Using the Transcript Tab

Powered by Avid AI, the Transcript tab shows the speech to text (Transcribe) output of your asset's audio. Transcribe workflows, at the highest level, include the following: A request is made for an analysis service to process some audio, convert spoken words into text and then deliver the text along with timing data that map the words to offsets into the audio; the transcript text is added to segments that are automatically divided by each individual speaker. Additionally, the Transcript tab provides the option to create a translation of each transcript.

Transcribe operations on assets and transcript translation can be initiated either by automation (rules defined in the Rules Editor app, scheduled jobs defined in the Schedule Editor app) or by manual interaction in the Transcript tab.

n The Transcript tab is only shown when the feature pack STT is installed and can only be used when the required licenses (Avid Ada Transcribe ) is activated. Transcript creation and editing features in the Transcript tab are controlled by an entitlement (Avid AI Transcribe RW Access) that is assigned on group level. To additionally use translation features in the Transcript tab, the entitlement Avid AI Translate RW Access is required.

Users of a group that has the following entitlements assigned can do the following in the Transcript tab:

Entitlement	Enabled Features
Avid AI Transcribe RW Access	Initiate the transcript creation for the entire asset or selected audio tracks Display and inspect transcripts Navigate in the transcript with synchronized playhead in the Media Viewer Rename transcripts Rename speakers Add new speakers Delete speakers Assign words, entire segments or text across segments to another speaker Edit transcript text Copy transcript text Export transcripts
Avid AI Translate RW Access	Initiate the translation of transcripts Display and inspect translations Navigate in the translation with synchronized playhead in the Media Viewer Edit translation text Copy translation text Export transcripts
<no entitlement assigned>	Display and inspect transcripts and translations Navigate in transcripts and translations with synchronized playhead in the Media Viewer Copy transcript and translation text Export transcripts

Limitations

In this release, only Production Management assets are supported for transcripts, as follows:

Avid Production Management and MediaCentral Production Management master clips and subclips are supported; other asset types are not supported.
Growing/Edit while capture (EWC) files are supported.
Remote assets are not supported.

The following limitations apply to transcript creation:

Avid Transcribe uses an Artificial Intelligence (AI) / Machine Learning (ML) model to produce transcripts and speaker labels from assets that include non-musical, spoken word. In terms of a newsroom workflow, this might be identified as a VO or "talking head". As with all AI/ML models, results might be incorrect as the model is predicting the output from the provided input. Therefore, the Transcript tab provides options to correct any of these errors.
Avid Transcribe results are directly impacted by the quality of audio signal being transcribed. For accurate transcriptions, it is important to ensure the audio signal has a reasonable signal-to-noise ratio (SNR).
Creating transcripts is covered with a quota license that tracks and limits the number of hours of transcribed audio.
Only a completely created transcript can be edited. The transcript portions already shown for EWC clips or very long clips are read-only until the transcribe operation is completely finished.
If a re-transcribe job for a transcript is triggered, all edits made to the transcript will be overwritten.

The following limitations apply to translation creation:

Only a completely created translation can be edited.
Editing options for translation are restricted to modifying the translation text.
If a re-translate job for a transcript is triggered, all edits made to the translation will be overwritten.

Basic Interaction Patterns

Note the following basic interaction patterns:

When the STT feature pack is installed but the required license is not activated, the Transcript tab shows the “Your system is not licensed for this feature. Please contact your system administrator for assistance” message.
When no asset is loaded in the Asset Editor, the Transcript tab shows an “Asset is not loaded” message.
The Transcript tab shows an “Asset is not supported” message:
- If there are no audio tracks for the asset.
- If the system type of the asset is not Production Management.
- If you open an asset that does not support the transcript feature (for example, a sequence or group clip).
If for none of the tracks a transcript has been created yet, the Transcript tab shows a “There is no transcript yet” message and a Transcribe Asset button.

The Translation controls are disabled.
If there is transcription at least available on one track, the Transcript tab selects the first audio track with transcription.

The Translation controls are enabled.

Right-to-Left Languages

The Transcript tab supports right-to-left languages:

You can display and edit text in right-to-left languages (for example, Arabic or Hebrew). MediaCentral Cloud UX recognizes right-to-left characters (RTL). If the entire text or more than 50 percent of the text in a transcript segment consists of right-to-left characters, the text direction in the transcript segment changes to right-to-left.
The same applies when you merge two transcript segments or move a portion of a segment text into another segment by using the Change Speaker feature: when more than 50 percent of the text in the merged transcript segment consists of right-to-left characters, the text direction in the transcript segment changes to right-to-left as soon as you click outside the field.

Searching for Transcript Data

After you have transcribed an asset, you can use either the Any or the Markers & Segments (simple or advanced) pill types in the Search app to search for the Speaker or Transcript text. Searches return master clips and subclips that include the matching transcribe text.

If you are using the Timeline view of the Search app's Inline Hits window, the transcript is displayed as one segment per sentence, and not as a 1:1 representation of the Transcript segments. Each segment includes information about the transcripted audio, speaker, language, and track.

For more information on Search, see Using the Search App.

Transcript Tab Layout

The following illustration and table describe the layout of the Transcript tab.

	Item	Description
1	Transcript/Translation tabs	Let you switch between Transcript and Translation mode in the Transcript tab. By default, the Transcript mode is enabled.
2	Reload button	Reloads transcripts and translations.
3	Transcript selection	Lets you select the completed, failed, or currently being created transcripts of the asset. If no name was specified, each transcript is named according to the audio track for which is was created. If several audio tracks have been selected for transcript creation at the same time, the tracks are mixed down into one track and a transcript for the mixed down audio track is created; the name of the transcript shows the included audio track names, for example "A1-A2-A3". You can use the transcript selection to rename a transcript at any time. When you hover the cursor over a transcript name the Edit button is shown. For a renamed transcript, the track name is additionally shown in brackets. If the name cannot be shown completely in the transcript selection, you can see the full name and track in a tool-tip. For more information, see Renaming Transcripts. When you select a transcript from the list, it is shown in the Transcript area. If the selected transcript is currently being created, the Transcript area shows a "Transcription in progress" message. If the creation of the selected transcript has failed, the Transcript area shows a "Transcription failed" message. If the transcript can only be partially displayed – transcript creation failed while portions of the transcript have already been shown on the Transcript tab – a warning icon is shown between the transcript selector and Find filter control. The tool-tip reads "Transcript error: partial transcript only". When no transcript has been created for the asset yet, the list shows the "There are no items in this list" entry.
	Translation selection (not shown in the illustration)	(only shown in Translation mode) Lets you select one of the available translations of the transcript. The language code is shown in the toolbar, the language label is shown in the list. When you select a language from the list, the corresponding translation is shown in the Translation area. If the selected translation is currently being created, the Translation area shows a "Translation in progress" message. If the creation of the selected translation has failed, the Translation area shows a "Translation failed" message. When no translation has been created for the transcript yet, only the dimmed button without a language code is shown. For more information, see Using Translations.
4	Find field	Lets you search words in the transcript or translation text. Transcript mode: The word count to the right side of the Find field shows the number of matching words in the form <selected word>/<total number of found words>. Using the navigation controls to the right side of the word count you can skip between found words. If Sync Playhead is enabled, skipping between found words also moves the playhead in the Media Viewer timeline. For more information, see Searching in the Transcript. Translation mode: The segment count to the right side of the Find field shows the number of matching segments in the form <selected segment>/<total number of found segments>. Using the navigation controls to the right side of the segments count you can skip between found segments. If Sync Playhead is enabled, skipping between found segments also moves the playhead in the Media Viewer timeline. For more information, see Searching in the Translation.
5	Sync Playhead button	Toggles the synchronization of the position indicator (playhead) and transcript or translation on and off : On (default): During playback in the Asset Editor's Media Viewer or when you position the playhead in the timeline, the corresponding word (in the transcript) or segment (in the translation) is highlighted in green in the Transcript tab. Vice versa, when you select a word/segment in the Transcript tab, the playhead in the Asset Editor's Media Viewer is positioned to the corresponding timecode. Off: During playback in the Asset Editor's Media Viewer, corresponding words (in the transcript) or segments (in the translation) are not highlighted in the Transcript tab. Selecting a word/segment in the Transcript tab does not move the playhead in the Asset Editor's Media Viewer. When you enable Edit Mode to edit the transcript or translation text, Sync Playhead is toggled off. For more information, see Navigating within the Transcript and Navigating within the Translation.
6	Edit Mode button	Toggles the edit mode for the Transcript/Translation area on and off : When toggled on, playback is stopped and synchronization with the player is disabled. In Transcript mode, all edit features – rename speakers, add speakers, assign segment to another speaker, edit transcript text – are now enabled. In Translation mode, the edit translation text feature is enabled. When toggled off, you can select a row but do not enter edit mode. The status of the Sync Playhead toggle is regarded. For more information, see Editing a Transcript and Editing the Translation Text.
7	Export button	Lets you export the transcript or translation to your local workstation. Supported formats are .txt, .csv and *.srt. If the Transcript tab is in Transcript mode, the currently selected transcript is exported. If the Transcript tab is in Translation mode, the currently selected translation of the transcript is exported. For more information, see Exporting the Transcript and Exporting the Translation.
8	Create New Transcript or Translation button	Gives you access to the following "create" features: Create New Transcript: Opens the Create Transcript dialog box, that lets you start the transcript creation for one or more audio tracks of the asset. For more information, see Creating Transcript for Selected Audio Tracks. Create New Translation: Opens the Translate dialog box, that lets you start the translation creation for the selected transcript. For more information, seeCreating the Initial Translation for a Transcript.
	More Options button (not shown in the illustration)	If you reduce the width of the Asset Editor to a point at which all buttons cannot be displayed at the same time, the Transcript tab responsively scales by hiding buttons from right to left. Appearing to the far right of the Transcript header the More Options button lets you access the hidden buttons in a menu. By default, the Export Transcript and Create New Transcript or Translation buttons are shown in the More Options menu. All buttons to the right of the Transcript selector – but not the Word filter field – can appear in the More Options menu. If an item in the More Options menu has at least one additional sub-item, an expand arrow is displayed, as shown in the following illustration for Export Transcript.
9	Transcript/Translation area	Shows the contents of the selected transcript or translation in a table. Each row consists of the following: Speaker: Name of the speaker generated by the transcript; can be modified. See Renaming Speakers and Creating New Speakers. Transcript: Transcript or Translation text of the speaker. The start-timecode of the segment is shown. You can edit the transcript or translation text. See Editing the Transcript Text and Editing the Translation Text. Only in Transcript mode, you can assign parts of the segment or the entire segment to another speaker. See Assigning Transcript Segment to Another Speaker.