- {post.tags.map((tag) => (
-
- {tag}
-
- ))}
-
- ) : null}
- - {post.title} -
-- by {post.author} ·{" "} - {formatDate(post.date)} · {post.readingMinutes} min read -
-
+ 
- 
+ 
- 
+ 
- by {post.author} ·{" "} - {formatDate(post.date)} · {post.readingMinutes} min read -
-- The story behind the project, what's shipping next, and the occasional - look under the hood. -
- - {posts.length === 0 ? ( -- Nothing published yet. -
- ) : ( -{formatDate(post.date)}
-{post.readingMinutes} min read
-- {post.excerpt} -
- ) : null} - {post.tags.length > 0 ? ( -- Hold the shortcut, speak, release — a capture lands in the Captures tab. Replay the - original audio, re-transcribe with a different model, refine with a local LLM, copy to - clipboard, or send it straight to any MCP-aware agent. Nothing leaves your machine. -
-- Base, Small, Medium, Large, and Turbo. Pick per-capture — 99 languages at every - tier, all local, all downloadable from inside the app. -
-- A local Qwen model cleans ums, self-corrections, and punctuation — without - rephrasing. Keep raw and refined side-by-side; the original audio is always kept. -
-- Every dictation keeps both the audio and the transcript. Search, re-run, or turn - any capture into a voice sample for cloning from the Captures tab. -
-- Free, open-source, local. No account, no API keys, no per-character fees. -
-- Optional, end-to-end encrypted backup and sync for your entire - Voicebox library. We can't read a byte of it — only your devices - can. Free for{" "} - - $VOICEBOX - {" "} - holders. -
- -- {f.body} -
-- {step.body} -
-- Voicebox is local-first and privacy-first. The cloud keeps that - promise: your library is encrypted before it leaves your device, - the server stores only ciphertext, and the keys never leave your - control. Same philosophy as the app — just backed up. -
-- {activeMeta - ? `Downloading Voicebox for ${activeMeta.label} (${activeMeta.description}). Check your downloads folder.` - : 'Check your downloads folder for Voicebox.'} -
- - ) : ( - <> -- {linksError - ? 'Our release server is temporarily unreachable. Please try again in a moment.' - : 'Pick your platform to get started.'} -
- - )} -- If this keeps happening, you can{' '} - - browse releases on GitHub - - {' '}and grab the build for your platform manually. -
-- I build and maintain Voicebox in my spare time. It's completely - free, open source, runs entirely on your machine — no accounts, no - cloud, no subscriptions, no upsells. If it saves you an ElevenLabs - bill or just made your day, a coffee genuinely helps me keep - shipping updates, adding new models, and fixing bugs. Every little - bit keeps the lights on. -
- -- We're currently working through CI issues that prevent us from shipping a reliable - pre-built binary for Linux. In the meantime, building from source is straightforward and - takes just a few minutes. -
- -cargo install just
-
- The built app will be in{' '}
-
- tauri/src-tauri/target/release/bundle/
-
-
-
- Open source voice cloning.
-
- Local-first. Free forever.
-
-
- {/* Border overlay */}
-
-
- - Clone voices, generate speech across seven TTS engines, dictate into - any app, and talk to agents in voices you own. A free and local alternative - to ElevenLabs and WisprFlow, running{" "} - entirely on your machine. -
- - {/* CTAs */} - - - {/* Version + downloads */} -- {version ?? ""} - {version && totalDownloads != null ? " \u00b7 " : ""} - {totalDownloads != null - ? `${totalDownloads.toLocaleString()} downloads` - : ""} - {version || totalDownloads != null ? " \u00b7 " : ""} - macOS, Windows, Linux -
-- Available for macOS, Windows, and Linux. No dependencies required. -
-- Everything that makes Voicebox great runs locally at no cost. Pay - only if you want optional, encrypted cloud backup & sync — and - holders get that free. -
-- The token is an optional way to back the project — and holders get - the Cloud tier at no cost. Learn how it works and verify everything - on-chain. -
- - View the token → - - -- {item.a} -
-- Cloud pricing and limits are not final — they'll be confirmed at - launch. -
-- Voicebox grew to over a million downloads with zero marketing — - but donations alone never made full-time work sustainable.{" "} - {TOKEN_TICKER} changed that overnight, and it's already - accelerating everything below. The app stays{" "} - free, open source, and local-first{" "} - — forever. -
-- {item.body} -
-- Encrypted cloud backup and sync (and the mobile cloud) will be a - paid service — roughly{" "} - $12/year for everyone else, and{" "} - free for {TOKEN_TICKER} holders. - Generate on the go, keep your captures and generations safe, and - pick up on any device. -
-- {item.a} -
-- {TOKEN_TICKER} is a community token with no affiliation to any - exchange or financial product. Nothing on this page is financial - advice. Verify the contract address before buying. -
-
- {MCP_CONFIG}
-
-
- {SPEAK_EXAMPLE}
-
-
- {/* Hint line */}
- POST /speak for anything that
- doesn’t speak MCP — ACP, A2A, shell scripts, or custom harnesses.
-
- One tool call —{' '}
- voicebox.speak —
- and any MCP-aware agent can talk to you in a voice you’ve cloned. Claude Code,
- Cursor, Cline, or anything that speaks MCP.
-
- {bullet.description} -
-- Every engine you download becomes a REST endpoint on your machine. - Build apps, games, and voice tools with full programmatic control — - no API keys, no rate limits, no per-character fees. -
-
- http://127.0.0.1:17493
-
-
- {ep.path}
-
-
- {ep.label}
-
-
- {CURL_SNIPPET}
-
- - {uc.description} -
-- Hold a key anywhere on your machine, speak, release — your words land in the focused - text field. A free, open-source, entirely-local alternative to{' '} - WisprFlow. And because Voicebox clones voices too, any - AI agent can speak back in a voice you own. -
- - {/* CTAs */} - - - {/* Version + downloads */} -- {version ?? ''} - {version && totalDownloads != null ? ' · ' : ''} - {totalDownloads != null ? `${totalDownloads.toLocaleString()} downloads` : ''} - {version || totalDownloads != null ? ' · ' : ''} - macOS, Windows, Linux -
-{feature.description}
-- Hold a shortcut anywhere on your machine, speak, release. - The transcript lands in a focused text field in any app, or your clipboard. Agents speak - back through the same pill in any cloned voice. -
-
-
- Latest Version
-{LATEST_VERSION}
-{description}
-{feature.description}
-- Everything you need to clone voices, generate speech, and produce multi-voice content — - running entirely on your machine. -
-“{PERSONA_DESCRIPTION}”
-- Give any voice profile a free-form personality. Then{' '} - Rewrite your text in their voice, or let them{' '} - Compose a fresh line of their own — your cloned voice, in full character. -
-- {bullet.description} -
-- {tier.tagline} -
- -- {isFree - ? tier.priceNote - : period === "annual" - ? tier.priceNote - : `Billed monthly · ${tier.priceNote ?? ""}`} -
- - - {tier.cta.label} - - -- {model.description} -
- {model.tags && model.tags.length > 0 && ( -{group.subtitle}
-- Pick the right model for every job — TTS, transcription, refinement. All models run - locally on your hardware. Download once, use forever. -
-- Voicebox has passed 1M+ downloads. Here's a handful of notes from - the people using it every day. -
--
- {t.quote} --
- The official {TOKEN_TICKER} token for supporters who want to back - the project and have some fun. Voicebox is and always will be{" "} - free and open source — the token - is entirely optional and not required to use anything here. -
-- Supply, holders, burns, locks and team holdings for {TOKEN_TICKER}, - read live from Solana. -
-
- Lifetime {TOKEN_TICKER} trading fees — the funding that pays for
- full-time work on Voicebox.{" "}
-
- Verify
- An optional way to back the project and have some fun. Voicebox is and - always will be{" "} - free and open source — the token is - not required to use anything here. -
- - - Learn about {TOKEN_TICKER} -{tutorial.author}
-- Coming soon -
-- Walkthroughs from the community covering setup, voice cloning, and - production workflows. -
-
- Drag and drop an audio file, or click to browse.
-
- Maximum duration: 30 seconds.
-
- Click to record from your microphone.
-
- Maximum duration: 30 seconds.
-
{formatTime(30 - elapsed)} remaining
-
- Capture audio playing on your system.
-
- Maximum duration: 30 seconds.
-
{formatTime(30 - elapsed)} remaining
-- Three ways to get a sample in. Upload a clip, record from your microphone, or - capture audio playing on your system. Voicebox clones the voice from as little as 3 - seconds of audio. -
-- {description} -
-