🚀 UniScribe July Updates – Big Improvements Just Landed!

Here's what we've shipped recently:

✅ Bulk Export Is Here!

You can now export multiple transcripts at once — save time, skip the clicks, and stay productive.

🧠 Mindmap Export: More Formats

We've expanded our mindmap export options!

In addition to PNG, you can now export as:

• Markdown (.md)

• XMind (.xmind)

Perfect for deeper editing or using with your favorite mind mapping tools.

🔁 Retry Failed Tasks

Sometimes things don't go as planned — especially with media downloads from YouTube or other platforms.

Now, if a task fails, you'll see a Retry option — up to 3 automatic retries per task.

Most issues are resolved with a retry, and if not, we'll help you troubleshoot further.

🧩 API Beta Is Live!

Developers, rejoice! 🎉

Our beta API is now available. You can start integrating transcription workflows today.

📘 Docs: https://www.uniscribe.co/docs

Hi Sumolings!

We've just rolled out three exciting updates to make your transcription experience even smoother:

1. 🎙️ Speaker Diarization is Now Live!

You can now identify different speakers in your recordings — available to both LTD Tier 1 & Tier 2 users, with no additional credits required.

2. 📁 Folders Management

You can now organize your files with folders — making it easier to manage transcripts across different projects or clients.

3. 🔍 Enhanced Transcript Editing: Search & Replace

Editing just got easier! You can now search and replace words directly in the transcript — perfect for quickly fixing recurring recognition errors.

We're continuing to improve the core experience and add new features — stay tuned for what's coming next. We can't wait to share more in the upcoming release!

Cheers,

David

Hi, Sumo-lings! 👋 This is David, Founder & CEO of UniScribe.

I’m thrilled to announce the launch of UniScribe!

Earlier this year, I saved up some money and quit my job to pursue the Barista FIRE lifestyle with my wife.

Investing is a key part of this lifestyle, and we often find ourselves listening to shareholder conference calls from the companies we invest in.

These meetings are usually quite lengthy, which inspired us to develop a tool for quickly extracting information from audio and video files — and that’s how UniScribe was born.

⚡️ What is UniScribe?

UniScribe is a platform that helps users quickly extract key information from lengthy audio and video files by converting them into text, powered by AI.

Its main features include:

• Fast conversion of audio and video files to text using an optimized Whisper model
• Automatic generation of summaries, mind maps, and key Q&A
• Supports exporting text content in various formats such as .srt, .txt, .pdf, .docx, .vtt, and .csv

😎 Who it’s for?

People who want to efficiently extract key information from audio and video content, such as:

• Journalists and Writers: To transcribe interview recordings for easier quoting and editing
• Students and Academics: To transcribe lectures, seminars, or meetings for easier note-taking and research
• Market Researchers: To transcribe focus groups and interview recordings for analysis
• Legal Professionals: To transcribe court records, testimonies, and client interviews for legal documentation
• Content Creators and Producers: To create subtitles or scripts for video content, or to transcribe audio for blogs and social media sharing

UniScribe has definitely helped us obtain investment information more efficiently, and we truly hope it can help others improve how they acquire and process information too!

What 3rd party tools is your product critically dependent on?

GPT-4o-mini, Replicate, FAL

Where is your customer data stored?

USA

How many customers do you have today?

We have served 7000+ users in 166 countries

What’s the origin of the idea for your product?

Earlier this year, I saved up some money and quit my job to pursue the Barista FIRE lifestyle with my wife. Investing is a key part of this lifestyle, and we often find ourselves listening to shareholder conference calls from the companies we invest in. These meetings are usually quite lengthy, which inspired us to develop a tool for quickly extracting information from audio and video files and that’s how UniScribe was born.

What problem is your product solving and how?

UniScribe uses an optimized Whisper model for speech-to-text, so transcription is super fast. Besides, AI helps turn long audio or video files into key takeaways, Q&A, and mind maps—making it easy for users to quickly find the most important information.

What’s the #1 thing you’re looking to gain from the AppSumo campaign?

We are looking to boot the number of active users to help spread the word more broadly

What are your plans with the customers, cash, and learnings from the AppSumo campaign?

We’ll keep improving the product experience and adding new features, such as speaker diarization (identifying multiple speakers), chatting directly with audio/video content, translating transcribed text, and integrating with more productivity tools. All to help users work more efficiently with audio and video files.

Any details to clarify about the deal?

1. Currently, our tiered plans include specific transcription time limits, while AI-generated summaries and mind maps are free to use. In the future, as we roll out more AI-powered features such as speaker diarization and the ability to chat directly with audio/video content, these features will also be available to users who purchased a lifetime deal on AppSumo. However, these advanced features will consume additional credits, which may need to be purchased or redeemed separately.

2. Our transcription feature currently supports 98 source languages for audio and video files. However, due to the limitations of the underlying AI model’s training data, the transcription accuracy for some less common languages may not be as high as for English. We strongly recommend trying it out for free before purchasing, we offer 120 minutes of free usage.