Specify audio time-codes for precise synchronization

May 10, 2023

Synchronize text to speech audio with videos using time-codes, to provide voiceovers for screencasts and existing videos easily. Use the new pause-until stage direction to specify exact timings when blocks of audio narration should start, and Narakeet will automatically calculate the required pause duration from the end of the previous block for you.

Until today, you could create pauses only by specifying the duration, which was great to create a short delay to give your audience time to think about a question, but not convenient to add a voiceover to an existing video. You would need to figure out the approximate duration of the audio that was generated in the previous segments to calculate the pause, which often required several attempts to get it right.

From today, you can just specify that the voiceover should continue at a specified time from the start of the audio clip. To do that, use the pause-until stage direction, and provide a number of seconds from the start of the scene, or a time code. Here is an example:

Open the application and wait for it to load.

(pause-until: 10.04)

Click the View menu.

(pause-until: 00:15.512)

Click the Zoom option.

In this example, the second sentence (“Click the View menu”) will start at 10 seconds 40 milliseconds from the beginning of the audio, and the third sentence (“Click the Zoom option.”) will start at 15 seconds 512 milliseconds from the start of the audio. Narakeet will automatically calculate the required pause duration between the sentences based on the chosen voice and the actual output of the preceding audio blocks.

When to use pause-until

This new stage direction makes it much easier to create dubbing and translation for existing videos, and to provide voiceovers for screencasts and instructional videos. You can use it for all types of projects, including

• Text to speech audio projects, to create a voiceover synchronized with an external set of subtitles
• Powerpoint to video projects, by including a video into a slide, and easily creating a voiceover on top of it
• Markdown to video projects, to provide narration over a longer video clip without having to split it or mark up video segments

The pause-until stage direction applies time codes from the start of the current scene. In case of an audio file, this will mostly be from the start of the audio. For Powerpoint to Video projects, the time code is relative to the start of the narration for the current slide. For Markdown to video projects, the time code is relative to the start of the current scene.

Important limitations

The pause-until stage direction can only be used to move an audio clip forward in time, and cannot be used to move a narration block forward and run in parallel with the previous clip. If the previous block ends after the requested time code, the stage direction will have no effect. (If you add more than 10 seconds of audio in the first block of the previous example, the second block will start immediately after the first block and not at the requested time code).

You cannot create pauses longer than 10 minutes with this stage direction.

For more information, see the pause-until documentation.