Voicebox
Free, MIT-licensed desktop voice studio that clones voices, generates speech with seven local TTS engines such as Qwen3-TTS, Chatterbox and Kokoro, dictates into any app with Whisper, and exposes voices to agents over MCP.
About Voicebox
Voice cloning and dictation tools usually run in the cloud with subscriptions and send your recordings to a vendor.
Who it’s for
- Creators who want local voice cloning and text-to-speech without per-character fees
- Developers who want agents to speak in voices they own through MCP
When to consider it
Consider Voicebox when you want one local app for voice cloning, multi-engine speech generation and dictation that runs on your machine without an account.
Tradeoffs & limitations
- Prebuilt apps are for macOS (Apple Silicon and Intel) and 64-bit Windows; Linux users must build from source.
- The Cloud ($12 a year launch price) and Studio sync and backup plans are listed as coming soon, so there is no cross-device sync yet.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Voicebox.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Nov 2, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Voicebox official website
Free, MIT-licensed desktop voice studio that clones voices, generates speech with seven local TTS engines such as Qwen3-TTS, Chatterbox and Kokoro, dictates into any app with Whisper, and exposes voices to agents over MCP.
Based on official pages and announcements checked on 2026-11-02. No hands-on test, performance benchmark or popularity ranking is claimed.