100% Local • Zero Cloud • Your Voice Stays Private

Clone your voice.
Keep it yours.

Record 5 seconds. VoiceForge clones your voice on-device and generates speech from any text — forever. No subscription. No servers. No one else touches your voice data.

One-time payment
No internet required after setup
macOS • Windows • Linux
Apple Silicon • NVIDIA • CPU
MIT licensed core

From recording to narration
in under a minute

No vocal training, no engineers, no waiting. Just record a short sample and VoiceForge handles the rest — entirely on your machine.

1

Record or Upload

Capture 5–10 seconds of your voice in the app, or upload any clean audio clip you already have.

~10 seconds
2

Clone Your Voice

Qwen3-TTS analyzes your vocal signature locally. No audio ever leaves your machine — processing happens on your GPU or CPU.

~5 seconds
3

Generate Anything

Type or paste any text. Hit Generate. Export to WAV, MP3, FLAC, or M4A instantly. Repeat forever with no extra cost.

Real-time

Built for creators,
not cloud companies

Every feature is designed to work completely offline, so you own your voice and your workflow.

Quick Clone Mode

Record or upload a 5–10 second voice sample, paste your text, and generate speech in seconds. Perfect for one-off clips, social media voiceovers, or podcast intros.

5-sec sample Instant output VoiceDesign style hints
📚

Voice Library

Save as many cloned voices as you want. Switch between them instantly — ideal for creators who narrate multiple characters or brands.

Unlimited voices Local storage only Named profiles
🌐

OpenAI-Compatible API Server

Run tts_server.py and get a local /v1/audio/speech endpoint. Drop VoiceForge into any workflow that supports the OpenAI TTS API — n8n, LangChain, custom scripts, anything.

OpenAI-compatible Local port only Scriptable n8n / LangChain ready

Hear the difference

This simulates VoiceForge's Quick Clone interface. In the real app, output is generated by Qwen3-TTS running locally on your machine in real time.

VoiceForge — Quick Clone
Initializing local model…
Output ready — voice_output.wav
0:00 / 0:00
💻

Your Machine.
Your Voice. Full Stop.

All AI inference runs locally using Qwen3-TTS. Models are downloaded once from Hugging Face (~2GB) then run entirely offline.

🔒

Zero cloud. Zero compromise.

When you clone your voice with ElevenLabs or Play.ht, your audio goes to their servers and trains their models. With VoiceForge, it never leaves your machine.

🚫

No audio uploads ever

Your reference recording is processed locally. It is never transmitted anywhere.

🆕

No account required

Buy once, download, run. No login, no API keys, no profile to delete.

Works offline

After the initial model download, VoiceForge runs with no internet connection required. Planes, boats, bunkers — wherever.

🔑

You own the output

Generated audio is yours, no licensing restrictions from a cloud TTS provider.

Why pay monthly
for your own voice?

Cloud voice cloning services charge recurring fees AND process your voice on their infrastructure. VoiceForge does it better, once, for less.

Feature VoiceForge ElevenLabs Play.ht
Pricing $49 one-time $11–$99 / mo $31–$99 / mo
Voice stays on your machine Yes No No
Works offline Yes No No
Voice cloning from sample Yes — 5 sec Yes Yes
Audiobook / EPUB mode Yes No No
Unlimited generation Yes Credit limits Credit limits
OpenAI-compatible API Yes Yes (cloud) Partial
Apple Silicon (MPS) Yes N/A (cloud) N/A (cloud)
Export formats WAV, MP3, FLAC, M4A MP3, WAV MP3, WAV
No account needed Yes Required Required

At $99/mo for ElevenLabs, VoiceForge pays for itself in less than two months — and you keep it forever.

Runs on what you have

VoiceForge detects your hardware automatically and uses the fastest available inference backend.

Apple Silicon

Mac M1 / M2 / M3 / M4

Runs via Metal Performance Shaders (MPS). Fast generation on Apple Silicon. 16GB unified RAM recommended.

NVIDIA CUDA

CUDA GPU (Windows / Linux)

Requires CUDA 12.4+ and 8GB+ VRAM. Generation is real-time on mid-range and above GPUs (RTX 3060 and up). AMD ROCm 6.2+ also supported.

CPU Fallback

Any Modern CPU

Works without a GPU. Slower — expect 2–5× real-time. 32GB RAM recommended. Good for occasional use or older machines.

One price. Yours forever.

No subscription tiers, no monthly limits, no data harvesting business model. Pay once and generate as much as you want.

Open Source

$0
Free forever

Self-host from source. Requires Python 3.12+ and some CLI comfort.

  • Full source code (MIT license)
  • All core features
  • Community support (GitHub)
  • Native desktop installer
  • Bundled Python runtime
  • One-click setup
Best Value

VoiceForge Desktop

$49
One-time purchase — no subscription

Native desktop app for macOS, Windows, and Linux. Everything bundled. Just download and run.

  • macOS DMG (arm64 + Intel)
  • Windows NSIS installer
  • Linux AppImage
  • Bundled Python — no setup needed
  • Quick Clone + Audiobook Mode
  • Voice Library + API Server
  • Lifetime updates
  • Email support

30-day money-back guarantee. If VoiceForge doesn't work on your hardware, we'll refund you, no questions asked.

Your voice.
Your machine. Your terms.

Stop paying monthly to rent access to your own voice. VoiceForge runs locally, costs once, and generates forever.

macOS • Windows • Linux • No subscription • 30-day guarantee