Fuchsia Studio is a Mac app for documentary and podcast producers. The craft runs on your Mac, and your audio never leaves it. If something isn't working, start below — or write to us.
There's no account to create and no cloud project to set up. Importing, transcribing, searching and assembling all run on your Mac; only the optional AI features send anything off it, on your own key.
A Mac running macOS 26. That's the whole list, and there's no account to create. macOS downloads Apple's speech model once; after that, none of that work needs the network.
From the Mac App Store. Download Fuchsia Studio, open it, and you're working: no sign-up, no login, no cloud project to create. You land in a native Mac document window and open — or start — a story.
Free to download, and free in full for fourteen days — no cap, no watermark, nothing held back. After that, only assembling stories needs a purchase: $129 or equivalent once, on the Mac App Store, not a subscription. Everything you already made stays open, playable and exportable — it's yours. Importing tape, transcribing it and recording narration stay free, always. Studio Pro, which adds the command line and an MCP server, isn't available yet; when it is, it will be sold separately, direct from us.
Bring it all in at any sample rate. Studio always finishes at 48 kHz, conforming other rates as it renders and naming each source it resampled in the export report. The file you deliver is a separate choice, at the rates your chosen format can actually deliver.
Short, honest answers to the things producers ask most. If yours isn't here, email us — we read everything.
Open Tape view (⌘2): your source is laid out there as a readable page, word for word. If a recording hasn't appeared yet, Studio is most likely still transcribing it and separating the speakers — all of that runs on your Mac, and hours of tape take real time to work through. It needs no account, and once your Mac has what transcription needs, no network either. The one exception is the first time: the speech model is supplied by macOS, not by us, so if this Mac doesn't already have it, macOS downloads it — once. A tape you import before it arrives simply has no words until it does. Give it time.
The usual cause is that the audio lives on a drive that isn't connected. If you imported from an external drive that has since been unplugged, reconnect it — Studio needs to reach the original audio to play it.
The same applies at export: if export warns you about offline clips, moments in your running order point at audio Studio can't currently reach. Reconnect the drive that holds those recordings and export again.
The reads — the Thread, the interpretations in Reading view, and speaker-name proposals — are opt-in and run on your own AI provider account, not on your Mac. So first: have you added a provider key in Settings?
If a key is entered and the reads still won't run, check that you're online and that the key is still valid on the provider's side — an expired key or an exhausted allowance there will stop the reads. Everything else in Studio — import, transcription, speaker separation, search, editing, assembly, finishing — never uses the key and keeps working regardless.
Yes. Speakers arrive as unnamed voices — Speaker 1, Speaker 2 — and you can rename any of them. A name you type yourself is never overwritten. If you've connected an AI provider, Studio proposes a name only when that name is actually spoken on tape: the moment plays, and nothing changes until you confirm that it belongs to this voice.
One honest limit in this release: you can rename a voice, but not move a passage from one voice to another. If the separation itself put words under the wrong voice, we'd like to hear about it — get in touch so we know it matters to you.
Email us at support@fuchsiaprojects.com. Tell us your macOS version and what you were doing when things went wrong; if it involves a specific recording, the file format and sample rate help too. We read everything, and feature requests are genuinely welcome.
The short version, and the part that matters day to day: the craft — import, transcription, speaker separation, search, editing, finishing — runs on your Mac with no account, and your audio never leaves it. AI features are opt-in, run on your own Anthropic key, and send only text, never your audio.
Read the full Privacy Policy.