#7272nd of 81 in VoiceFor voice, speech and music
scriberr
Offline audio transcription server with speaker diarization and LLM chat
- Stars
- 3.1k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Dec 2025
- Language
- Go
2,549 on 21 Apr 20263,143 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Scriberr is a self-hosted web app, written in Go, that transcribes audio and video locally using NVIDIA Parakeet, Canary or Whisper models, with word-level timing. It adds speaker diarization, a folder watcher, a REST API, a built-in recorder, notes, and summaries or chat over transcripts via Ollama or OpenAI-compatible endpoints. Data is stored in SQLite, and it installs via Docker (CPU or CUDA images) or Homebrew.
Who it is for: Self-hosters who want private, local transcription of recordings and meetings
Strengths
- Runs transcription locally with Parakeet, Canary or Whisper; no cloud provider required
- Speaker diarization and word-level timestamps with seek-from-text playback
- Folder watcher and API allow integration with tools like n8n
- Separate Docker images for CPU, CUDA and RTX 50-series Blackwell GPUs
Weaknesses
- First start takes several minutes while Python environments and models download
- Upgrading from v1.1.0 requires splitting volumes and deleting the old whisperx-env
- Plain HTTP access needs SECURE_COOKIES=false or audio streaming fails
- Maintainer reported a development pause; last release was December 2025
What it needs
- GPU optional
- Docker + Compose
- Needs Docker or Homebrew, uv, SQLite, Ollama or OpenAI-compatible API (optional, for chat)
- Models: NVIDIA Parakeet, NVIDIA Canary, Whisper, PyAnnote (diarization), Ollama
- port 8080
Quick answers
Is scriberr open source?
Yes. Its code is on GitHub under the MIT license.
Can you run scriberr with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does scriberr need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |