Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

Voicebox

voicebox.sh

  • Free plan
  • Open source
  • Windows
  • macOS
  • Linux
  • Web
  • iPhone and iPad
  • Android
  • API
  • Self-hosted
8.6 Club score Visit voicebox.sh

What Voicebox is

Voicebox is a free, open-source local AI voice studio for voice cloning, speech generation, dictation and agent voice output. The desktop app can clone a voice from a short recording or uploaded audio, and the maker lists seven text-to-speech engines with cloning, preset voices and delivery controls. Its timeline editor supports multi-voice stories, track arrangement, trimming and conversation mixing. Effects include pitch shift, reverb, delay and compression. A keyboard shortcut can send dictation to the focused text field or clipboard; local Whisper models support 99 languages. Voicebox offers a local REST API, and compatible agents can use a speak endpoint. The app works offline without an account; its privacy policy says recordings, profiles, transcripts, generations and settings are not sent to the maker. The Local plan is free forever with unlimited local generations and captures. Cloud plans are listed at $12/year and $48/year, but cloud availability, pricing and limits are marked as not final or coming soon.

Who it suits

Voicebox suits people who want local voice generation, voice cloning or dictation, as well as developers connecting speech to agents through an API. It is available for desktop systems including macOS, Windows and Linux.

Good to know, and what to watch

  • Open-source local app works offline without an account.
  • Local generations and captures are unlimited on the free plan.
  • Dictation supports local Whisper models in 99 languages.
  • Timeline editor supports multi-voice narratives and mixing.
  • Local REST API exposes speech-generation functions.
  • Cloud backup and mobile sync are marked coming soon.
  • Cloud pricing and limits are not final.
  • Linux download is listed as build from source.

Local

Free

Cloud

$12/yr

Studio

$48/yr

Free plan

Getting started

  1. Download the desktop app for macOS or Windows
  2. Build from source on Linux if required
  3. Launch Voicebox; the Local plan needs no account
  4. Import or record at least three seconds of voice audio
  5. Create speech, dictation or agent output locally

Limits to check

The Local plan is free forever with unlimited local generations and captures. Cloud plans are marked coming soon, with pricing and limits not final; the listed Cloud plan includes 25 GB and five devices, while Studio lists 250 GB and unlimited devices.

The verdict

Voicebox focuses on local voice tools, with editing, dictation and API functions alongside cloning and speech generation. The free Local plan is available now; cloud backup and mobile sync are not yet presented as ready offerings.

Questions people ask

Is Voicebox free?

The Local plan is free forever, includes the full app and requires no account. Paid plans are listed from $12/yr.

Which platforms are supported?

Voicebox lists Android, iOS, API, Linux, macOS, self-hosted and Windows support. Desktop downloads cover macOS and Windows, while Linux is built from source.

Does Voicebox work offline?

Yes. The desktop app works offline without an account.

How quickly can it clone a voice?

Voicebox can clone a voice from as little as three seconds of audio supplied by upload, microphone or system capture.

What are the cloud plans?

Cloud is listed at $12/year and Studio at $48/year, both coming soon; cloud pricing and limits are not final.

What the maker publishes

Agent integration
The built-in MCP server lets Claude Code, Cursor, Cline, Windsurf, and other MCP clients call Voicebox speech tools. source
Agent integrations
MCP-aware agents including Claude Code, Cursor, and Cline can speak through Voicebox using a cloned voice; the maker also describes a POST /speak endpoint for other clients. source
API
Voicebox exposes a local REST API for speech generation, voice profiles, model status, generation history, and health checks. source
API access
Yes source
API endpoint
The documented local server runs at http://127.0.0.1:17493 and exposes OpenAPI documentation at /docs. source
Architecture
Voicebox uses a Tauri desktop shell, React and TypeScript frontend, and Python FastAPI backend communicating over localhost HTTP. source
Audio effects
Voicebox offers pitch shift, reverb, delay, compression, and other effects, with saved presets and live preview. source
Audio effects
Its effects pipeline supports pitch shift, reverb, delay, compression, and saved presets. source
Cloud security
The announced cloud backup encrypts library data on users’ devices, while servers store ciphertext and cannot decrypt it. source
Cloud status
Voicebox Cloud is marked coming soon, and the pricing page says cloud pricing and limits are not final. source
Commercial use
Yes source
Company facts: acquisition record
Crunchbase lists Voicebox Technologies Corporation as acquired by Nuance Communications and operating status closed. source
Company facts: similarly named entity
LinkedIn lists a separate Voicebox Technologies Corporation in Bellevue, Washington, founded in 2001, with 201–500 employees. source
Company identity
The Voicebox website footer identifies the maker as Spacedrive Technology Inc. source
Dictation
A global keyboard shortcut records speech and sends the transcript to the focused text field or clipboard; local Whisper models support 99 languages. source
Dictation
A global keyboard shortcut records speech and places the transcript into a focused application field or the clipboard. source
Documentation
The documentation covers installation, Docker deployment, quick start, GPU acceleration, dictation, cloning, MCP, stories, troubleshooting, API reference, architecture, building, and contributing. source
Free plan
Yes source
Languages
23 source
Licence
The source repository is released under the MIT licence, permitting use, modification, distribution, sublicensing, and sale subject to the notice requirement. source
Limit: cloning setup
Dave Swift reported that models must be installed before cloning, clipped recordings can make cloning fail, and the app uses the operating system's selected microphone. source
Limit: commercial polish
HysenLabs characterized Voicebox as unsuitable for users needing a fully polished commercial product or prebuilt Linux binaries. source
Limit: compliance
HysenLabs noted that the project claims no compliance certification despite local processing being suitable for privacy-sensitive workflows. source
Limit: effects bug
Dave Swift reported that built-in effects were unimpressive and saving customized presets produced an error. source

Checked against the maker's pages on 14 Oct 2026.