Open-source speech-to-text built on Whisper that adds word-level timestamps via forced alignment and optional speaker diarization.
- Stars
- 466
- Forks
- 70
- Open issues
- 2
- Last commit
- 7 months ago
What is it?
SubStudio is a web app for creating subtitles from video. You upload a video file or paste a direct media link, and the app extracts the audio and sends it to Together AI's Whisper Large v3 model to transcribe it with word-level timestamps. Short intervals are merged into readable subtitle blocks.
Before export, you can preview and style the captions in real time using six preset looks: Classic, TikTok, Modern Box, Cinematic, Outline and Bold Center. Subtitles can be downloaded as SRT or VTT files, or burned into an MP4.
The project is built with Next.js (App Router), Tailwind CSS, Framer Motion, and FFmpeg via fluent-ffmpeg. It can be run locally with a Together AI API key in a .env file or entered in the UI, and deployed to Vercel with one click.
Key features
- 01Transcribes video audio with word-level timestamps via Together AI Whisper Large v3.
- 02Accepts uploaded video files or direct media links.
- 03Offers six preset caption styles with real-time preview.
- 04Exports subtitles as SRT, VTT, or burned-in MP4.
Use cases
- Adding captions to short-form videos for TikTok or Reels.
- Generating SRT or VTT subtitle files for video editing workflows.
- Creating burned-in subtitles for social media posts.
Quick start
- 1
Clone the repository
git clone https://github.com/Luffixos/ai-subtitles.git - 2
Create a .env file with your Together AI key (TOGETHER_API_KEY=your_api_key_here)
- 3
Install dependencies
npm install - 4
Start the dev server at http://localhost:3000
npm run dev
Things to know
- Transcription requires a Together AI API key.
- The listing metadata has no license, while the README says MIT; confirm the license before reuse.
Topics
FAQ
- What is ai-subtitles?
- A Next.js web app that generates timed subtitles from uploaded videos or media links using Together AI's Whisper model. SubStudio is a web app for creating subtitles from video. You upload a video file or paste a direct media link, and the app extracts the audio and sends it to Together AI's Whisper Large v3 model to transcribe it with word-level timestamps. Short intervals are merged into readable subtitle blocks.
- Is ai-subtitles free to use? What license does it have?
- ai-subtitles has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is ai-subtitles still maintained?
- No commits for 6+ months. The last commit to ai-subtitles was on Apr 7, 2026.
- What can I use ai-subtitles for?
- Adding captions to short-form videos for TikTok or Reels. Generating SRT or VTT subtitle files for video editing workflows. Creating burned-in subtitles for social media posts.
- How do I install ai-subtitles?
- Clone the repository: git clone https://github.com/Luffixos/ai-subtitles.git Create a .env file with your Together AI key (TOGETHER_API_KEY=your_api_key_here) Install dependencies: npm install Start the dev server at http://localhost:3000: npm run dev
- Where can I get ai-subtitles?
- The source code and installation instructions are on GitHub: https://github.com/Nutlope/ai-subtitles
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Desktop app that transcribes and translates audio and video offline on your computer, built on OpenAI's Whisper.
Desktop app that transcribes audio and video fully offline on your own device, using Whisper and other speech models.
Local-first AI subtitle generator that runs offline and plugs into DaVinci Resolve, Premiere Pro and After Effects.
Open-source local subtitling for any video: Whisper transcription, translation, styling and burn-in, in the browser, desktop app or CLI, without uploading the video.
Desktop app that transcribes a video with AI and burns styled captions directly into the output video.