Search and Discovery (Transcription & Precision Filtering)

Transcription

Whenever you upload a video or audio file containing dialogue, Shade automatically generates a full transcription. Transcriptions are time-coded, searchable, and exportable, making it easy to navigate long recordings and find specific moments without scrubbing through footage manually.

How It Works

After a video or audio file is uploaded, Shade detects whether it contains dialogue and, if so, queues a transcription job. The transcript is broken into segments tied to specific timestamps, and different voices are automatically identified and labeled as Speaker A, Speaker B, Speaker C, and so on.

Because transcription runs as a background job after upload, it may take a few minutes before the transcript is available on a newly uploaded file.

Accessing the Transcript

Open any asset with dialogue and click the Transcription tab in the right panel. The full transcript is displayed as a list of labeled, time-coded segments. Clicking any segment jumps the video or audio playback directly to that point, making it easy to navigate by what was said rather than by timeline position.

Searching Within a Transcript

A search bar at the top of the Transcription panel lets you search for specific words or phrases within that file's transcript. Matching segments are highlighted, so you can quickly scan through a long recording for the moments most relevant to you.

You can also download the transcript using the export icon next to the search bar.

Exporting a Transcript

Transcripts can be exported in several formats to fit different workflows:

• TXT — Plain text, useful for reading, copying, or archiving dialogue.

• SRT — Subtitle format, compatible with most video players and editing tools.

• VTT — Web-native subtitle format, commonly used for web video captions.

• ScriptSync — For use with professional editorial workflows that support ScriptSync-formatted transcripts.

Searching Transcriptions Globally

Transcription content is also indexed in Shade's global AI search. To search across all transcribed files in your drive for a specific word or phrase, wrap your query in quotes.

For example, searching "basketball" will return every video and audio file where the word "basketball" is spoken.

Things to Keep in Mind

• Transcription is only generated for files where dialogue is detected. Music, ambient audio, or silent video will not produce a transcript.

• Transcription runs after upload and may take a few minutes to appear. If the Transcription tab is empty on a newly uploaded file, check back shortly.

• Speaker labels (Speaker A, B, C, etc.) are assigned automatically based on voice detection. They are not linked to named individuals from the People feature.

Precision Filtering

Shade allows you to filter files by various intrinsic, inherited, or custom metadata attributes, including but not limited to:

• Names

• Creation dates

• Extensions

• Tags

• Status labels

• EXIF data

• IPTC data

These filters can be accessed from the top of any asset page as shown below. Filters can be combined to find the the assets that match all the attributes you have selected.