← Directory

Fireside

Fireside converts EPUB e-book files and public story links into chapter-by-chapter narration audio, built for long serialized fiction.

  • Media Applications
  • Media Servers
  • Productivity
Fireside converts EPUB e-book files and public story links into chapter-by-chapter narration audio, built for long serialized fiction. It imports EPUBs, pasted story links, and Archive of Our Own stories (with an optional login cookie), produces per-chapter audio you can replay or a continuous whole-book mode, and stores everything on your local filesystem with SQLite metadata (MySQL/MariaDB optional). Bring your own text-to-speech key for Azure, OpenAI-compatible, or MiniMax services, or point it at a local engine such as Kokoro for zero per-word cost. A free, open source (MIT) self-hosted option for homelab users who want audiobooks without a subscription.

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.

42/100 Fair

Maintained
75last commit 3 days ago
Popular
00 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
304 GB minimum RAM

Availability: platform listings confirmed today

GitHub stars
0
Open issues
47
Last commit
2026-10-19
License
MIT
Activity
rising

Checked 3 days ago - source: GitHub (Cstolworthy/fireside)

Resources & Compatibility

Minimum requirements: 4 GB RAM, 4 GB disk. ARM (e.g. Raspberry Pi) is not supported.

Checked 3 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Run it Needs only Python 3.8+ (standard library only — no pip install or build). Run `python3 server.py` then open http://127.0.0.1:8765. On desktop, double-click `start_reader.bat` (Windows) or `start_reader.command` (macOS), or run `./start_reader.sh` (Linux). source
  • First run Open the web interface, add a speech engine on the Settings page, drop in a book, and press play. source
  • Run directly Start the server with `python3 server.py` (Python 3.8+, standard library only, no pip install or build needed), then open http://127.0.0.1:8765; on Windows and macOS you can instead double-click start_reader.bat or start_reader.command. source

Fetched 2 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

How do I run Fireside and choose a different port or output folder?

Run python3 server.py and open the WebUI on port 8765. You can pass options such as --port 9000 and --out ./out.

How can I expose Fireside to other people on my network?

Run it with --host 0.0.0.0 --port 8765 or use Docker. It has no accounts and shares the same bookshelf and out/ folder, so only use it on a trusted machine or LAN.

How do I import an AO3 story, including works that require login?

Paste a public story link or use AO3's Download -> EPUB and drop the EPUB into the app. For login-gated works, download the EPUB in your browser first.

How is generated audio stored and updated when I change voices?

Each chapter is rendered into one audio file and cached per voice. Render all chapters skips chapters already rendered, and changing voice requires playing again to render that voice.

How do I save or keep my TTS engine settings?

Press Remember settings to save the engine, key, and voice. The button shows unsaved if something changed, and the next visit reloads the saved key and voice.

Answers sourced from github.com

Community

Collected 2 days ago - public community threads