# TTS Workbench

TTS Workbench is a self-hosted, multi-engine text-to-speech platform that gives homelab users one local Gradio workflow for Kokoro narration, F5-TTS voice cloning, Qwen3-TTS generation, and compatible Intel Arc GPU. It is open source and self-hosted, installable on Unraid and Docker Hub.

Canonical page: https://ourlocalhost.com/app/2468/tts-workbench

## Description

TTS Workbench is a self-hosted, multi-engine text-to-speech platform that gives homelab users one local Gradio workflow for Kokoro narration, F5-TTS voice cloning, Qwen3-TTS generation, and compatible Intel Arc GPU acceleration.

## Platform availability

Available on 1 of 10 platforms: Unraid.

## Health score

43/100 (Fair), based on 3 of 4 factors.
- Maintained: 66 (last commit 95 days ago)
- Popular: 12 (3 GitHub stars)
- Easy to install: 35 (1 install platform, install notes, Docker image)

## Links

- GitHub: https://github.com/heroeswearkapes/tts-workbench
- Unraid: https://ca.unraid.net/apps/tts-workbench-1kb27ro0j6o7pk?q=TTS-Workbench
- Docker Hub: https://hub.docker.com/r/heroeswearkapes/tts-workbench

## Common questions

### Does TTS-Workbench send my text or reference audio to an external service?

No. It is designed to make engines usable through a consistent workflow without sending text or references.

### How do I access the TTS-Workbench UI?

It provides one local Gradio interface for narration, voice cloning, and emerging TTS models.

### Does TTS-Workbench support voice cloning?

Yes. Its local Gradio interface includes voice cloning along with narration and emerging TTS models.

### How does TTS-Workbench handle TTS engines with very different controls?

It makes engines with very different controls and runtime requirements usable through a consistent workflow.

---
Source: Our Local Host (https://ourlocalhost.com/app/2468/tts-workbench), the self-hosted and open-source app directory.
