Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

NotebookLM fans, ever wished for more customization options? Open-sourcing Doc2Podcast, a simple Next.js app that generates customized podcasts from your docs. Customizations include: - # of speakers - Choice of speakers - Conversation length - Convo style & instructions

Misbah Syed

8,296 subscribers

51,145 views • 1 year ago •via X (Twitter)

Education Science & Technology Arts

Anya Rossi• Live Now

Private livecam show

10 Comments

Misbah Syed1 year ago

It is connected to a @langflow_ai API, so you could further customize the flow to: - Add more document types - URLs for Web Scraping - Run it entirely locally with local LLM and TTS S/o to João Oliveira for building the awesome flow! Repo link:

SGM1 year ago

@nextjs @MisbahSy Can I give a suggestion can it 1) can it be multilingual 2) ability to prompt like the example below perhaps this is something you guys can work for in the near future the customisation feature and multi hosts is cracker nice job

Misbah Syed1 year ago

@nextjs Those are really nice suggestions. I haven’t tried multilingual documents, but my feel is since whisper is multilingual, it should work. Adding stability TTS would be pretty cool. Lemme try adding.

Yash1 year ago

@nextjs Love it 🔥🚀

Misbah Syed1 year ago

@nextjs 🙌

Moses and AI1 year ago

@nextjs My problem with NotebookLM is that one cannot control the structure of the podcast. I wanted it to use direct quotes but it just goes wild doing the default

Misbah Syed1 year ago

@nextjs That’s true

Kris Krakowiak1 year ago

@nextjs we need more languages support

Misbah Syed1 year ago

@nextjs Give it a try with multilingual documents, whisper supports many languages

Me, Myself & I1 year ago

Esteemed colleagues, I am writing to express my concern about the rapid pace of development within the AI industry. The speed at which new applications are being created is outpacing our ability to develop our own ideas and bring them to market. This is a serious issue that requires our immediate attention. Thank you for your time and consideration. Sincerely, [I love AI ]

Related Videos

We just released Universal-3 Pro. And it's free for all of February. LLM-style control over transcription: not just keywords, but actual instructions: → "Be more verbatim, capture filler words" → "This is a medical conversation" → "Label speakers as doctor vs. patient" One prompt. Hundreds of calls. Consistent output.

We just released Universal-3 Pro. And it's free for all of February. LLM-style control over transcription: not just keywords, but actual instructions: → "Be more verbatim, capture filler words" → "This is a medical conversation" → "Label speakers as doctor vs. patient" One prompt. Hundreds of calls. Consistent output.

AssemblyAI

11,499 views • 6 months ago

A small outfit customization preview for HakuSN Phoenix! 🌸 The first part shows a few outfit combinations I made with the model, and the second part gives a broad overview of most of the clothing parameters available for the female body. The remake includes many more mix-and-match options and customization possibilities, so you can create a look that fits your own style. More previews coming soon! #HakuSNPhoenixCustomizableModel #CustomizableVtuber #vtuber

A small outfit customization preview for HakuSN Phoenix! 🌸 The first part shows a few outfit combinations I made with the model, and the second part gives a broad overview of most of the clothing parameters available for the female body. The remake includes many more mix-and-match options and customization possibilities, so you can create a look that fits your own style. More previews coming soon! #HakuSNPhoenixCustomizableModel #CustomizableVtuber #vtuber

HakuSN Phoenix CustomizableModel OUT now

14,464 views • 2 months ago

Introducing NotebookLlama - an open-source version of NotebookLM! 📓🦙 NotebookLlama is a full implementation of NotebookLM that includes all the capabilities that makes it so great for researchers+business users: ✅ Create a knowledge repository of documents. Has likely higher accuracy than NotebookLM since it’s using LlamaCloud under the hood for high-quality parsing/extraction over complex docs. ✅ Generate summaries and knowledge graph mind-maps 🤯 ✅ Generate podcasts thanks to ElevenLabs 🗣️ ✅ Agentic chat with docs and view metrics with OpenTelemetry This all lives within an open-source repo so you can clone/modify at will to swap in your own components! Huge shoutout to Clelia Bertelli (🦙/acc) for leading this. Repo: LlamaCloud helps power the parsing/ingestion. You can always use your own stuff too, but in the meantime you can check out LlamaCloud here:

Introducing NotebookLlama - an open-source version of NotebookLM! 📓🦙 NotebookLlama is a full implementation of NotebookLM that includes all the capabilities that makes it so great for researchers+business users: ✅ Create a knowledge repository of documents. Has likely higher accuracy than NotebookLM since it’s using LlamaCloud under the hood for high-quality parsing/extraction over complex docs. ✅ Generate summaries and knowledge graph mind-maps 🤯 ✅ Generate podcasts thanks to ElevenLabs 🗣️ ✅ Agentic chat with docs and view metrics with OpenTelemetry This all lives within an open-source repo so you can clone/modify at will to swap in your own components! Huge shoutout to Clelia Bertelli (🦙/acc) for leading this. Repo: LlamaCloud helps power the parsing/ingestion. You can always use your own stuff too, but in the meantime you can check out LlamaCloud here:

Jerry Liu

137,793 views • 1 year ago

Here's an MS Word feature that nobody is talking about and that just blew my mind. Open an blank document in MS Word and click on the "Dicatate" button. Select "Transcribe." Next upload an audio file you want to transcribe. I uploaded recording of one my webinars. It's 3 hours and 17 minutes long. And MS Word will transcribe the whole thing for you in a few minutes. Once it's done transcribing, Word gives you four options: Just text, With speakers, With timestamps, With speakers and timestamps. Choose the one according to your preference and you will have the whole transcript.

Here's an MS Word feature that nobody is talking about and that just blew my mind. Open an blank document in MS Word and click on the "Dicatate" button. Select "Transcribe." Next upload an audio file you want to transcribe. I uploaded recording of one my webinars. It's 3 hours and 17 minutes long. And MS Word will transcribe the whole thing for you in a few minutes. Once it's done transcribing, Word gives you four options: Just text, With speakers, With timestamps, With speakers and timestamps. Choose the one according to your preference and you will have the whole transcript.

Mushtaq Bilal, PhD

343,820 views • 2 years ago

Today we’re introducing Superhuman Docs, the evolution of Coda (Superhuman Docs) into the best place for teams and AI to work together. I co-founded Coda to reimagine the modern document and enable anyone to make a doc as powerful as an app. Superhuman Docs builds on that mission, and is reimagined for how teams work with AI now. With Superhuman Docs, AI is no longer a solo experience. Docs AI works with you the way a teammate would, with full context of everything your team has built: your data, your briefs, your roadmaps, your connected tools. You can ask it to summarize a sprint, draft a decision record from your meeting notes, or pull a competitor analysis into a new page, and that work stays right where your teammates can pick it up. I’m incredibly proud of the team for bringing Docs to life! There’s so much more we’re launching, including a way to create custom interfaces on top of your data just by describing it. We’re also introducing Superhuman Databases for teams to manage up to 1 million rows, launching Docs MCP to open it up to the AI tools you already use, and debuting a brand new Mac app. We’ve been building toward this moment for a long time, and Docs starts rolling out today. If you’re an existing Coda user, everything you rely on in your docs will remain the same, and if you’re new, now is a great time to jump in.

Shishir

23,206 views • 1 month ago

We’re excited to announce that new visual customizations features are now live on Napkin, making it easier than ever to personalize your visuals 🎨 ✅ Choose from new fonts like Arial, Times New Roman, Noto Serif Japanese, M PLUS Rounded 1c and more ✅ Add any color using our new color picker for fill and borders ✅ Customize visuals during export with different backgrounds, color modes, and resolutions - all with a real-time preview to get perfect visuals These are just some of the highlights - there’s more to explore! Go to to try out the new customizations and let us know your thoughts in the comments 🙌 #NapkinAI #VisualAI #AITools #VisualStorytelling #Customization

We’re excited to announce that new visual customizations features are now live on Napkin, making it easier than ever to personalize your visuals 🎨 ✅ Choose from new fonts like Arial, Times New Roman, Noto Serif Japanese, M PLUS Rounded 1c and more ✅ Add any color using our new color picker for fill and borders ✅ Customize visuals during export with different backgrounds, color modes, and resolutions - all with a real-time preview to get perfect visuals These are just some of the highlights - there’s more to explore! Go to to try out the new customizations and let us know your thoughts in the comments 🙌 #NapkinAI #VisualAI #AITools #VisualStorytelling #Customization

Napkin AI

24,202 views • 1 year ago

I just launched a free App that lets you open Mac Apps…from your iPhone. And close them with a swipe. A much faster drag and drop. And a ton of more features in the pipeline. It’s called choclift and you really should try it out. Available for free in the App Store for iOS and macOS.

I just launched a free App that lets you open Mac Apps…from your iPhone. And close them with a swipe. A much faster drag and drop. And a ton of more features in the pipeline. It’s called choclift and you really should try it out. Available for free in the App Store for iOS and macOS.

Phil Traut ᯅ

504,584 views • 4 months ago

In the age of Gemini, we are reimagining how we work across Docs, Sheets, Slides and Drive. The new way of working evolves our digital digital work from compiling information to directing outcomes. Excited to bring more contextual, helpful and collaborative Google Workspace. Simply choose your sources and create a Doc draft in seconds, build complex Sheets 9X faster, or generate on-brand Slide layouts with a simple prompt. And, Google Drive now generates summarized answers right at the top of your search results (AIO!) and helps you have a multi-turn conversation with your files/folders. Available today in beta for Workspace Gemini Alpha customers and G1 AI Ultra and AI Pro subscribers. 1/6

Chandu Thota

45,449 views • 5 months ago

Open Mac apps on your iPhone with my new app choclift 🍫 After extending my Mac screen with Vision Pro, I wanted even more connectivity between devices so I explored the advantage of having a separate user interface just for app management. It seems simple but it actually allows for a lot of new workflows and use-cases as you might think. Everyone works differently so we’re building this app as a platform that will support many different workflows, beyond just opening apps. Stay tuned as I’ll be sharing more in the coming weeks.

Open Mac apps on your iPhone with my new app choclift 🍫 After extending my Mac screen with Vision Pro, I wanted even more connectivity between devices so I explored the advantage of having a separate user interface just for app management. It seems simple but it actually allows for a lot of new workflows and use-cases as you might think. Everyone works differently so we’re building this app as a platform that will support many different workflows, beyond just opening apps. Stay tuned as I’ll be sharing more in the coming weeks.

Phil Traut ᯅ

158,880 views • 4 months ago

We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood. Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙 It's a CLI + TS-native library for layout-aware text parsing from PDFs, Office docs, and images. Local, zero Python dependencies, and built specifically for agents and LLM pipelines. Think of it as our way of giving the community a solid starting point for document parsing: npm i -g @llamaindex/liteparse lit parse anything.pdf - preserves spatial layout (columns, tables, alignment) - built-in local OCR, or bring your own server - screenshots for multimodal LLMs - handles PDFs, office docs, images Blog: Repo:

We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood. Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙 It's a CLI + TS-native library for layout-aware text parsing from PDFs, Office docs, and images. Local, zero Python dependencies, and built specifically for agents and LLM pipelines. Think of it as our way of giving the community a solid starting point for document parsing: npm i -g @llamaindex/liteparse lit parse anything.pdf - preserves spatial layout (columns, tables, alignment) - built-in local OCR, or bring your own server - screenshots for multimodal LLMs - handles PDFs, office docs, images Blog: Repo:

LlamaIndex 🦙

581,431 views • 4 months ago

🚨 CUNY’s Cuba Conference: “Every Drone Iran Fires Defends Cuba,” America “#1 Terrorist,” and Calls to Speed the End of US Empire Here are some of the more jaw-dropping lines from today’s opening plenary of the Cuba Under Siege conference at the CUNY Graduate Center. What was advertised as a “US-Cuba Normalization” conference quickly turned into anti-American agitprop, praise for the Cuban Revolution, and open rhetorical alignment with Iran. Speakers tied Cuba directly to Iranian military action and cast both as part of a wider anti-American front that also included Palestine and Venezuela. Other remarks called the U.S. government “the number one terrorist in the world,” described the end of the U.S. “empire” and urged activists to “speed up the end in every way possible,” even invoking Che Guevara’s call to create “1, 2, 3 Vietnams.” Speakers featured in this clip include Sara Flounders, Berthony Dupont, Artemio Camacho, and Corinna Mullin.

🚨 CUNY’s Cuba Conference: “Every Drone Iran Fires Defends Cuba,” America “#1 Terrorist,” and Calls to Speed the End of US Empire Here are some of the more jaw-dropping lines from today’s opening plenary of the Cuba Under Siege conference at the CUNY Graduate Center. What was advertised as a “US-Cuba Normalization” conference quickly turned into anti-American agitprop, praise for the Cuban Revolution, and open rhetorical alignment with Iran. Speakers tied Cuba directly to Iranian military action and cast both as part of a wider anti-American front that also included Palestine and Venezuela. Other remarks called the U.S. government “the number one terrorist in the world,” described the end of the U.S. “empire” and urged activists to “speed up the end in every way possible,” even invoking Che Guevara’s call to create “1, 2, 3 Vietnams.” Speakers featured in this clip include Sara Flounders, Berthony Dupont, Artemio Camacho, and Corinna Mullin.

Stu Smith

93,569 views • 5 months ago

My review on the new Vtuber App EmoteLab. This app is only in beta, and it's a 10/10! You can modify just enough from the default settings, to have so much done! incredibly quality and speed. You can modify the textures too! Advance options are easy to access. Someone REALLY Smart can even create an entire Vtuber Models and Giftuber models with this! My personal take, this is an amazing thing for beginners or even those who Vtube as a hobby, want to use it for personal projects. A customized personal emote from start still holds a special place, never forget the meaning of an emote as well, it is whatever your heart desires. As simple as an emote can be, sometimes they should encapsulate moments of your streamer journey, or your favorite memes, and so much more.

My review on the new Vtuber App EmoteLab. This app is only in beta, and it's a 10/10! You can modify just enough from the default settings, to have so much done! incredibly quality and speed. You can modify the textures too! Advance options are easy to access. Someone REALLY Smart can even create an entire Vtuber Models and Giftuber models with this! My personal take, this is an amazing thing for beginners or even those who Vtube as a hobby, want to use it for personal projects. A customized personal emote from start still holds a special place, never forget the meaning of an emote as well, it is whatever your heart desires. As simple as an emote can be, sometimes they should encapsulate moments of your streamer journey, or your favorite memes, and so much more.

Sain | Cyber Idol 🌐✨【V-HOST】

22,767 views • 6 months ago

📢 New in Visual Studio: Bring Your Own Model to Chat We’re expanding flexibility in Copilot for Visual Studio. You can now connect API keys from providers like OpenAI, Anthropic, and Google to run Chat on the model of your choice. This update gives you: ✅ Choice – Access the latest models beyond the built-in defaults. ✅ Customization – Select models that fit your infrastructure and requirements. ✅ Control – Manage API usage, limits, and billing directly with your provider. ✅ Flexibility – Switch seamlessly between Copilot’s built-in models and your own. This release is the first step toward a more open and customizable chat experience in Visual Studio, with more providers and capabilities to come. 🔗

📢 New in Visual Studio: Bring Your Own Model to Chat We’re expanding flexibility in Copilot for Visual Studio. You can now connect API keys from providers like OpenAI, Anthropic, and Google to run Chat on the model of your choice. This update gives you: ✅ Choice – Access the latest models beyond the built-in defaults. ✅ Customization – Select models that fit your infrastructure and requirements. ✅ Control – Manage API usage, limits, and billing directly with your provider. ✅ Flexibility – Switch seamlessly between Copilot’s built-in models and your own. This release is the first step toward a more open and customizable chat experience in Visual Studio, with more providers and capabilities to come. 🔗

Visual Studio

11,873 views • 11 months ago

Meet Runway Agent. Your new AI creative partner that helps you ideate and execute fully finished, sound designed and edited videos. All with just a simple conversation. From ads to shorts to content for social, Runway Agent makes it easy to make more of what you need. Get started on web at the link below.

Meet Runway Agent. Your new AI creative partner that helps you ideate and execute fully finished, sound designed and edited videos. All with just a simple conversation. From ads to shorts to content for social, Runway Agent makes it easy to make more of what you need. Get started on web at the link below.

Runway

576,834 views • 3 months ago

"I think the only way to get out from this complex situation is that eventually Israel is going to ease the activity in Lebanon, thus allowing the negotiations to go forward." The ever prescient Danny (Dennis) Citrinowicz ,داني سيترينوفيتش predicted Netanyahu's moves in a conversation with me earlier today. This week's epsode of The View From Here, "Ceasefire or Escalation? Israel, the US and Iran after the brink," is out now wherever you get your podcasts. Danny, thank you for the fascinating conversation!

"I think the only way to get out from this complex situation is that eventually Israel is going to ease the activity in Lebanon, thus allowing the negotiations to go forward." The ever prescient Danny (Dennis) Citrinowicz ,داني سيترينوفيتش predicted Netanyahu's moves in a conversation with me earlier today. This week's epsode of The View From Here, "Ceasefire or Escalation? Israel, the US and Iran after the brink," is out now wherever you get your podcasts. Danny, thank you for the fascinating conversation!

Jasmine El-Gamal

29,633 views • 4 months ago

Introducing SuperDesign.Dev The first open-source Design Agent that lives inside Cursor, Windsurf, or any IDE: 👉 Instantly spin up 10 different design in parallel 👉 Explore, fork, and iterate 10x faster 👉 Create new or iterate on your existing UI — all fully local JackJack and I shipped this as a quick weekend experiment to validate a hunch: design is the killer use case for parallel agents. Currently at V0.005 — a simple customization of the Claude Code SDK + static HTML generation. (We might be the first product powered by the Anthropic Claude Code SDK!) More coming soon: web app, mobile app, SVG generation, and more. GitHub: Try it out: ----- Upvote on Hacker News ❤️:

Introducing SuperDesign.Dev The first open-source Design Agent that lives inside Cursor, Windsurf, or any IDE: 👉 Instantly spin up 10 different design in parallel 👉 Explore, fork, and iterate 10x faster 👉 Create new or iterate on your existing UI — all fully local JackJack and I shipped this as a quick weekend experiment to validate a hunch: design is the killer use case for parallel agents. Currently at V0.005 — a simple customization of the Claude Code SDK + static HTML generation. (We might be the first product powered by the Anthropic Claude Code SDK!) More coming soon: web app, mobile app, SVG generation, and more. GitHub: Try it out: ----- Upvote on Hacker News ❤️:

Jason Zhou

49,435 views • 1 year ago

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,927 views • 4 months ago

I’ve been to 30+ stadiums, I’ve seen playoff games in all four major sports… What I just witnessed Knicks fans do in Cleveland is unlike anything I’ve ever seen before. “LETS GO KNICKS” chants broke out and they were so loud that Rocket Arena turned the volume up on the speakers to drown them out. Analytically speaking (😉) when I saw a $79 ticket on TickPick and pulled the trigger, I figured Knicks would be in the building - that was an underestimation. There may have been MORE KNICKS FANS than Cavs fans. At tip off. Getting the “nah nah nah hey hey hey goodbye” at your own arena… AT THE END OF THE THIRD QUARTER… is nuts. That doesn’t happen. When you’re in the bathroom at a game and hear cheers you assume the home team is doing something great right? At this game, those blind cheers were for the Knicks. MGK (Cleveland born) tried hyping up the Cavs fans and told them to show Knicks fans the door… He was met with more boos from the Knicks fans than cheers from Cavs fans. Wasn’t even close. Cavs missed a free throw at home, and the crowd CHEERED. This was one of the most unbelievable fan spectacles I’ve ever seen in my life.

I’ve been to 30+ stadiums, I’ve seen playoff games in all four major sports… What I just witnessed Knicks fans do in Cleveland is unlike anything I’ve ever seen before. “LETS GO KNICKS” chants broke out and they were so loud that Rocket Arena turned the volume up on the speakers to drown them out. Analytically speaking (😉) when I saw a $79 ticket on TickPick and pulled the trigger, I figured Knicks would be in the building - that was an underestimation. There may have been MORE KNICKS FANS than Cavs fans. At tip off. Getting the “nah nah nah hey hey hey goodbye” at your own arena… AT THE END OF THE THIRD QUARTER… is nuts. That doesn’t happen. When you’re in the bathroom at a game and hear cheers you assume the home team is doing something great right? At this game, those blind cheers were for the Knicks. MGK (Cleveland born) tried hyping up the Cavs fans and told them to show Knicks fans the door… He was met with more boos from the Knicks fans than cheers from Cavs fans. Wasn’t even close. Cavs missed a free throw at home, and the crowd CHEERED. This was one of the most unbelievable fan spectacles I’ve ever seen in my life.

Max Loeb

126,943 views • 2 months ago

A resurfaced clip has fans debating Atlanta rap history. 👀 Pastor Troy claims producer Shawty Redd taught a young Jeezy some of the ad-libs and stylistic elements that were already a major part of Troy’s sound during the early 2000s. He pointed to Jeezy’s mixtape era and suggested the influence was obvious before his rise to mainstream success. 🎤 Some fans call it inspiration, while others think Pastor Troy deserves more credit for helping shape Atlanta rap. Do y’all think Jeezy borrowed from Pastor Troy, or was it just the Atlanta sound at the time? 🤔👇🏾 🎥 Via: Bad Speakers Podcast

A resurfaced clip has fans debating Atlanta rap history. 👀 Pastor Troy claims producer Shawty Redd taught a young Jeezy some of the ad-libs and stylistic elements that were already a major part of Troy’s sound during the early 2000s. He pointed to Jeezy’s mixtape era and suggested the influence was obvious before his rise to mainstream success. 🎤 Some fans call it inspiration, while others think Pastor Troy deserves more credit for helping shape Atlanta rap. Do y’all think Jeezy borrowed from Pastor Troy, or was it just the Atlanta sound at the time? 🤔👇🏾 🎥 Via: Bad Speakers Podcast

Traps N Trunks

13,394 views • 2 months ago

Instead of putting up a traditional railing that would’ve blocked the view and taken away from the beauty of his new stairs, he went with glass instead. The difference is huge. The stairs still feel open, modern, and showcase the wood instead of hiding it behind vertical spindles. The glass railing does exactly what it’s supposed to do — keep it safe — without sacrificing how good the staircase looks. It’s a clean, simple choice that makes the whole space feel bigger and more intentional. Would you ever choose glass railings if you were building or updating stairs?

Instead of putting up a traditional railing that would’ve blocked the view and taken away from the beauty of his new stairs, he went with glass instead. The difference is huge. The stairs still feel open, modern, and showcase the wood instead of hiding it behind vertical spindles. The glass railing does exactly what it’s supposed to do — keep it safe — without sacrificing how good the staircase looks. It’s a clean, simple choice that makes the whole space feel bigger and more intentional. Would you ever choose glass railings if you were building or updating stairs?

End3of6Days9 (Helen) 🇺🇸

172,042 views • 1 month ago