Voicebarn
$34 once — yours forever

Unlimited natural-sounding text-to-speech on your own machine.

ElevenLabs Creator costs $22/month — $264 a year — and still caps you at 100,000 characters a month. Voicebarn runs Piper, a fast local neural TTS engine, on your own machine: unlimited characters, per-paragraph voice and speed control, batch folder conversion, and your unreleased scripts never touch anyone's cloud.

Desktop app · runs offline
See it run

Voicebarn in 60 seconds

What you get

Everything in the box

Local neural TTS via Piper — unlimited characters, per-paragraph voices, WAV/MP3 export.

Local neural TTS via Piper

Clean, natural narration voices, 100% offline after the one-time engine + voice download.

Per-paragraph control

Every paragraph gets its own voice + speed override (0.5x–2.0x), inheriting document defaults when left blank.

Inline pause tags

Drop <pause 500ms> or [pause 1s] anywhere for a precise, sample-rate-matched silence gap.

Instant preview

Synthesize and play any single paragraph before you export, with results cached by content hash.

WAV or MP3 export

MP3 via bundled ffmpeg with a bitrate picker (128/192/256/320 kbps).

Batch mode

Point it at a folder of .txt files and get one narrated audio file per input — chapter-by-chapter audiobook workflow.

8 curated starter voices

English (US/UK), German, Spanish, French — medium-quality Piper voices, each downloaded once from Hugging Face.

100% private

No telemetry, no account, no network calls except the clearly-surfaced one-time engine and voice downloads.

Side by side

Voicebarn vs ElevenLabs (Creator)

ElevenLabs (Creator) charges $22/mo. Here's what actually differs.

 VoicebarnElevenLabs (Creator)
Price$34 once$22/mo, forever (~$264/yr)
Characters Unlimited100,000/mo cap (Creator)
PrivacyText never leaves your PCUploaded to their cloud
Works offline Yes No
Per-paragraph voice/speed Yes No
Batch folder processing YesLimited/paid tier
Voice cloning No — narration voices only Yes
Account required No Yes

Pays for itself in under 2 months versus ElevenLabs Creator. Year two costs you $0; theirs costs another $264.

Pricing

One price. No asterisks.

Desktop app — pay once, it's yours on your machine forever.

Pay once, own it forever
Lifetime license
$34once
Free updates · MIT source on GitHub
Get Voicebarn — $34
Checkout by Whop · instant delivery · ElevenLabs (Creator) costs $22/mo
Downloads

Download Voicebarn

install, then sign in with Whop. Your purchase unlocks it; there is no licence key to enter.

Voicebarn

Windows and macOS. Buy once, download any time — this page always links the current build.

Installers are being published — check back shortly, or see GitHub releases.
macOS builds are unsigned — right-click the app and choose Open the first time. All releases on GitHub.
How it works

Up and running in three steps

  1. Buy once on Whop

    One-time $34 for the packaged Windows installer with lifetime updates — no terminal, no build step.

  2. First run downloads the engine

    The Piper engine (~22 MB) from official GitHub releases and your default voice (~60 MB) from Hugging Face, with a visible progress bar. After that it's fully offline.

  3. Write, preview, export

    Assign voices and speeds per paragraph, drop pause tags where you need a beat, preview any paragraph, export WAV or MP3 — or batch a whole folder.

FAQ

Fair questions

Is it really free on GitHub?

Yes — the full source is MIT at github.com/bensblueprints/voicebarn-mvp, always. $34 buys the signed installer, 1-click setup and updates instead of npm i && npm start.

Can it clone my voice or sound like a specific person?

No — and ElevenLabs is genuinely better if that's what you need. Voicebarn ships clean neural narration voices, great for videos, courses, audiobooks, IVR prompts and accessibility — not celebrity impressions or voice cloning. That's a different product category.

Does it support SSML?

Only an SSML-lite pause tag: <pause 500ms> or [pause 1s]. Piper doesn't support full SSML, and Voicebarn doesn't pretend otherwise — prosody, emphasis and phoneme tags will be read aloud literally. If you need real SSML, Piper isn't the right engine.

How does the quality compare to ElevenLabs?

Piper's voices are natural, clean narration voices — very good for the job, but ElevenLabs' newest cloud models are more expressive. What you get in exchange: unlimited characters, total privacy, offline operation and no bill ever again.

Does my text get uploaded anywhere?

Never. Synthesis runs locally via Piper (ONNX runtime on your CPU). The only network calls are the one-time engine and voice downloads, both clearly shown in the UI.

Stop renting. Own Voicebarn.

Local neural TTS via Piper — unlimited characters, per-paragraph voices, WAV/MP3 export.

Get Voicebarn — $34 once

Everything about Voicebarn — every page we have on it

Compare & pricing

Guides

Try & tools

Source