Repolode
Submit
0xSojalSec

0xSojalSec/free-voice-clone

A curated list of local, free, open-source voice-cloning TTS models and music generation models, with comparison tables.

Open-source alternative to:ElevenLabs

View on GitHub
Stars
653
Forks
97
Open issues
2
Last commit
6 months ago

What is it?

This is an awesome-style list that catalogs open-source text-to-speech models with zero-shot voice cloning, along with music generation models. Each entry gives parameter counts, supported languages, streaming support, voice cloning ability, and license in a quick-comparison table, followed by per-model detail sections with links to code and Hugging Face weights.

The list covers a wide range of models, from very small on-device systems such as KittenTTS and Kokoro-82M to multi-billion-parameter models such as Fish Speech, Qwen3-TTS and MOSS-TTS. It also includes sections for audio restoration, speech recognition, and general audio language models, though the visible content focuses mainly on TTS and music generation.

The page is useful for developers choosing a self-hostable speech model, comparing licenses before commercial use, or finding models that run on CPU or consumer GPUs.

Key features

  • 01Side-by-side comparison tables of TTS models by voice cloning, languages, streaming and license.
  • 02Per-model sections with parameter counts, release dates and links to GitHub and Hugging Face.
  • 03Coverage of both speech synthesis and music generation models.
  • 04Entries include models that run on-device or on CPU, such as GGUF-quantized and ONNX-based options.

Use cases

  • Choosing a self-hosted TTS model for a product that must keep voice data on-premises.
  • Comparing licenses of voice-cloning models before commercial use.
  • Finding lightweight TTS models for on-device or CPU-only deployment.
  • Exploring open-source music generation options for experiments.

Things to know

  • The repository has no license listed in its metadata, so reuse terms are unclear.
  • Individual models carry different licenses, and some are restricted, such as the Fish Audio Research License.

Topics

#tts#voice-cloning#speech-synthesis#music-generation#awesome-list#open-source-models

FAQ

What is free-voice-clone?
A curated list of local, free, open-source voice-cloning TTS models and music generation models, with comparison tables. This is an awesome-style list that catalogs open-source text-to-speech models with zero-shot voice cloning, along with music generation models. Each entry gives parameter counts, supported languages, streaming support, voice cloning ability, and license in a quick-comparison table, followed by per-model detail sections with links to code and Hugging Face weights.
Is free-voice-clone free to use? What license does it have?
free-voice-clone has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
Is free-voice-clone still maintained?
No commits for 6+ months. The last commit to free-voice-clone was on Apr 9, 2026.
What can I use free-voice-clone for?
Choosing a self-hosted TTS model for a product that must keep voice data on-premises. Comparing licenses of voice-cloning models before commercial use. Finding lightweight TTS models for on-device or CPU-only deployment. Exploring open-source music generation options for experiments.
Where can I get free-voice-clone?
The source code and installation instructions are on GitHub: https://github.com/0xSojalSec/free-voice-clone

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects