Voicebox: features, limits & comparisons
A local voice studio with cloning, reusable profiles, long-form generation and a multi-track editor.
functionality and fit
Recorded license: MIT.
- Qwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA and Kokoro; Whisper/Whisper Turbo for speech-to-text; local Qwen3 models for refinement and personas
- SQLite plus model, voice-profile, generated-audio and capture files in the local Voicebox data directory; original audio and transcripts stay on device
- Install the macOS DMG or Windows MSI; Docker is supported, while Linux currently requires a source installation
Costs and editions: A source license is separate from operating costs. Hosting, storage, external APIs and commercial support may require payment.
scope and migration checks
- It has no turnkey multilingual video translation and dubbing pipeline, and output consistency depends on the local engine and hardware.
- Local cloned and open models do not provide WellSaid's vetted commercial voice catalog, team collaboration or consistent studio QA.
- Voicebox is a heavyweight voice studio whose dictation hotkey is only one module, bringing larger models and more complexity than Superwhisper's focused utility.
recorded catalogue description · recorded source check 2026-08-11 · suitability checks are editorial assessments, not hands-on tests
licenseMIT
runson your machine
installInstall the macOS DMG or Windows MSI; Docker is supported, while Linux currently requires a source installation
enginesQwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox Multilingual, Chatterbox Turbo, HumeAI TADA and Kokoro; Whisper/Whisper Turbo for speech-to-text; local Qwen3 models for refinement and personas
dataSQLite plus model, voice-profile, generated-audio and capture files in the local Voicebox data directory; original audio and transcripts stay on device
setupLarge model downloads and choosing a hardware backend; Linux has no prebuilt binary yet
recorded source check 2026-08-11 · installation not tested
compare these app workflows
These are scoped comparisons, not guarantees that Voicebox reproduces every paid feature. Follow each build guide for the implementation boundary and the collection for other options.
A local voice studio with cloning, reusable profiles, long-form generation and a multi-track editor.
the verdict →Voice profiles, long-form generation and a multi-track story editor in one local app; collaboration is absent.
the verdict →Clone or choose a local voice, feed it a script and export long-form audio; the Mac build may need a Gatekeeper nudge.
the verdict →all LOVO alternatives →A local voice studio with cloning, seven engines, transcription and a multi-track editor; dubbing still takes manual assembly.
the catchIt has no turnkey multilingual video translation and dubbing pipeline, and output consistency depends on the local engine and hardware.
the verdict →all ElevenLabs alternatives →Reusable local voice profiles, long-form scripts and exportable audio without a character meter.
the catchLocal cloned and open models do not provide WellSaid's vetted commercial voice catalog, team collaboration or consistent studio QA.
the verdict →all WellSaid Labs alternatives →Voice cloning studio attached to a global dictation hotkey; overkill, free overkill.
the catchVoicebox is a heavyweight voice studio whose dictation hotkey is only one module, bringing larger models and more complexity than Superwhisper's focused utility.
the verdict →all Superwhisper alternatives →Local voice cloning, generation, transcription and an API in one installer; detection and a managed realtime SLA are absent.
the verdict →latest catalogue source check 2026-08-11 · recorded recurring plans: $941.88/yr (before operating costs) · no votes, no pay-to-list
sources and related categories
These are sources retained with the catalogue record. Their recorded check date is not a new verification of current terms.