transcriptionstream

What it does

A turnkey self-hosted diarization service that runs fully offline: drag files in over SSH or the web UI, get transcripts attributed per speaker, summaries via Ollama, and full-text search across everything. Nothing leaves your infrastructure, which is the whole point for regulated work. The flip side is that a searchable who-said-what archive needs a retention policy and an access list decided up front — and that diarization makes mistakes, so it isn't evidence. GPL-3.0.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

• Setup difficultySome setup needed
• Command lineRequired
• API keyNot required
• Sends data onlineNo

Judged automatically from the project's own metadata. Always confirm on the official page.

transcriptionstream FAQ

Is transcriptionstream free?

Yes. It runs on your own machine, so there is no usage-based cost either.

Do I need to install anything or write code to use transcriptionstream?

It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.

Does transcriptionstream work on a phone?

No. It needs a computer.

Can transcriptionstream run offline?

Yes. Everything happens on your own machine, so your data is never sent to an outside server. That makes it usable for material you cannot share externally.

Can I use transcriptionstream commercially?

The licence is GPL-3.0. Using it commercially is fine, but if you distribute something built on it you may be required to release that under the same licence. Keep it internal, or check before distributing.

How it compares

The conditions that decide whether you can actually use it, side by side.

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other meetings & transcription tools