Stories Feature: A Step-by-Step Guide 📖

After uploading your story, you’ll be prompted to select the source language. This is the language in which your story is written.

By selecting the correct language, the AI will be able to accurately narrate your story.

Once you’ve uploaded your story, selected the language, and chosen the narrator’s voice (and description, if desired), you’re ready to move forward.

To begin the narration process, click on the "Begin Creating a Story" button.

Once you click on "Begin Creating a Story," you will be navigated to the Stories page, where paragraphs are split into lines, each containing a single sentence.

When you first enter the Stories page, all lines will be in a muted state.

Please review the script for sentence flow, ensure each line is properly split, and confirm that punctuation is included on the same line to avoid audio artifacts.

Once you're satisfied with the script, click on the "Re-generate all stale/muted dialogues audio" button in the floating toolbar.

This will generate audio for all lines.

You’ll receive a notification in the bottom-right corner once the audio has been generated.

After that, the play button will be enabled. You can then click Play to listen to the audio and verify it.

Use the seek bar to move forward or backward, and click the play button to play or pause the story.

If you edit any line, it will become stale, as indicated in the screenshot.

To regenerate audio for the edited line, click "Re-generate Selected Dialogue Audio" and listen to the updated output.

You can also modify the dialogue structure using the following options:

Split – divides a dialogue into two separate lines.

Add Before / Add After – inserts new dialogue lines before or after the selected one.

Merge Before / Merge After – combines the selected line with the previous or next line.
​

Delete – removes the selected line entirely.​
​

Additionally, you can adjust the speed of individual dialogue lines to match the desired tone or pacing. If the speed is set to anything other than 1x, it will be displayed on the line.
​

​

​

You can also add gaps between lines—useful for inserting chapter names, headings, titles, or subheadings. These elements can be represented as separate lines with specific timing.

By default, there is a 0.4-second gap between lines.

Select More: You can select one or more dialogues to regenerate or change the speaker all at once
​

By default, no voiceover will be generated after uploading.

Make sure the speaker details are accurate for your audio file to ensure high-quality audio.

You can use the stock voices available in our portal, or upload your own custom voice references. Refer Voice Library 👉 Voice Library Article

If you change the voice reference in the speaker settings, you will need to regenerate the voiceover.

You can use the forward and backward options on the seek bar to go to the next or previous line.

You can also click anywhere on the seek bar to jump to any line randomly.

'51/112' means that '51' represents the current cursor position(Line Number), and '112' is the total number of lines.

After editing click on “Generate Audio Tracks”

A dialog box will pop up. Click on 'Export'.

Once processed, click on ‘Download.’

You can download the source audio in the formats shown in the screenshot.

You can also download Dialogue‑Only Audio if your story has multiple speakers.

Please refer to this article : How-to-download-mastered-output

You can also view the most recent edit time, as shown in the screenshot below.

Ensure that your story file is in TXT or DOCX format and within the 100000000 character limit for optimal performance. 📜

If you’re uploading a custom voice, make sure it’s in the right format and meets the system's requirements. 🎙️

OCR = Optical Character Recognition. It reads text from images.
​Stale lines = edited lines needing new audio.
​Gaps = timed pauses between dialogues. You can adjust them.