Audio descriptions.Hours faster.
Purpose-built desktop software for professional audio describers. Automatic scene detection, dialogue transcription and voicing handle the busywork — you write every word, fully offline, on your own machine.
00:01:14:08The workflow problem
Three tools. Five hours. One 30-minute video.
Professional audio describers juggle a video editor, an audio editor, and manual spreadsheets. No tool was built for the AD workflow — it was stitched together from generic software.
Every export, timestamp, and voice pass eats time that should go into the writing. EAA 2030 and CVAA are pushing the industry to scale — manual tool-juggling doesn't.
For professional audio describers & AD service companies
Less tool-juggling, more writing time.
Synchrogen is not here to write your descriptions for you. It is here to remove the parts of the job that don't need a storyteller — finding the gaps, avoiding dialogue, voicing the line — so your attention goes to the writing.
Every description is written by you, timed by you, approved by you. AI-assisted first drafts are on the roadmap — the tool you get today is a manual editor with the busywork stripped out.
Know where to write, instantly.
Scene detection and dialogue transcription find the gaps for you — scene by scene, timed to the cut. You open a script that already knows where every description belongs. No manual timestamp math.
Dialogue never gets stepped on.
The transcript is locked in automatically, so your descriptions never collide with a spoken line. Trim, retime, or duck the dialogue track — resolved inline, on the timeline.
Write once, hear it instantly.
Type a description and voice it with built-in local narration in seconds — no separate recording pass, no external audio editor, no re-import. Your writing time goes further.
Every decision is yours.
Edit any clip inline, split or merge, approve at your own pace — every keystroke logged to an audit trail. You write it, you time it, you decide what ships.
00:02:30:00Inside the platform
Seven screens, one workflow.
Closed-beta product, shipping today. Use the rail below to jump anywhere, or let it play — this is the editor as it exists right now, not a concept.
What the describer writes. Voiced locally with built-in text-to-speech, in your own words.
Source audio, transcribed automatically. Always wins. Descriptions yield, every time, by design.
Cuts, jumps and time-changes — detected automatically, framed for the listener.
Your footage never leaves your machine. Video, descriptions, and project data live in a local database on your computer — scene detection, transcription, and narration all run on-device. The only thing that touches the cloud is your login.
00:04:08:12Voice delivery
Voicing, built in.
No separate recording software, no re-import step. Write a description and hear it narrated in the same window.
Write it, voice it, on the spot.
Type your description and generate narration right in the editor — local text-to-speech, no separate recording pass, no re-import from another tool. It runs entirely on your machine.
More voices and languages, coming.
Additional narrator voices, an expanded language set, and custom voice options are planned next. Today's voicing already covers your typed descriptions out of the box.
00:05:42:00Built around your standards
Quality is designed in, not bolted on.
The editor is built around the standards a senior describer already holds themselves to — dialogue never gets stepped on, nothing gets missed, and every decision is logged.
Coverage
Scene and gap detection surface every place a description could go, so nothing gets missed before delivery.
Timing & sync
Descriptions never collide with dialogue. The dialogue track wins, always — enforced by the editor, not a checklist.
Show, don't tell
The editor stays out of your prose. Factual, third-person description is the standard we design the workflow around.
Audit trail
Every approval, edit, and export is logged, so a completed project has a clear record for compliance sign-off.
00:06:30:08Your time back
Same compliance bar. More billable hours back.
An illustrative estimate — adjust to your monthly volume. Based on a 30-minute video typically taking 4–5 hours manually vs. an estimated 1.5–2 hours with Synchrogen at €35/hr; your own numbers will vary.
Hours you don't spend juggling tools are hours you can bill on the next project.
Pricing
00:08:12:00Asked by every professional describer
Frequently asked questions.
00:09:30:00Open beta · individual describers & service companies
Bring a project you're working on.
Leave with a faster workflow.
A 30-minute session on your actual content. We'll describe a clip from one of your videos together — edit it, retime it, export it — before you commit to anything.