The best Hacker News stories from Show from the past day
Latest posts:
Show HN: CloneDub – Convert audio into any language using the same voices
Hey everyone! Excited to share CloneDub - a tool that allows you to convert audio into any language while keeping the same voices.<p>We currently translate to: English, Spanish, French, Hindi, Italian, German, Polish, and Portuguese.<p>The voices are cloned so that the podcasters sound the same! For example, if you were to upload a Lex Fridman podcast interviewing Sam Altman and requested that it was translated into Hindi, it would sound like Lex Fridman and Sam Altman, but just in a different language/accent!<p>How does CloneDub work?<p>Audio Upload: Upload your audio file, paste a YouTube Link, or the link to your mp3/wav file<p>Output Language Selection: Choose the language you’d wish to convert the audio to - we support English, Spanish, French, Hindi, Italian, German, Polish, and Portuguese.<p>Generate, Download & Share: Wait for the output to generate, download, and share
* Note we only allow you to use CloneDub for one episode at a time and only allow for up to 10 min of audio for now as it is still in beta<p>You can view a demo and try it out here:clonedub.com<p>We decided to make CloneDub for 2 main reasons:
We love building for creators and have seen the impact that multilingual support for subtitles and dubbing has had for other industries (eg. on Netflix) / growing up watching Bollywood movies that we could only understand because of subtitles !
We have family members who are not great at understanding
English and thus have had limited access to information, educational content, and entertainment that we had the luxury of having just based off the language we speak<p>Let us know what you think
Show HN: CloneDub – Convert audio into any language using the same voices
Hey everyone! Excited to share CloneDub - a tool that allows you to convert audio into any language while keeping the same voices.<p>We currently translate to: English, Spanish, French, Hindi, Italian, German, Polish, and Portuguese.<p>The voices are cloned so that the podcasters sound the same! For example, if you were to upload a Lex Fridman podcast interviewing Sam Altman and requested that it was translated into Hindi, it would sound like Lex Fridman and Sam Altman, but just in a different language/accent!<p>How does CloneDub work?<p>Audio Upload: Upload your audio file, paste a YouTube Link, or the link to your mp3/wav file<p>Output Language Selection: Choose the language you’d wish to convert the audio to - we support English, Spanish, French, Hindi, Italian, German, Polish, and Portuguese.<p>Generate, Download & Share: Wait for the output to generate, download, and share
* Note we only allow you to use CloneDub for one episode at a time and only allow for up to 10 min of audio for now as it is still in beta<p>You can view a demo and try it out here:clonedub.com<p>We decided to make CloneDub for 2 main reasons:
We love building for creators and have seen the impact that multilingual support for subtitles and dubbing has had for other industries (eg. on Netflix) / growing up watching Bollywood movies that we could only understand because of subtitles !
We have family members who are not great at understanding
English and thus have had limited access to information, educational content, and entertainment that we had the luxury of having just based off the language we speak<p>Let us know what you think
Show HN: CloneDub – Convert audio into any language using the same voices
Hey everyone! Excited to share CloneDub - a tool that allows you to convert audio into any language while keeping the same voices.<p>We currently translate to: English, Spanish, French, Hindi, Italian, German, Polish, and Portuguese.<p>The voices are cloned so that the podcasters sound the same! For example, if you were to upload a Lex Fridman podcast interviewing Sam Altman and requested that it was translated into Hindi, it would sound like Lex Fridman and Sam Altman, but just in a different language/accent!<p>How does CloneDub work?<p>Audio Upload: Upload your audio file, paste a YouTube Link, or the link to your mp3/wav file<p>Output Language Selection: Choose the language you’d wish to convert the audio to - we support English, Spanish, French, Hindi, Italian, German, Polish, and Portuguese.<p>Generate, Download & Share: Wait for the output to generate, download, and share
* Note we only allow you to use CloneDub for one episode at a time and only allow for up to 10 min of audio for now as it is still in beta<p>You can view a demo and try it out here:clonedub.com<p>We decided to make CloneDub for 2 main reasons:
We love building for creators and have seen the impact that multilingual support for subtitles and dubbing has had for other industries (eg. on Netflix) / growing up watching Bollywood movies that we could only understand because of subtitles !
We have family members who are not great at understanding
English and thus have had limited access to information, educational content, and entertainment that we had the luxury of having just based off the language we speak<p>Let us know what you think
Show HN: SQL Dry Runs with SQL Simulator
My name is Weston Goodwin. I created a tool called SQL Simulator which allows you to do Dry Runs with your SQL Scripts. The reason I created the tool was because I wanted to verify that my SQL scripts did what I thought they would do without executing them against the database.<p>It is similar in concept to Redgate SQL Clone or Windocs. If you are not familiar with these tools they make clones of your database. The key difference with SQL Simulator is, it only makes a clone of the database objects affected by your sql script, not the entire database. Nor does it copy the entire table (if your sql has where clauses). Once those database objects have been cloned, SQL Simulator then executes your script against the cloned database it created.<p>This software is only compatible with Oracle and SQL Server at the present time. My plan is to make it compatible with more databases in the future.<p>For a more in depth technical overview click here:
<a href="https://docs.tribalknowledge.tech/ratifier-tutorials/sql-simulator/technical-overview" rel="nofollow">https://docs.tribalknowledge.tech/ratifier-tutorials/sql-sim...</a><p>You can download the software here:
<a href="https://www.tribalknowledge.tech/download.html" rel="nofollow">https://www.tribalknowledge.tech/download.html</a><p>You can read the documentation here:
<a href="https://docs.tribalknowledge.tech/ratifier-tutorials/sql-simulator" rel="nofollow">https://docs.tribalknowledge.tech/ratifier-tutorials/sql-sim...</a>
Show HN: SQL Dry Runs with SQL Simulator
My name is Weston Goodwin. I created a tool called SQL Simulator which allows you to do Dry Runs with your SQL Scripts. The reason I created the tool was because I wanted to verify that my SQL scripts did what I thought they would do without executing them against the database.<p>It is similar in concept to Redgate SQL Clone or Windocs. If you are not familiar with these tools they make clones of your database. The key difference with SQL Simulator is, it only makes a clone of the database objects affected by your sql script, not the entire database. Nor does it copy the entire table (if your sql has where clauses). Once those database objects have been cloned, SQL Simulator then executes your script against the cloned database it created.<p>This software is only compatible with Oracle and SQL Server at the present time. My plan is to make it compatible with more databases in the future.<p>For a more in depth technical overview click here:
<a href="https://docs.tribalknowledge.tech/ratifier-tutorials/sql-simulator/technical-overview" rel="nofollow">https://docs.tribalknowledge.tech/ratifier-tutorials/sql-sim...</a><p>You can download the software here:
<a href="https://www.tribalknowledge.tech/download.html" rel="nofollow">https://www.tribalknowledge.tech/download.html</a><p>You can read the documentation here:
<a href="https://docs.tribalknowledge.tech/ratifier-tutorials/sql-simulator" rel="nofollow">https://docs.tribalknowledge.tech/ratifier-tutorials/sql-sim...</a>
Show HN: Google Code Jam Archive
Hi HN,<p>As many of you already know, Google has discontinued their coding competitions and is shutting down the competitions website.
Before it's gone forever, I've scraped everything I could from their website and set up my own archive.<p>(Disclaimer: I'm not affiliated with Google besides participating in these contests years ago)<p>While the initial version was ready back in March, today I'm rolling out big and hopefully the final update, so this might be a good time to share it with the HN community.<p>Everything is static HTML and SQLite archives (with a very minimal backend to serve files directly from SQLite), so you can easily grab your own copy.
May these 3.5 million source files be a nice training dataset for some fancy future AI!<p>Some useless stats:<p>Tabs or spaces? 28% tabs vs 72% spaces for the whole dataset, but quite unexpectedly, 66% tabs vs 34% spaces if we consider only the final rounds.<p>Most used languages: 63% C/C++, 20% Python, 12% Java, 2% C#, with others less than 1% each. For the final rounds it's 83% C/C++, 13% Java, 2% Python.
Show HN: Google Code Jam Archive
Hi HN,<p>As many of you already know, Google has discontinued their coding competitions and is shutting down the competitions website.
Before it's gone forever, I've scraped everything I could from their website and set up my own archive.<p>(Disclaimer: I'm not affiliated with Google besides participating in these contests years ago)<p>While the initial version was ready back in March, today I'm rolling out big and hopefully the final update, so this might be a good time to share it with the HN community.<p>Everything is static HTML and SQLite archives (with a very minimal backend to serve files directly from SQLite), so you can easily grab your own copy.
May these 3.5 million source files be a nice training dataset for some fancy future AI!<p>Some useless stats:<p>Tabs or spaces? 28% tabs vs 72% spaces for the whole dataset, but quite unexpectedly, 66% tabs vs 34% spaces if we consider only the final rounds.<p>Most used languages: 63% C/C++, 20% Python, 12% Java, 2% C#, with others less than 1% each. For the final rounds it's 83% C/C++, 13% Java, 2% Python.
Show HN: Rarbg on IPFS
Show HN: Rarbg on IPFS
Show HN: Rarbg on IPFS
Show HN: Rarbg on IPFS
Show HN: An accessible, beautiful Raspberry Pi Pico pinout
I wanted to create an accessible alternative to the official Pico pinout image, offering more complete pin details, light/dark modes, screen-readable text, and at least some capacity to focus on the peripherals you’re interested in. It’s a sister site to the now ancient Raspberry Pi pinout (<a href="https://pinout.xyz/" rel="nofollow">https://pinout.xyz/</a>) which started out life hosted on a Raspberry Pi.
Show HN: An accessible, beautiful Raspberry Pi Pico pinout
I wanted to create an accessible alternative to the official Pico pinout image, offering more complete pin details, light/dark modes, screen-readable text, and at least some capacity to focus on the peripherals you’re interested in. It’s a sister site to the now ancient Raspberry Pi pinout (<a href="https://pinout.xyz/" rel="nofollow">https://pinout.xyz/</a>) which started out life hosted on a Raspberry Pi.
Show HN: An accessible, beautiful Raspberry Pi Pico pinout
I wanted to create an accessible alternative to the official Pico pinout image, offering more complete pin details, light/dark modes, screen-readable text, and at least some capacity to focus on the peripherals you’re interested in. It’s a sister site to the now ancient Raspberry Pi pinout (<a href="https://pinout.xyz/" rel="nofollow">https://pinout.xyz/</a>) which started out life hosted on a Raspberry Pi.
Show HN: Pot is a cross-platform translation software
Introducing my cross-platform translation software that makes it easier than ever to translate text on the fly. Our software is designed to be user-friendly and intuitive, with a sleek and modern interface that works seamlessly across all major platforms.<p>One of the standout features of our software is its ability to work with multiple translation APIs simultaneously (such as OpenAI,Google and so on), giving you access to a wider range of translations and ensuring that you always get the most accurate and relevant results.<p>Whether you're a student, or a business professional, our software is the perfect tool to help you communicate more effectively and bridge the language gap. With our software, you can translate text in real-time, without ever having to leave your current application or website.<p>So why wait? Download our cross-platform translation software today and experience the smoothest translation experience!
Show HN: TodoBot is an AI coach that helps you write a better todo list
I thought I'd be more likely to do the things on my todo list if GPT-4 was watching me (fail to) do them, so I built this. Let me know what you think!
Show HN: Local implementation of text-to-3D using Shap-E
Show HN: Local implementation of text-to-3D using Shap-E
Show HN: Local implementation of text-to-3D using Shap-E
Show HN: Verify LLM Generated Code with a Spreadsheet
Hey HN! Been a minute. We launched Mito here last year (<a href="https://news.ycombinator.com/item?id=32723766" rel="nofollow">https://news.ycombinator.com/item?id=32723766</a>).<p>Mito is a spreadsheet that generates Python code as you edit it. We've spent the past three years trying to lower the startup cost to use Python for data work. In doing so, we’ve been thrust into the middle of many Python transition processes at larger enterprises, and we’ve seen up-close how non-technical folks interact with generated code.<p>The Mito AI chatbot lives inside of the Mito spreadsheet (<a href="https://www.trymito.io/">https://www.trymito.io/</a>>. The obvious benefit of this is that you can use the chatbot to transform your data and write a repeatable Pythons script. The less obvious (but equally important) benefit is that by connecting a spreadsheet and chatbot, Mito helps you understand the impact of your edits and verify LLM generated code. Every time you use the chatbot, Mito highlights the changed data in the spreadsheet. You can see a quick demo here (<a href="https://www.tella.tv/video/clibtwssv00000fl65oky13nu/view">https://www.tella.tv/video/clibtwssv00000fl65oky13nu/view</a>).<p>Three main insights shaped our approach to LLM code generation:<p># Consumers of generated code don't know enough Python to verify and correct the code<p>Mito users span the range of Python experience. For new programmers, generating code using LLMs is an easy step one. Ensuring the generated code is correct is the forgotten step two.<p>In practice, LLMs often generate incorrect code, or code with unexpected side effects. A user will prompt an LLM to calculate a total_revenue column from price and quantity columns. The LLM correctly calculates total_revenue = price * quantity but then mistakenly deletes price and quantity.<p>New programmers find it almost impossible to verify generated code by reading it alone. They need tooling designed for their skillsets.<p># Not everyone knows how to use a chat interface for transformations<p>We were surprised to learn that many Mito users a) had no experience with ChatGPT, and b) didn’t understand the chat interface at all! Mito AI presents users a few example prompts and an input field. A surprising number of users thought the example prompts were all they could use Mito AI for.<p>AI chatbots are new. Us builders might be using them for natural language interactions, but users are still learning how to use them in new contexts. This stands in stark contrast to spreadsheets, where pretty much ever business user has experience. Shout out 40 years of Excel dominance!<p># The more context a prompt has about the user’s data + edits, the better the LLM results<p>For the LLM to generate code that can execute correctly, the prompt should include the names of the dataframes, the column headers, (some) dataframe values, and a few previous edits as examples. Duh.<p>But there’s no reason users should be responsible for writing this prompt. No one loves writing long chats, and in practice Mito AI users expect to be able to write ~12 words. Spreadsheets are well-suited to building the rest of the prompt for you - they have all of your data context, and know your recent edits.<p>With these three insights, it became very clear to us what role a spreadsheet could play in LLM based code-gen: a spreadsheet is the prompt builder, and a spreadsheet is the code verifier.<p>Mito AI builds an effective prompt by supplementing your input with the context of your data and recent edits.<p>Mito AI then helps you to verify the LLM generated code by highlighting the added, modified, and removed data within the chat interface - and within the spreadsheet. This way, you can ensure your LLM generated code is correct.<p>Give it a spin. Let us know what you think of the recon and how we can make it more helpful!<p>Also, if you like what we’re doing, we’re hiring – come help us build! (<a href="https://www.ycombinator.com/companies/mito/jobs" rel="nofollow">https://www.ycombinator.com/companies/mito/jobs</a>)