan's podcast, for instance – trying to pin it down to a single genre is like trying to fit a square peg in a round hole. The reality is that podcast content has become more genre-fluid than ever before, particularly in long-form formats.” The technical innovation behind Podyssey is substantial. The platform employs a sophisticated combination of audio recognition algorithms and natural language processing, utilizing bi-encoders and cross-encoders to analyze user queries. This goes beyond simple keyword matching, allowing the system to understand the intent behind searches and deliver more relevant results, even without exact matches. "There is nothing else like Podyssey out there," according to Saleem. "We are the only podcast platform that allows listeners to curate their listening based on the content being discussed." This means listeners can finally break free from the constraints of genre-based discovery. Podyssey goes beyond search capabilities. By studying listener behavior – from search patterns to engagement rates with specific clips – the platform creates highly detailed user profiles that enable complete personalization. Instead of sitting through a three-hour episode for ten minutes of relevant content, users can enjoy sixty minutes of carefully curated material drawn from various sources, all focused on their specific interests. The company’s journey is about more than just improving podcast discovery – it's about reimagining the entire podcast ecosystem. While traditional platforms have remained relatively unchanged since the industry's inception, Podyssey represents a fundamental shift in how both creators and listeners engage with podcast content. By removing artificial boundaries and putting content relationships at the center of the experience, Podyssey isn't just participating in the podcast revolution – it's leading it. The message is clear: the future of podcast discovery has arrived, and it's time for listeners to break free from the constraints of traditional platforms. Podyssey stands ready to ensure that every listener can find exactly what they're looking for – and discover content they never knew they needed.

The Future of Podcast Curation: Podyssey's AI-Driven Approach to Content Discovery

AI image manipulation tools have come a long way in the last few years. It’s quite easy nowadays to create beautiful, stylistic portraits of people and animals. But AI models are highly unpredictable. So most tools rely on the user (or some human) to weed out bad generations and find the best one. This is the classic “human in the loop” problem that often plagues AI tools. Turns out, with some clever tricks and careful tuning, you can build a pipeline that reliably works for the vast majority of pets. It is extremely resilient to variations in pose, lighting etc. In this post, I’ll dive deeper into how it works and all the neat little tricks that enable this. Here’s some examples of portraits you can generate with this pipeline. Let’s get started! The Key Ingredients IPAdapter The crux of the technique is the IPAdapter. It’s essentially a way to prompt a model using an image instead of text (it literally stands for Image Prompt Adapter). So instead of taking a text embeddings, it uses an image to get the embeddings. This is super powerful because it can accurately capture the style and structure in an image directly, instead of someone having to translate what they want from an image into text. In our ComfyUI IPAdapter node, we have two inputs, one for style and one for composition. We use a watercolor painting image for style, and feed the original image for composition (since we want to keep the same composition, but change the style). ControlNets Now that we have a way to keep the style consistent, we can turn our attention to faithfully representing the pet. IPAdapters bias heavily towards image quality, and image likeness suffers. So we need to do something to be able to keep the output looking like the same object as the input. The answer to that is ControlNet. ControlNets are another cool technique to provide additional constraints to the image generation process. Using a ControlNet, you can specify constraints in the form of edges, depth, human pose etc. A great feature of ControlNets is that they can be stacked. So you can have an edge controlnet that forces the output to have similar edges as the input, and also a depth controlnet that forces the output to have a similar depth profile. And that’s exactly what I do here. It turns out that controlnets are not just stackable with other controlnets, but they can also work in tandem with IPAdapter mentioned above. And so those are the tools we’ll use for this - IPAdapter with a source image to get the style, ControlNet with canny edge detector to constrain based on edges, and controlnet with depth to constrain based on depth profile. That’s really all you need in terms of techniques, but what I’ve learnt from experimenting with machine learning for production is that a lot of the value of these things comes from taking the time to tune all your parameters perfectly. So I want to talk a little bit about that. Finetuning Have you ever found a model with amazing example outputs, tried it on your own images and realized they look terrible? Often, the only reason for that is that the model hasn’t been finetuned for your images. It can feel like a complete blocker sometimes, because where do we even start with finetuning a pre-trained model?! Here’s what I’ve learnt about the topic. This extends beyond this particular pipeline too, so it’s good knowledge to have generally. ControlNets ControlNets are very powerful, so you have to be careful to control their effect on the output. Luckily, the custom nodes in ComfyUI let us reduce the effect of controlnets, and also stop their effects at any point. So we set the edge detector to 75% strength and make it stop influencing the generation at 75% and the depth detector stops at 30%. The reason we stop them at the end rather than just reducing their strength is that this allows the network to “clean up” any artifacts caused by them in the last few steps without being constrained externally. It just makes the image prettier. So it’s using just it’s training data to make things look as nice as possible, ignoring the edges and depth. The other big thing to tune is the KSampler. There’s a lot of little things going on here, but I’ll just briefly touch on some of them: KSampler - Steps First we have the steps. This is literally the number of times the model will repeatedly run. The more it runs, the more stylized your output gets, and the further away it will get from the original image. The effects of this are often not that obvious, so it’s worth playing around with it. KSampler - CFG Then there’s CFG. I honestly don’t fully understand this, but from its name - Classifier Free Guidance - I’m assuming it controls how much the model is allowed to modify the image unconstrained by the prompts in order to make it look better. This also affects the output image significantly, so is worth playing around with. Denoise Another neat little trick I use here is to start the image generation process with the input image  instead of a blank image, and keep the denoising low. This ensures that the output will look similar in terms of colors and textures. Text Prompt One thing you’ll notice I never mentioned is the text prompt until now! Surprising, since that’s usually the only conditioning that you normally provide to diffusion models. But in this case, we have so many other ways of conditioning that the text prompts usually just get in the way. So in this case, the prompt is literally just “a dog”. I do use the text prompt a little more in some of the more stylized portraits, like the chef dog or the one in the bathroom. Adding accessories In essence, this is more or less just an “AI Filter” that converts images into watercolor portraits. But it’s amazing how flexible this can be. For example, to make the portrait of the dog taking a shower, I literally just put images together in an image editing tool and used that as the input! The model takes care of unifying everything and cleaning up the image. Conclusion Now remove the background, add some text and Boom! You have a beautiful portrait that captures all the little details of your pet, and always paints them in the best light! Huge thanks to @cubiq for his work on ComfyUI nodes and his awesome explainer series on youtube! Most of this pipeline was built and explained by him in his videos. If you want a pet portrait without going through all this trouble, consider buying one from here: pawprints.pinenlime.com! AI image manipulation tools have come a long way in the last few years. It’s quite easy nowadays to create beautiful, stylistic portraits of people and animals. But AI models are highly unpredictable. So most tools rely on the user (or some human) to weed out bad generations and find the best one. This is the classic “human in the loop” problem that often plagues AI tools. Turns out, with some clever tricks and careful tuning, you can build a pipeline that reliably works for the vast majority of pets. It is extremely resilient to variations in pose, lighting etc. In this post, I’ll dive deeper into how it works and all the neat little tricks that enable this. Here’s some examples of portraits you can generate with this pipeline. Let’s get started! The Key Ingredients IPAdapter The crux of the technique is the IPAdapter. It’s essentially a way to prompt a model using an image instead of text (it literally stands for Image Prompt Adapter). So instead of taking a text embeddings, it uses an image to get the embeddings. This is super powerful because it can accurately capture the style and structure in an image directly, instead of someone having to translate what they want from an image into text. In our ComfyUI IPAdapter node, we have two inputs, one for style and one for composition. We use a watercolor painting image for style, and feed the original image for composition (since we want to keep the same composition, but change the style). ControlNets Now that we have a way to keep the style consistent, we can turn our attention to faithfully representing the pet. IPAdapters bias heavily towards image quality, and image likeness suffers. So we need to do something to be able to keep the output looking like the same object as the input. The answer to that is ControlNet. ControlNets are another cool technique to provide additional constraints to the image generation process. Using a ControlNet, you can specify constraints in the form of edges, depth, human pose etc. A great feature of ControlNets is that they can be stacked. So you can have an edge controlnet that forces the output to have similar edges as the input, and also a depth controlnet that forces the output to have a similar depth profile. And that’s exactly what I do here. It turns out that controlnets are not just stackable with other controlnets, but they can also work in tandem with IPAdapter mentioned above. And so those are the tools we’ll use for this - IPAdapter with a source image to get the style, ControlNet with canny edge detector to constrain based on edges, and controlnet with depth to constrain based on depth profile. That’s really all you need in terms of techniques, but what I’ve learnt from experimenting with machine learning for production is that a lot of the value of these things comes from taking the time to tune all your parameters perfectly. So I want to talk a little bit about that. Finetuning Have you ever found a model with amazing example outputs, tried it on your own images and realized they look terrible? Often, the only reason for that is that the model hasn’t been finetuned for your images. It can feel like a complete blocker sometimes, because where do we even start with finetuning a pre-trained model?! Here’s what I’ve learnt about the topic. This extends beyond this particular pipeline too, so it’s good knowledge to have generally. ControlNets ControlNets are very powerful, so you have to be careful to control their effect on the output. Luckily, the custom nodes in ComfyUI let us reduce the effect of controlnets, and also stop their effects at any point. So we set the edge detector to 75% strength and make it stop influencing the generation at 75% and the depth detector stops at 30%. The reason we stop them at the end rather than just reducing their strength is that this allows the network to “clean up” any artifacts caused by them in the last few steps without being constrained externally. It just makes the image prettier. So it’s using just it’s training data to make things look as nice as possible, ignoring the edges and depth. The other big thing to tune is the KSampler. There’s a lot of little things going on here, but I’ll just briefly touch on some of them: KSampler - Steps First we have the steps. This is literally the number of times the model will repeatedly run. The more it runs, the more stylized your output gets, and the further away it will get from the original image. The effects of this are often not that obvious, so it’s worth playing around with it. KSampler - CFG Then there’s CFG. I honestly don’t fully understand this, but from its name - Classifier Free Guidance - I’m assuming it controls how much the model is allowed to modify the image unconstrained by the prompts in order to make it look better. This also affects the output image significantly, so is worth playing around with. Denoise Another neat little trick I use here is to start the image generation process with the input image  instead of a blank image, and keep the denoising low. This ensures that the output will look similar in terms of colors and textures. Text Prompt One thing you’ll notice I never mentioned is the text prompt until now! Surprising, since that’s usually the only conditioning that you normally provide to diffusion models. But in this case, we have so many other ways of conditioning that the text prompts usually just get in the way. So in this case, the prompt is literally just “a dog”. I do use the text prompt a little more in some of the more stylized portraits, like the chef dog or the one in the bathroom. Adding accessories In essence, this is more or less just an “AI Filter” that converts images into watercolor portraits. But it’s amazing how flexible this can be. For example, to make the portrait of the dog taking a shower, I literally just put images together in an image editing tool and used that as the input! The model takes care of unifying everything and cleaning up the image. Conclusion Now remove the background, add some text and Boom! You have a beautiful portrait that captures all the little details of your pet, and always paints them in the best light! Huge thanks to @cubiq for his work on ComfyUI nodes and his awesome explainer series on youtube! Most of this pipeline was built and explained by him in his videos. If you want a pet portrait without going through all this trouble, consider buying one from here: pawprints.pinenlime.com!

Make Masterpiece Pet Portraits with ComfyUI

ComfyUI এর সাথে মাস্টারপিস পোট্রেট পোট্রেট তৈরি করুন

Erstellen Sie meisterhafte Tierporträts mit ComfyUI

Crea retratos de mascotas de gran calidad con ComfyUI

Créez des portraits d'animaux de compagnie de qualité avec ComfyUI

ComfyUI के साथ पालतू जानवरों के बेहतरीन चित्र बनाएं

ComfyUI で傑作ペットポートレートを作ろう

ComfyUI로 걸작 애완동물 초상화 만들기

Crie retratos de animais de estimação de obras-primas com ComfyUI

Создавайте шедевральные портреты домашних животных с помощью ComfyUI

ComfyUI ile Başyapıt Evcil Hayvan Portreleri Yapın

Tạo ảnh chân dung thú cưng tuyệt đẹp với ComfyUI

使用 ComfyUI 制作宠物肖像杰作

https://www.youtube.com/watch?v=jvqFAi7vkBc&embedable=true&transcript=true&long=true

"Compute is Going to the Currency of the Future," says Sam Altman on the Lex Fridman Podcast 

লেক্স ফ্রিডম্যান পডকাস্টে স্যাম অল্টম্যান বলেছেন, "কম্পিউট ভবিষ্যতের মুদ্রায় যাচ্ছে"

„Compute wird zur Währung der Zukunft“, sagt Sam Altman im Lex Fridman Podcast

"La informática se está convirtiendo en la moneda del futuro", dice Sam Altman en el podcast Lex Fridman

"Le calcul devient la monnaie du futur", déclare Sam Altman sur le podcast Lex Fridman

लेक्स फ्रिडमैन पॉडकास्ट पर सैम ऑल्टमैन कहते हैं, "कंप्यूट भविष्य की मुद्रा की ओर जा रहा है।"

「コンピューティングは未来の通貨になりつつある」とサム・アルトマン氏がレックス・フリッドマン・ポッドキャストで語る

Lex Fridman Podcast에서 Sam Altman은 "컴퓨팅은 미래의 통화로 변모하고 있습니다."라고 말합니다.

“A computação está indo para a moeda do futuro”, diz Sam Altman no Lex Fridman Podcast

«Вычисления становятся валютой будущего», — говорит Сэм Альтман в подкасте Lex Fridman.

Lex Fridman Podcast'inde Sam Altman "Bilgi İşlem Geleceğin Para Birimi'ne Gidiyor" diyor

Sam Altman nói trên Lex Fridman Podcast: “Máy tính đang hướng tới tiền tệ của tương lai”

Sam Altman 在 Lex Fridman 播客上表示：“计算将成为未来的货币”

92 Stories To Learn About Hackernoon Podcast

I write a newsletter called Above Average, where I talk about the second-order insights behind everything that is happening in big tech. If you are in tech and don’t want to be average, . subscribe to it A lot of people want podcasts transcribed and read instead of listening to them. We can go one level up and even extract insights from the podcasts as well using Open AI API. Here’s my tweet exchange, which provoked this experiment. So here is what we are going to do. And it will be slightly different from what I suggested in the tweet. The goal is to pick a YouTube video and get a transcription of that video, and then using prompt engineering, we extract insights, ideas, book quotes & summaries, etc., To Summarize, we achieve our goal in three steps: Step 1: Select a YouTube podcast video Step 2: Transcribe the video Step 3: Get Insights from the transcription Step 1: Select a YouTube podcast video A recent podcast conversation that broke YouTube was Jeff Bezos on Lex Friedman's podcast. So, for this exercise, I will pick this . video Step 2: Transcribe the video I used langchain along with Open AI’s audio-to-text model whisper to transcribe the youtube video. As usual you would need your OpenAI secret key to use the following script. YouTubeAudioLoader import os
import sys
import openai

from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file
openai.api_key  = os.environ['OPENAI_API_KEY']


## youtube video's audio loader - langchain 
from langchain_community.document_loaders.blob_loaders.youtube_audio import YoutubeAudioLoader
from langchain_community.document_loaders.generic import GenericLoader
from langchain_community.document_loaders.parsers import OpenAIWhisperParser #, OpenAIWhisperParserLocal

url="https://www.youtube.com/watch?v=DcWqzZ3I2cY&ab_channel=LexFridman"
save_dir="outputs/youtube/"
loader = GenericLoader(
     YoutubeAudioLoader([url],save_dir),
     OpenAIWhisperParser()
 )
docs = loader.load()
print(docs[0].page_content[0:500])

# Specify the file path where you want to save the text
file_path = "audio-transcript.txt"
try:
    with open(file_path, 'a', encoding='utf-8') as file:
        for doc in docs:
            file.write(doc.page_content)
    print(f'Large text saved to {file_path}')
except FileNotFoundError:
    print(f"Error: Input file '{file_path}' not found.")
except Exception as e:
    print(f"An error occurred: {e}") You might see the following error while running this script, and I pasted the solution that works in case you are using a Windows system. Postprocessing: and not found. Please install or provide the path using –ffmpeg-location. ERROR: ffprobe ffmpeg Running this script will generate the transcript and store it in a text file audio-transcript.txt. Step 3: Extract insights from the conversation To extract insights, I am using Open AI API, and here is the script. The code loads the transcript text and passes it along with a prompt designed to extract insights, people & books. To get more interesting things out of this conversation, you can come up with a more interesting prompt. Note that the file name is slightly different because I had to cut the transcript to a short length since my completion query to Open AI API exceeded my TPM limits. import os
import sys
import openai
import shutil
from pprint import pprint

from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv()) # read local .env file
openai.api_key  = os.environ['OPENAI_API_KEY']

client = openai.OpenAI()

file_path = "audio-transcript-copy.txt"
try:
    with open(file_path, 'r', encoding='utf-8') as file:
        long_text = file.read()
    print(f'{file_path} is rad')
except FileNotFoundError:
    print(f"Error: Input file '{file_path}' not found.")
except Exception as e:
    print(f"An error occurred: {e}")

prompt2 = f"""
You will be provided with text deilimited by triple quotes.
The given text is a podcast transcript.

Provide the host and guest name.
Summarize the transcript in to 10 points.

If there are any people referred in the transcript. Extract the people mentioned and list them along with some info about them in the following format
1. Person 1's Name: Person 1's profession or what he or she is known for or the context in which he or she was referred to.
2. Person 2's Name: Person 2's profession or what he or she is known for or the context in which he or she was referred to.
...
2. Person N's Name: Person N's profession or what he or she is known for or the context in which he or she was referred to.
If the transcript doesnt contain refereces to any people then simply write \"No people referred to in the conversation.\"

Extract the books mentioned and list them in the following format.
1. Book 1's Title: Context in which the book was referred to.
2. Book 2's Title: Context in which the book was referred to.
...
N. Book N's Title: Context in which the book was referred to.
If the transcript doesnt contain refereces to any books then simply write \"No books referred to in the conversation.\"

IF you find any inspiration quotoes complie them in to a list.

\"\"\"{long_text}\"\"\"
"""

response = client.chat.completions.create(
  model="gpt-4",
  messages=[
    {
      "role": "user",
      "content": prompt2
    }
  ],
  temperature=0.7,
  #max_tokens=64,
  #top_p=1
)

print(response.choices[0].message.content) Here is what the output I got: Result: Lex Freidman & Jeff Bezos Podcast Summary Can provide a service to podcasters to generate smart transcripts with insights. This would be a B2B play. AI PRODUCT IDEA ALERT 1: Instead of a service to podcast creators, it could be B2C customers who listen to podcasts and want to read through podcasts and create their own library of insights. AI PRODUCT IDEA ALERT 2: Expect both these ideas to be used by existing podcast hosting companies like Spotify & launch these ideas as new features. If I was a Product Manager in any such companies I would be pitching them by now. That’s it for day 5 of 100 Days of AI. Follow me on , for latest updates on 100 days of AI or & Check out Twitter LinkedIn bookmark this page Day 4: How to Use ChatGPT to be More Productive? Also published . here

100 Days of AI Day 5: Transcription and Extracting Insight from Podcasts with OpenAI

If you don’t know, I write a newsletter called Above Average, where I talk about the second-order insights behind everything that is happening in the big tech. If you are into tech and want to be above average, . subscribe to it I have always admired Scott Galloway's newsletter, No Mercy, No Malice. One unique thing Scott does with his newsletter is that he hired his friend George Hahn to convert the newsletter into a podcast, which is published every week in his podcast feed . here I don’t have a friend like George Hahn, but I know AI voices have become very life-like with recent advances. So I thought, why not convert my newsletter into a podcast? So, I played around and wrote a script to use Open AI’s text-to-speech API to convert my newsletter post into its audio version. To follow along and use this script, you need Open AI credits and an Open AI Secret Key. Here is the code I used. from openai import OpenAI


client = OpenAI()
client.api_key = 'YOUR SECRET KEY'
txt = """1/ Google is the dark horse in AI

Only Google can mess up a good thing multiple times. Google has struggled to play the perception game that has turned against it after the launch of ChatGPT and with Sathya’s offense on all things AI.

Google released an impressive Gemini AI preview series and the success lasted for two days. Before media started to observe that the demo is not so much as a demo but series of well constructed prompts. Or a series of good demos complied to one great demo.

This is obviously putting Google back again in the perception wars of AI. The keyword here is perception.

If everything is perception & marketing than nothing in the world will be a surprise. In case of Google in AI, don’t let the perception confuse you. Google is still the dark horse in AI. Google was talking about AI in every Pixel device launch since last 5 years while the tech industry and VCs were saying that Crypto is the next big thing.

The day to day news cycle exists to take your attention and make you click & confuse you. AI is a continuous innovation not a discontinuous one. Google has strong fundamentals in AI and the AI cycle is much longer than 12 months of ChatGPT. Google has shipped more AI products via Gmail, Google Search, Ads and most importantly Google Pixel than any other company. So just because Google has failed to market itself doesn’t mean its a loser in AI.

Google is still a dark horse in AI."""

response = client.audio.speech.create(
    model="tts-1",
    voice="onyx",
    input=txt,
)

response.stream_to_file("output.mp3") The newsletter post I took in this example is from . Here is the output . this edition result it generated The result was not as good as George Hahn’s voice, but it’s much better than most of the audio book out there. This idea can be expanded further to create a product that takes a new newsletter when published, converts it automatically to a podcast, and publishes it in the podcast feed. George Hahn as a Service. AI PRODUCT ALERT: That’s it for day 1 of AI. Follow me on for the latest updates on 100 days of AI or . Twitter bookmark this page Also published . here

100 Days of AI Day 1: From Newsletter to Podcast, Leveraging AI for Audio Transformation

OpenBB Podcast Transcript: Empowering Finance for All With Didier Lopes

When hearing about the behemoth " " podcasts may be among the last things to cross your imagination. After all, it's not hours-long, stuffed dialogues that get the viewer through a dozen various emotions that fueled the platform's unmatched popularity and catapulted it among the top apps with the most considerable penetration rates. TikTok The short-form videos condensed the whole meaning and purpose of the piece of content in a matter of sentences and hooked users by delivering information in the most straightforward and captivating ways. Through its appeal and mainstreamness, TikTok can reach more than adults monthly. It sees its popularity going nowhere anytime soon, especially now that podcasters are getting a taste of the benefits it can deliver. 1 billion TikTok has lately embraced new purposes and become a thriving ecosystem for podcasters to have a louder voice and connect with the categories of internet users they're targeting. And because of Monolith, the large-scale, real-time recommendation system embedded in TikTok's algorithm made it such a reliable platform for those desiring content tailored to their needs and preferences, podcasters or aspiring podcasters can conduct their work with more support. And as seasoned podcasters are well aware, the journey to a thriving audience involves a multifaceted strategy. TikTok, coupled with niche tools and services designed to , excels beyond compare among social media platforms. help content creators in their quest for audience growth So, how can a platform designed and aggrandized for briefly summarized content become such a haunted tool for the opposite type of video? And what are some examples of world-famous podcasters who nailed it? Gen Z looks at podcasts as a leading source of information. Gen Z unearths fresh podcasts at a speed rate incomparable with any other generation, being the first ones flocking to the platform and slowly leaving others such as heavyweight Facebook and Instagram behind. Longing for a piece of the pie represented by the booming popularity of TikTok podcast viewing, quick-on-the-uptake platforms have mobilized in their attempt to meet the changing demands of this growing watcher category through features and options similar to those of TikTok. Spotify, the most revered music platform at the moment, has long expanded beyond its initial scope of allowing independent artists in their developmental stages and giant record labels to upload content, fairly paying each contributor for their share. Spotify is now a platform where podcasters are at home, and more and more look to it to boost their content's popularity and reach. Yet, it's premature and rushed to claim that Spotify will go as far as TikTok succeeded in the podcast game and build such a kingdom. Podcast creators are migrating to TikTok for its unparalleled potential Creators can use numerous ways to promote their channels and content on TikTok. Probably one of the most straightforward and accessible methods is to take the route of comments. That section allows users to share their thoughts, which often take the form of means to make one's digital offerings acknowledged. Undoubtedly, TikTok couldn't have made it among the myriad platforms aimed at publicizing podcasts without a specifically designed feature. In light of an increasingly refined user base, the " " section is precisely what a podcaster or any other type of long-format content creator needs to grow their following and gain notoriety based on their exact type of content. This focal point of the platform wins organic growth for any type of podcaster because it recommends videos after analyzing the user interests instead of how large the account's following is. Genuine effort is at play here! Those searching for videos on human evolution shouldn't be obscured by content speculating on the world's state a century from now. For Your Feed Celebrity Memoirs Book Club – one of the most successful stories to look to With over 305k followers at the moment and a growing cohort of viewers familiar with this podcast, Celebrity Memoirs Book Club has grown from serving a small user base of several hundred to a score that doesn't stop rising. This weekly podcast began over three years ago and has built a passionate following ever since on their platform. What fueled its ascension to popularity are the topics approached, serving as a fantastic means to help those with tight schedules learn the highlights in the celebrity world. After all, who wouldn't want to skip the part where they consume endless hours of content just to extract an essential that could have otherwise been delivered more succinctly and less boringly? Not to mention the pandemic of deceptive clickbait and misleading headlines that are the bane of today's online world. Celebrity Memoirs Book Club is the channel where today's internauts repelled by lengthy memoirs can elevate their knowledge about celebrities, famous individuals, and everything noteworthy. By looking at the hosts' ways of delivering their message and having watchers glued to their displays, more podcasters aspiring to achieve tremendous fame can take their efforts to the next level. Diary of a CEO – another example of a well-done job For the business world has always been one of the hottest (and most complex) topics; having interested parties wrap their heads around it, the podcasters approaching this topic in the savviest and cleverest ways are on the path to achieving unmatched success. Diary of a CEO is where collections abounding in wisdom catch the interest of individuals of any age category. The hosts approach subjects of both failure and triumph, making viewers feel empowered and optimistic about their future. There's something inescapable about content that tackles the ins and outs of such a complex topic and shades light on the most intricate aspects, whether it's about how the or how everyone can tap into their unearthed persuasive talker. rich evade taxes The wrap-up TikTok, conceived with the exact opposite thought in mind rather than dishing out minutes-long videos, has managed to meet more than its original purpose. Now, podcasters find a great ally in its technology and potential, and users flock from different podcast-based platforms to their competitor, TikTok, for numerous reasons, whether it’s the pursuit of entertainment or a thirst for education.

TikTok's Podcast Revolution: A Surprising Ally for Creators and Audiences

Christian Science by Mark Twain, is part of the HackerNoon Books Series. You can jump to any chapter in this book . CHAPTER XIII here CHAPTER XIII In drawing Mrs. Eddy's portrait it has been my purpose to restrict myself to materials furnished by herself, and I believe I have done that. If I have misinterpreted any of her acts, it was not done intentionally. It will be noticed that in skeletonizing a list of the qualities which have carried her to the dizzy summit which she occupies, I have not mentioned the power which was the commanding force employed in achieving that lofty flight. It did not belong in that list; it was a force that was not a detail of her character, but was an outside one. It was the power which proceeded from her people's recognition of her as a supernatural personage, conveyer of the Latest Word, and divinely commissioned to deliver it to the world. The form which such a recognition takes, consciously or unconsciously, is worship; and worship does not question nor criticize, it obeys. The object of it does not need to coddle it, bribe it, beguile it, reason with it, convince it—it commands it; that is sufficient; the obedience rendered is not reluctant, but prompt and whole-hearted. Admiration for a Napoleon, confidence in him, pride in him, affection for him, can lift him high and carry him far; and these are forms of worship, and are strong forces, but they are worship of a mere human being, after all, and are infinitely feeble, as compared with those that are generated by that other worship, the worship of a divine personage. Mrs. Eddy has this efficient worship, this massed and centralized force, this force which is indifferent to opposition, untroubled by fear, and goes to battle singing, like Cromwell's soldiers; and while she has it she can command and it will obey, and maintain her on her throne, and extend her empire. She will have it until she dies; and then we shall see a curious and interesting further development of her revolutionary work begin. About HackerNoon Book Series: We bring you the most important technical, scientific, and insightful public domain books. This book is part of the public domain. Mark Twain (2004). Christian Science. Urbana, Illinois: Project Gutenberg. Retrieved October 2022 https://www.gutenberg.org/cache/epub/3187/pg3187-images.html This eBook is for the use of anyone anywhere at no cost and with almost no restrictions whatsoever. You may copy it, give it away or re-use it under the terms of the Project Gutenberg License included with this eBook or online at , located at . www.gutenberg.org https://www.gutenberg.org/policy/license.html

Stories, News & Mentions about PORTCAST

Portcast’s Stories on HackerNoon

Portcast's News & Mentions