Local speech production studio for Mac
Local speech production means turning recordings, scripts and authorized reference voices into a finished speech deliverable on the Mac. VoxForge is designed around that job: one persistent project holds the transcript, speakers, edits, voice takes and exports.
Updated 22 September 2026. VoxForge targets macOS 14+ on Apple silicon. Candidate build 9 is in preparation; beta access and commercial terms are not yet open.
What the workflow covers
- Import a rights-cleared local recording or script.
- Create a transcript with a supported local model and correct words or speakers.
- Build a supported local voice take where the selected engine and hardware allow it.
- Export text, subtitles or audio from the saved project.
What local means here
User-media processing runs locally in the documented workflow. Model downloads and ordinary network request metadata remain possible. Local processing is not a claim of absolute security, perfect accuracy or zero network activity.
Who this fits
VoxForge is for independent podcasters, course and video creators, audio producers, journalists, researchers and small studios that repeatedly finish speech projects on Apple silicon. Free is planned to start with local transcription, basic local TTS, basic exports and one active simple project. Pro is planned as a one-time purchase for broader engines, reusable consent-aware profiles, production workspaces, batch jobs, mastered bundles and unlimited projects; pricing remains approval-gated.
Where it does not fit
Choose a cloud editor for live multi-user collaboration, hosted API scale or access from multiple device types. Choose a transcription specialist for a transcript-only job. VoxForge does not promise every language, perfect speaker separation, arbitrary voice cloning or a universal quality result.