BrendownFerreira/transcriber

What is it?

Key features

• 01Transcribes YouTube URLs and uploaded .mp3, .mp4, .wav and similar files.
• 02Shows live job progress over WebSockets.
• 03Offers openai-whisper and faster-whisper engines with NVIDIA CUDA support.
• 04Pairs media files with transcripts in a library and supports cleanup.
• 05Ships a multi-stage Docker image that runs as a non-root user.

Use cases

• Transcribing interviews or recordings without uploading them to a third-party service.
• Creating text transcripts of YouTube videos for reading or searching.
• Running a private transcription service on a home server or internal network.

Quick start

1. 1

   Create and activate a virtual environment (macOS/Linux)

   python -m venv .venv
2. 2

   Activate the virtual environment (macOS/Linux)

   source .venv/bin/activate
3. 3

   Run the automated installer (installs GPU support and dependencies)

   python install.py
4. 4

   Start the application, then open http://localhost:8000

   uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Things to know

• !Requires Python 3.10 to 3.12 for reliable NVIDIA GPU support; Python 3.13+ may fall back to CPU-only PyTorch.
• !An NVIDIA GPU is optional but needed for faster transcription.
• !FFmpeg is needed; automatic installation may fail and require manual setup.

Topics

FAQ

What is transcriber?

Self-hosted web app that transcribes YouTube videos and local audio/video files with OpenAI Whisper, running on your own machine. Transcriber is a FastAPI web application that turns YouTube links and uploaded audio or video files into text using OpenAI Whisper. Processing runs locally, so media does not need to be sent to a cloud transcription service, and there is no subscription.

Is transcriber free to use? What license does it have?

transcriber 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 transcriber still maintained?

No commits for 6+ months. The last commit to transcriber was on Mar 18, 2026.

What can I use transcriber for?

Transcribing interviews or recordings without uploading them to a third-party service. Creating text transcripts of YouTube videos for reading or searching. Running a private transcription service on a home server or internal network.

How do I install transcriber?

Create and activate a virtual environment (macOS/Linux): python -m venv .venv Activate the virtual environment (macOS/Linux): source .venv/bin/activate Run the automated installer (installs GPU support and dependencies): python install.py Start the application, then open http://localhost:8000: uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Where can I get transcriber?

The source code and installation instructions are on GitHub: https://github.com/BrendownFerreira/transcriber