Every video, described — in the words it deserves.

tomiko watches your footage, writes the visual action in the language of professional audio description, and speaks it into the pauses — so blind and low-vision audiences never miss the scene.

Describe a video free →
Fig. 1 — the waveform of your soundtrack Description is placed only in the silences between dialogue — never over it.
00:03
00:09
00:21
The method

Three steps, the way a describer would work.

1

Find the silences.

tomiko transcribes the dialogue to the word and inverts it, leaving the gaps — the moments where a describer is allowed to speak.

2

Describe the scene.

A vision model reads the footage and writes concise, present-tense description, sized to fit each gap — following the craft the BBC and Netflix style guides teach: actions, entrances, expressions, never a word over the dialogue.

3

Voice & mix.

A natural narrator speaks each line; the original soundtrack is gently ducked beneath it. Review and edit any line, then render.

What you take away

Three ways to leave with it.

Described video
Your film with the description as a second, switchable audio track — ready to publish.
AD audio stem
The narration alone, as a clean WAV, to drop into Premiere or DaVinci on your own timeline.
Text track
A WebVTT of every description with its timecode, for players and archives.
Pricing

Pay for finished minutes. Start free.

FreeTry itPro$39 / moBusiness$149 / mo
Included / month10 min40 min200 min
Overage / minute$1.50$1.00
Resolution720p1080p1080p
ExportsVideo · VTT+ AD stem (WAV)+ API · batch
LicenceNon-commercialCommercialTeam · multi-language
Start free → Choose Pro → Choose Business →

$1.50 per finished minute, pay as you go — roughly twenty times less than a manual studio, and built for the EU Accessibility Act.

Give your first video a voice for its pictures.

Get 10 free minutes →