Your speech-to-text results, polished in seconds
⬇️ Download NowHave you ever used speech-to-text software and gotten a transcript full of "um," "uh," repeated words, or missing punctuation? ElBruno.S1Mini fixes all of that for you — automatically and completely offline.
This is a free, open-source tool that runs on your Windows computer. It takes your raw transcript (from Whisper, superwhisper, or any other speech recognition tool) and cleans it up so it reads like natural, professional text. No more editing hours of transcripts by hand!
Gets rid of "um," "uh," "like," "you know," and other verbal fillers that clutter your transcript.
Turns "I-I-I think" into "I think." Repeats and stutters are automatically smoothed out.
Adds proper commas, periods, question marks, and capitalization so your text reads naturally.
Everything runs on your computer. Your transcripts never leave your machine. No cloud, no internet required.
ElBruno.S1Mini uses advanced AI technology (specifically a Qwen3 model called "s1-mini") that runs through ONNX Runtime GenAI. Here's what happens behind the scenes:
The first time you run it, the app will automatically download a small AI model from HuggingFace. After that, everything works offline. The model is compact and efficient, so it runs well on most modern computers.
Getting started takes less than 2 minutes. Here's what to do:
Step 1: Visit this link to download the application.
📦 Get ElBruno.S1MiniClick the link above to go to the download page.
Step 2: On that page, find the latest release and download the file.
The download page will show you the available files. Choose the one for Windows and save it to your computer.
After downloading, run the application. A simple window will open.
Copy your raw transcript from any speech-to-text tool and paste it into the text box.
Press the button to start the cleaning process. The AI will process your text in a few seconds (longer for very long transcripts).
Once done, your cleaned transcript appears. Copy it to your clipboard or save it as a text file.
Yes! ElBruno.S1Mini is open-source and completely free to use. No subscriptions, no hidden costs.
Yes. As long as you have the text transcript, ElBruno.S1Mini can clean it up. It works with Whisper, superwhisper, Google Speech-to-Text, and any other tool.
For a typical 5-minute transcript (about 750 words), it usually takes 10-20 seconds. Longer transcripts take proportionally more time.
No. Everything runs 100% locally on your computer. Your transcripts never leave your machine.
If you run into any issues or have questions, check the GitHub repository for documentation, troubleshooting guides, and community support.
🔗 Visit GitHub RepositoryElBruno.S1Mini is an open-source project. Built with ❤️ using .NET and ONNX Runtime GenAI.
Keywords: ai, asr, csharp, dotnet, dotnet10, dotnet8, huggingface, llm, local-ai, microsoft-extensions-ai, nuget, onnx, onnx-runtime, onnxruntime-genai, qwen3, s1-mini, speech-to-text, text-normalization, transcription, whisper