Open source · Self-hosted · MIT / Apache-2.0
v0.1.0 released

Run studio-grade voice AI
on your own GPU.

VoxLoom bundles OmniVoice, Qwen3-TTS and Chatterbox into one local CLI + Web UI. Generate and clone voices on hardware you control — no subscriptions, no rate limits, no vendor lock-in.

View on GitHub Try VoxLoom Cloud

The open-source alternative to ElevenLabs that you actually own.

Why VoxLoom

We got rate-limited by a commercial TTS API one time too many. So we aggregated the best open-source speech models into one studio you run yourself.

Open & self-hosted

MIT / Apache-2.0. Audit it, fork it, own it. Your voice data never leaves your machine.

No rate limits

Your GPU, your rules. Not someone else's API tier or monthly quota.

646 languages

OmniVoice covers 646 languages; Qwen3-TTS gives studio-grade Chinese cloning.

Clone in seconds

3-second reference audio, or text-prompt a voice — no training rig required.

Free to start

pip install voxloom and point it at your GPU. No account, no key.

Optional cloud

Need more horsepower or a premium voice? Our hosted API is there when you do.

Engines, unified

One CLI, three best-in-class open models. Pick per job.

EngineLanguagesCloningLicenseMin VRAM
OmniVoice6463s ref / text-promptApache-2.06 GB
Qwen3-TTS10+yesOpen8 GB
Chatterbox23few-sec refMIT8 GB

Quick start: pip install voxloom && voxloom serve --engine omni-voice --device cuda

Pricing

Start free and self-hosted. Pay only when you need cloud horsepower, a premium voice, or a commercial SLA.

Open Source
$0
Local CLI + Web UI. MIT. For developers, privacy-first users, tinkers.
  • ✓ All 3 engines
  • ✓ Unlimited local use
  • ✓ Community support
API Starter
$9/mo
Hosted API, standard engines, billed per character. No monthly minimum beyond plan.
  • ✓ 1M chars / mo
  • ✓ $0.0015 / extra 1k
  • ✓ Commercial license
Enterprise
Custom
On-prem deployment + SLA + compliance (data-residency, HIPAA-ready).
  • ✓ Private deploy
  • ✓ $2K–7K setup
  • ✓ $300–800 / mo

Join the VoxLoom Cloud waitlist

Be first to get premium voices and hosted GPU. No spam — one launch email.

Join the waitlist →

Opens your email app and sends straight to our inbox. Most reliable — no middleman.

Prefer a web form instead?

Note: the form routes through a 3rd-party relay and may be delayed or filtered.

FAQ

Is it really free and open source?

Yes — the repo is MIT and every bundled engine is open (OmniVoice Apache-2.0, Chatterbox MIT). Run it forever at no cost.

Do I need a big GPU?

OmniVoice runs on 6 GB VRAM; Qwen3-TTS / Chatterbox on 8 GB. CPU works but slower. Cloud API covers the rest.

Can I use it commercially?

Self-hosted: yes under each engine's license. Cloud API plans include a commercial license.

How is this different from ElevenLabs?

You own the stack, your audio stays local, and there are no rate limits or subscriptions. Cloud is optional.