Skip to main content

​
Overview

Text-to-Speech (TTS) generates narration from the Body and Choices in a Show Panel action. The generated audio is attached to that panel and plays when the action runs. After editing the spoken text, generate the narration again and preview it before saving.

​
Where to Find It

TTS is available in two places, both tied to the Show Panel action: Both paths produce the same result — an audio file attached to the panel.

​
Generating Narration

1

Prepare the panel text

Select the step’s existing Show Panel action, or add one to On Entry. Enter the Body text and any Choices you want narrated. The Title is displayed but is not spoken.
2

Click Generate Audio

Click the speaker icon beside Body. It shows a loading indicator while generating and a check mark when generation succeeds. The tooltip also reports the generation status.
3

Preview

Play the audio preview in the panel’s Audio section. Check the pronunciation and make sure the narration matches the body and choices.
4

Regenerate after edits

If you change the Body text or Choices, click Generate Audio again and preview the new recording.
5

Save the training

Click Save, or press Ctrl+S on Windows or Cmd+S on macOS, to save the panel’s audio assignment. Verify playback in the trainee app.
Show Panel action with body text, choices, and generated audio playback controls

Show Panel narration text and generated audio preview

​
What Gets Spoken

The narration includes:
  • The Body text of the panel
  • The text of each Choice (if the panel has multiple-choice options)
The panel Title is not included in the narration. Keep titles short and put the spoken content in the body.
Enter body text before generating narration. If the generation control is unavailable, check that the body contains text and that generation is not already in progress. A title alone does not provide spoken content.

​
Variables in Narration

Show Panel can display current variable values using {{variableName}}, but narration generation uses the text as written. It does not replace these placeholders with the trainee’s runtime values. For example, a body containing Equipment: {{equipmentId}} sends that placeholder to the speech generator. The resulting audio does not change when equipmentId changes, and regenerating with the same placeholder does not insert its current value. For panels with changing values, use general narration or assign a separate audio recording that remains appropriate as the displayed text changes.

​
Voice and Language

  • Voice Type is selected in the training’s Settings in the Dashboard. Show Panel uses that training-level setting when generating narration.
  • Show Panel has no separate voice or language picker for individual panels.
To change the voice, save your authoring work, update Voice Type in the Dashboard’s training Settings, and reopen the training to load the updated setting. Regenerate the affected panels’ narration, preview it, and save again. Changing the voice setting does not change an existing audio recording.

​
How the Audio Is Stored

When Generate Audio succeeds, the panel action is updated with an audio source that points to the generated file on the server. The audio plays automatically when the Show Panel action runs at runtime. Generated narration appears as Generated Audio in the panel’s Audio field. It is attached directly to the panel rather than selected as a library asset. Duplicating a step can retain its existing audio reference. After editing the duplicate’s body or choices, regenerate its narration so the recording matches the new text.
For audio you want to select and reuse across several steps, upload it to the asset library and use Play Audio or the panel’s Audio field.

​
Example: Narrated Instruction

Set up a Show Panel action with:
  • Title: Step 3
  • Body: Pick up the torque wrench from the workbench and set it to 8 Newton-metres.
Click Generate Audio, preview the recording, and save. When the action runs, the learner sees the panel and hears the body text. No separate Play Audio action is needed.

​
Example: Narrated Question

Set the Title to “Quick Check” and the Body to “Which tool is the correct one for this fastener?” Add these choices:
  • Screwdriver
  • Wrench
  • Hex key
Connect each choice to the appropriate transition, then generate and preview the audio. The narration includes the question and all three choice labels. See Choice Events for routing instructions.

​
Replacing or Removing TTS Audio

  • Regenerate — Edit Body or Choices, then click Generate Audio again. The old audio is replaced.
  • Switch to library audio — Clear Generated Audio using the remove control on the Audio field, then select or upload the replacement audio.
  • Remove — Use the remove control on the Audio field to clear the panel’s audio assignment. This does not delete the generated file or remove audio assigned to another panel.
Save after changing the audio assignment using Ctrl+S or Cmd+S.

​
Best Practices

1

Write for listening, not just reading

Use short sentences. Avoid tables, code blocks, and long bullet lists in Body — they sound awkward when read aloud.
2

Keep titles off the narration

Titles are not spoken. If a piece of information is important, put it in Body so the learner hears it.
3

Use a consistent voice across a training

Choose the training’s Voice Type in the Dashboard. If you change it, regenerate the affected narration so the panels use the intended voice.
4

Regenerate after changing spoken text

The audio is a snapshot of the body and choices at the time you clicked Generate Audio. Regenerate after changing either. Editing only the title does not change the spoken content.
5

Preview before publishing

Play the generated audio inside Creator to catch mispronunciations or awkward phrasing. Adjust the text and regenerate if needed.

​
Limitations

  • Only in Show Panel — TTS is part of the Show Panel action. To narrate other actions, use Play Audio with a pre-uploaded audio asset.
  • No per-panel voice override — Generation uses the training’s selected Voice Type.
  • Title not spoken — Only Body and Choices are included in the audio.
  • Static narration — Regenerate after editing the spoken text. The recording does not update dynamically with runtime variable values.
  • Show Panel — Configure panel content, audio, and navigation
  • Events — Connect panel choices and Next to transitions
  • Play Audio — Play a library audio asset
  • Variables — Create variables for training logic and displayed content