Skip to main content

How to create Audio Description (AD) for a video 👁️‍🗨️

Make a video accessible to blind and partially sighted viewers: what to describe, broadcast AD standards (140–160 wpm, 1.5–2 s gaps, 0.25–0.5 s buffers), and the step-by-step workflow in Video Narration with MARS8-Instruct pacing tags.

Audio Description (AD) makes a video accessible to blind and partially sighted viewers. A narrator describes the important things you can only see (actions, settings, on-screen text) in short, objective sentences placed in the natural pauses between dialogue. In CAMB.AI you create AD with Video Narration.

ℹ️ New to Video Narration? Read How to create an AI video narration and How do I use the editor in Video Narration? first. This article adds what's specific to AD.

What should I describe?

  • Actions and body language: movements, facial expressions, gestures and where people are, when they drive the story. For example "Carries his box to the table." or "She frowns."

  • Settings and scene changes: the location, time of day, lighting and transitions, when they change or set the scene.

  • On-screen text and graphics: opening titles, name and role captions (lower thirds), scoreboards, prices and other key graphics.

  • Appearance and costumes: clothing, props or details that help identify a character or set the tone. For example "Adam wears a bold Hawaiian shirt."

How should AD be written?

  • Present tense: describe the action as it happens. "Stephen steps to a contestant", not "Stephen stepped".

  • Objective and neutral: describe what is visible. Don't explain motives, judge emotions or add literary flourishes.

  • No spoilers: never reveal a plot twist, punchline or reveal before it happens on screen. A split-second lead-in is fine when dialogue starts right after a quick visual cue, so the description doesn't collide with the speech.

  • Concise and specific: use strong verbs and exact nouns. Skip filler such as "We see…" or "On screen…".

What timing standards should I follow?

Never talk over dialogue, commentary, lyrics or sound effects that matter to the story. Broadcast AD usually follows these benchmarks:

  • Speech rate: 140–160 words per minute (about 2.5–3 words or 14–16 characters per second).

  • Minimum gap: a pause of at least 1.5–2 seconds between dialogue lines to fit a short description without rushing.

  • Cue length: 1–2 short sentences per description, roughly 40–120 characters depending on the gap.

  • Safety buffer: leave about 0.25–0.5 seconds before and after dialogue so the description never clips the speech.

ℹ️ Use these numbers as a guide, not hard limits. AI voices adapt their pace to each line, so check each description by ear in the preview rather than by word count alone.

How do I create AD in CAMB.AI?

Step 1: Create the project

  1. In the left sidebar, under Projects, click Video Narration.

  2. Upload your video under File, or paste a Link.

  3. Choose the Source Language for the AD track and click Select Narrator voice to pick a voice (you can preview voices before choosing).

  4. Already have a written AD script? Upload it under Script (Optional) on the right (.txt or .docx).

  5. Click Begin Narration.

Step 2: Review and refine the descriptions

  1. Automatic gap placement: CAMB.AI analyses the original audio, finds the natural pauses between dialogue and places the AD lines in those silent gaps on the timeline.

  2. Refine the text: click a line to edit it, so each description fits comfortably in its gap without overlapping dialogue. You can also move or resize a line on the timeline, or add, split, merge and delete lines. See How do I use the editor in Video Narration?

  3. Generate and listen: generate the audio and play the video through to check that each description matches the picture, sits in a natural pause and is balanced with the original sound. If a line sounds unnatural or clips into dialogue, shorten the text or change its pacing tag, then re-generate just that line. See How to re-generate dialogues after editing.

Tip: control the pace with MARS8-Instruct

Video Narration uses MARS8-Instruct by default, so you can direct the delivery with a tag. When a gap is tight and a line sounds rushed or too slow, add a pacing instruction such as [fast paced] or [concise, brisk pace] to that line and re-generate. See the Emotion Tag Gradation Guide and Which speech model should I choose?

Step 3: Export

When every description sounds right, click Export (top-right) to download the video with the AD track, the audio, or subtitles. See How to download output files.

Checklist before you export

  • No description overlaps dialogue, lyrics or important sound effects.

  • Each description is in the present tense, objective and free of spoilers.

  • On-screen text, titles and name captions are read out.

  • Names are pronounced correctly. If not, see How to make your audio sound good.

  • You've listened to the whole video at least once from start to finish.

Attachment icon
Did this answer your question?