Vellichor

Vellichor is a self-hosted web app that turns your written stories and ebooks into narrated audiobooks.

  • Media Applications
  • Media Servers
  • Productivity
  • Tools & Utilities
Vellichor is a self-hosted web app that turns your written stories and ebooks into narrated audiobooks. It narrates your text with the Kokoro-82M text-to-speech (TTS) model, with an optional Chatterbox engine adding expressive narration, emotional intensity, and voice cloning from a short clip or your own browser recording. Supports multi-voice character casting, background ambience, chaptered M4B and per-chapter MP3 output, and auto-export to an Audiobookshelf library. Built for writers who want to hear their own work.

Platform availability

Available on 1 of 10 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)
  • Any server (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.

46/100 Fair

Maintained
69last commit 113 days ago
Popular
176 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data

Based on 3 of 4 factors.

Availability: platform listings confirmed today, links checked 17 days ago

GitHub stars
6
Open issues
0
Last commit
2026-07-31
License
MIT
Activity
stale

Checked 5 days ago - source: GitHub (woodscode/vellichor-web)

Resources & Compatibility

Minimum requirements: 6.83594 GB disk.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Requirements Requires Docker and Docker Compose. Optional NVIDIA GPU acceleration needs the NVIDIA Container Toolkit on the host — on Unraid, the Nvidia Driver plugin; without a GPU it falls back to CPU. Expect about 7 GB of disk for the image and models. source
  • Install requirements (GPU & Ollama) Install with Docker and Docker Compose and set aside roughly 7 GB of disk. GPU is optional — if used, install the NVIDIA Container Toolkit on the host (the Nvidia Driver plugin on Unraid); without a GPU the app runs on CPU. The AI 'Smart cast' feature needs a separate Ollama container (set the Ollama URL in settings); without it, rule-based Quick detect casting is used. source

Fetched 43 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Does Vellichor require an NVIDIA GPU?

No, it runs on CPU by default. Optional NVIDIA GPU acceleration requires the Nvidia Driver plugin on Unraid.

How do I enable AI Smart cast?

Run a separate Ollama container and set the Ollama URL in Vellichor. If Ollama is not configured, the app uses the rule-based Quick detect instead.

What audio output formats can Vellichor create?

It can create chaptered M4B files and per-chapter MP3 files. It can also auto-export to an Audiobookshelf library.

Can Vellichor use different voices for different characters?

Yes, it supports multi-voice character casting. It also supports background ambience.

Can Vellichor clone a custom voice?

Yes, with the optional Chatterbox engine. It can clone a voice from a short clip or let you record your own.

Answers sourced from github.com

Community

Collected 49 days ago - public community threads