Scriberr at a glance
Checked 15 Oct 2026Scriberr is a self-hosted transcription server (Docker or Homebrew, web UI on port 8080) using Whisper, NVIDIA Parakeet or Canary with word-level timing. Diarization uses pyannote and needs a free Hugging Face token plus accepting the model terms. Summaries and chat use Ollama or an OpenAI-compatible API. MIT code; Parakeet, Canary and pyannote weights are CC-BY-4.0. CPU and CUDA images. Last release v1.2.0 (Dec 2025); the author says work is resuming.
RepoQuarry. “Scriberr.” Checked 15 Oct 2026. https://repoquarry.dev/projects/scriberrHow much of Otter.ai does it replace?
3 of 3 jobs. Transcribes uploaded or recorded audio with speaker labels and summaries; it does not join live meetings.
How much of ElevenLabs does it replace?
1 of 4 jobs. Self-hosted transcription with word timing and diarization.
For speech generation, voice cloning, voice agents, see other ElevenLabs alternatives. You may also need to build an interface, an API server and hosting yourself.
Facts, with sources
Every answer links to where we found it. We read the documentation; we did not install it.
Scriberr allows you to transcribe audio and video locally on your machine, ensuring no data is ever sent to a third-party cloud provider.github.com · Scriberr#introduction ↗ 1d ago
license: cc-by-4.0huggingface.co · speaker-diarization-community-1 ↗ 1d ago
OPENAI_API_KEY | API Key for OpenAI (optional).github.com · Scriberr#configuration ↗ 1d ago
Use this configuration for running Scriberr on any machine without a dedicated NVIDIA GPU.github.com · Scriberr#docker-deployment ↗ 1d ago
The easiest way to install Scriberr is using Homebrew.github.com · Scriberr#install-with-homebrew-macos--linux ↗ 1d ago
When you run Scriberr for the first time, it may take several minutes to start.github.com · Scriberr#app-startup ↗ 1d ago