Skip to main content

Create Voiceovers from SRT Subtitles

Use SRT / Subtitle File mode when you have subtitles and want a translated subtitle file, a voiceover, or both.

Audio Studio understands that SRT files contain extra subtitle information such as cue numbers and timestamps. It keeps that timing information for subtitle files, but it does not read those numbers out loud. Nobody wants a narrator saying, “zero zero colon zero zero colon four comma five hundred arrow zero zero colon zero zero colon six.” That is not a voiceover. That is a microwave having a very organized day.

What SRT Mode Does​

When you upload or paste an SRT file, Audio Studio:

  1. Reads the subtitle cues.
  2. Separates cue numbers and timestamps from the spoken text.
  3. Translates only the subtitle text.
  4. Keeps the original cue numbers and timestamps for translated subtitle output.
  5. Creates clean narration text for audio.
  6. Generates audio only from the cleaned subtitle text.

This means the voiceover should speak the actual content, not the subtitle metadata.

Output Options​

SRT mode gives you three choices:

Output OptionWhat You Get
Voiceover AudioA spoken audio file created from the cleaned subtitle text
Translated SRTA translated subtitle file with original timing preserved
BothA voiceover audio file and a translated SRT file

Choose Both when you want audio for a video and translated captions to go with it.

Upload an SRT File​

  1. Open Audio Studio.
  2. Select SRT / Subtitle File.
  3. Choose Upload SRT file.
  4. Select a .srt file from your computer.
  5. Review the extracted subtitle text preview.
  6. Choose a Target language.
  7. Choose a Voice.
  8. Choose a Style.
  9. Choose Voiceover Audio, Translated SRT, or Both.
  10. Select Generate Audio or Generate SRT.

Paste SRT Text​

You can also paste subtitle content directly into the SRT text area.

Example SRT format:

1
00:00:01,000 --> 00:00:04,000
Welcome to our product tour.

2
00:00:04,500 --> 00:00:08,000
Today we will show you how to create a website faster.

Audio Studio will use:

Welcome to our product tour.

Today we will show you how to create a website faster.

It will not speak 1, 2, or the timestamp lines. The timestamp lines are useful for subtitles, but terrible party guests.

Target Language​

Choose the language you want the subtitle text translated into.

For example:

  • English
  • Spanish
  • French
  • German
  • Italian
  • Portuguese
  • Japanese
  • Korean

If you only want the same-language voiceover, choose the same language as the original subtitle text.

Preview Areas​

In SRT mode, the preview panel shows:

  • Extracted Subtitle Text: the clean text found in your SRT file
  • Translated Text: the translated narration text after generation
  • Audio Player: the generated voiceover, when audio is selected
  • Download SRT: the translated subtitle file, when SRT output is selected

Use the extracted text preview as a quick sanity check. If it looks strange there, your SRT file may need cleaning before generation.

Best Practices for SRT Voiceovers​

  • Use clean subtitle files with normal cue numbers and timestamps.
  • Keep each subtitle cue readable.
  • Avoid mixing too many languages in one file.
  • Review the extracted text before generation.
  • Choose Both when creating video-ready voiceover content.
  • Expect long videos to take longer because Audio Studio creates audio in smaller clean segments and joins them.

For voice choices, see Choose Voices, Languages, and Styles, CloudMySite AI Audio Voice Library, and Supported Audio Languages.

For failed uploads or odd output, see Fix Common Audio Studio Issues.