Audio Description

Introduction

The Audio Description feature uses AI to generate audio description tracks for your videos. Audio descriptions narrate visual elements—such as actions, scene changes, and on-screen text—making content more accessible for viewers who are blind or have low vision. This feature generates Standard Audio Description, meaning it fits descriptions into natural pauses in the video.

You can generate audio description from three entry points in Video Cloud Studio:

• Upload Module – Generate audio description during or after the upload workflow.
• Media Module – Two paths:
  • Bulk generation – Generate audio description for multiple videos at once.
  • Video-level generation – Generate audio description for a single video from Video Details.

Setting default languages

Configure default audio description languages so they are pre-selected when you generate audio description from the Upload module or the Media module. This is a configuration step only and does not trigger any generation.

1. Navigate to the Admin module.
2. Under Upload Settings, locate the Audio Description field.
3. Add or select the default languages for audio description.

   

4. Click Save to store your settings.

Upload Module

Generate audio description from the Upload module as part of your upload workflow.

1. Navigate to the Upload module.
2. In the Audio Description field on the left, select the languages you want to generate audio description for.

   

3. Complete the upload. When processing is complete, audio description tracks will appear as Audio Tracks with variant Descriptive in the video’s Video Details (see Where Audio Descriptions Appear).

Media module: Bulk generation

Generate audio description for multiple videos at once from the Media module.

1. In the Media module, select the videos you want to process.
2. Click the ... menu and choose Captions and Audio.

   

3. In the dialog, navigate to the Audio Description section on the left, then set your languages using the Add button on the right. Save the language(s) you have chosen.

   

   

4. Click Generate to trigger audio description generation.

   

5. When processing is complete, audio description tracks will appear in the Languages section of each video’s Video Details page (see Where Audio Descriptions Appear). Review and publish as needed.

Media module: Video-level generation

Generate audio description for a single video from the Video Details page.

1. In the Media module, open a video and locate the Languages section.
2. Click the Add button next to Audio Tracks, then click Generate Audio Description.

   

3. Select the languages and click Generate. If no languages are selected, the default ones will be applied.

   

4. When processing is complete, the new audio description track will appear in the Languages section (see Where Audio Descriptions Appear). Review and publish as needed.

Where Audio Descriptions Appear

Once generated, audio descriptions appear in the Languages section of the Video Details page. They are shown as Audio Tracks with the variant labeled Descriptive.

Editing Audio Descriptions

1. To edit an audio description, you must edit the corresponding text track with the kind set to descriptions.

   

2. Make your changes in the text editor and save. Regenerate the audio description after saving your edits to ensure the audio track reflects your updated text (use the Generate Audio Description button).

   

API access

The Audio Description feature is available via the Ingest API. All endpoints require OAuth with scope video-cloud/video/read.

Create / Get Audio Description jobs (by video)

Endpoint:

POST | GET https://ingest.api.brightcove.com/v1/accounts/{account_id}/videos/{video_id}/ai/audio-descriptions
Scope: video-cloud/video/read

POST – Create audio description job

Starts audio description generation for a video. Request body:

• languages: required array of strings. At least one language code (e.g. ["en-US", "es-ES"]). Each language generates one track; rate limits count per language.

Response: job_id (string), job_status (e.g. processing).

GET – Get jobs for a video

Returns all audio description jobs for the given account and video. Response: array of job objects. Each job includes:

• account_id, video_id: strings
• job_id: string (workflow execution ID)
• languages: array of strings (e.g. ["en-US"])
• status: processing | finished | failed
• error: string (present when status is failed)
• input: string (JSON of the workflow input used when the job was created)

Status is updated from the workflow; when status is finished, the audio description tracks are available as Audio Tracks with variant Descriptive in the video’s Languages section (see Where Audio Descriptions Appear).

Get list of Audio Description jobs (by account)

GET https://ingest.api.brightcove.com/v1/accounts/{account_id}/ai/audio-descriptions/jobs
Scope: video-cloud/video/read
Response: array of job objects (same shape as the video-level GET)

Supported languages

Audio description can be generated in the following languages:

FAQs

• How long does processing take?
  Generation can take several minutes depending on video length. When ready, the audio description track will appear on the Video Details page under the Languages section as an Audio Track with variant Descriptive.
• How is credit consumption calculated?
  Usage is based on minutes of video processed. Contact your account team for details.