Docs•Core Features

Subtitle Creation

Generate subtitle files and transcript-ready timing data from your source media.

What you get
Subtitle file (SRT, VTT, ASS) • Video with soft or burned-in subtitles • History entry
What it costs

300 credits per minute of source media

  • Rounded up to the next whole minute: a 90-second video is billed 2 minutes.

What it looks like

Subtitle Creation in SonicVox

Overview

Subtitle Creation packages transcription and timed text workflows into a feature focused on delivery-ready captions. It is useful for creators who need portable subtitles without opening the full transcription editor first, while still exposing transcript exports, structured insights, and async callbacks for production integrations.

Quickstart

1

Add your media

Upload the audio or video source you want to caption.

2

Generate timing data

Run the caption workflow so segments and timings are produced automatically.

3

Review subtitles

Check wording, segmentation, and timing before export.

4

Export delivery files

Download the caption format required by your publishing workflow.

Best practices

  • Review punctuation before exporting subtitles to video platforms.
  • Use Subtitle Creation for fast deliverables and Speech to Text when you need deeper transcript editing.

FAQs

How accurate is the auto-captioning?

Accuracy depends on your audio: clear speech transcribes best, and background noise, music or overlapping speakers lower it. Timing comes from word-level timestamps, and you can correct any caption in the editor before export.

Can I edit the subtitles after generation?

Yes. Side-by-side video and subtitle editor with hotkeys, search-replace, bulk timing nudges, speaker re-labeling, and version history.

Which formats can I export?

SRT, VTT, ASS, TXT, JSON — plus burned-in subtitles in the rendered MP4.

Does it support multiple languages at once?

Not in one pass. Subtitle Creation captions the language spoken in your video. For other languages, run the video through Dubbing, which translates the transcript and can burn the translated subtitles into the video or give you the subtitle file.

Does it label speakers?

Yes. Automatic speaker diarization labels each caption with the right speaker, with manual re-labeling in the editor.

Can I deliver captions to streaming platforms?

Yes, to any platform that accepts SRT or WebVTT, as most video platforms and web players do. Export either from the same project, with the same timing in each.

Can I batch a whole video library?

Not yet. The uploader takes one video per job, so a backlog goes through one video at a time. There is no bulk or CSV upload.

Is there an API?

Not yet. There is no public subtitle API: subtitles are created, edited and exported in the app.

Was this page helpful?