← Directory

akou

Self-hosted transcription server.

  • AI
  • Productivity
  • Tools & Utilities
Self-hosted transcription server. A program uploads an audio file and reads back the text with word and segment times and speaker labels, as JSON, SRT or VTT, by long-poll, an event feed or a signed webhook. It also answers the OpenAI transcription endpoint (POST /v1/audio/transcriptions). A web page shows the job queue, the API keys, the models and the settings. This is the server mode of akou, a call recorder for macOS, with the same core.

First use: the speech models (about 3 GB) download on the first job. Set the web page's admin password from the Unraid terminal, at least 12 characters (this reads it without echo): read -rs P && printf '%s' "$P" | docker exec -i -u 1000:1000 akou akou admin set-password; unset P then log in and create one API key per program on the Keys page.

Folders: Unraid creates the appdata folders as root, and akou runs as uid

Platform availability

Available on 1 of 9 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

47/100 Fair

Maintained
79last commit 0 days ago
Popular
198 GitHub stars
Easy to install
201 install platform, Docker image
Light to run
No data

Based on 3 of 4 factors.

Availability: platform listings confirmed today

GitHub stars
8
Open issues
4
Last commit
2026-10-13
Latest release
v1.1.0
License
GPL-3.0
Activity
rising

Checked today - source: GitHub (GeiserX/akou)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is supported.

Checked today - source: Docker Hub image tags and published docs

First-install notes

No first-install notes yet.

Alternatives

No alternatives collected yet.

Common questions

Can the self-hosted server integrate with common transcription targets?

The Docker server exposes an OpenAI-compatible endpoint, a Wyoming endpoint for Home Assistant Assist, and Bazarr's /asr endpoint. File jobs are also part of the server mode.

Can I control calls from a terminal agent?

Yes. Claude Code, Codex, or another MCP-compatible agent can start, follow, question, and annotate a call through a local API or MCP.

How can finished calls be saved into my own tools?

A finished call can be handed off as Markdown, an event log, and the audio via an export folder, hooks, a signed webhook, or the API.

Do I need a meeting bot or virtual audio driver to record?

No. akou records the microphone and call audio on separate channels without a bot in the meeting or a virtual audio driver.

Answers sourced from geiserx.github.io, github.com

Community

No community discussions collected yet.