How to Create Subtitles From a Video (Step-by-Step)

To create subtitles from a video, extract the spoken audio, transcribe it into timestamped text, then export an SRT or VTT file you can attach to the video. With PlainScribe you upload the file (up to 200MB), get an AI transcript at up to 99% accuracy, and download an SRT/VTT in minutes for $0.067/min ($4 per audio hour). No subscription, no editing required.

TL;DR

• Three steps: transcribe the audio, review the timed text, then export SRT or VTT. PlainScribe collapses this into a single upload-and-download flow.
• Cost: $0.067 per minute, which is $4 per audio hour. A 10-minute clip costs about $0.67. Start with 30 free minutes, no credit card.
• Formats out: SRT, VTT, TXT, and CSV. SRT and VTT are the two you attach to a video.
• 47 languages auto-detected for transcription, plus translation if you want subtitles in another language.
• Private: uploads and transcripts auto-delete after 7 days. Sensitive footage can run fully offline on the desktop app.

Why Make Subtitles From Video at All

Subtitles widen your audience three ways at once: viewers who are deaf or hard of hearing can follow along, non-native speakers can read what they cannot catch by ear, and the roughly 80% of social feeds watched on mute stay watchable. They also feed search engines real text to index, so captioned videos surface for more queries.

Step 1: Transcribe the Audio

Subtitles are just timed text, so the first job is turning speech into a transcript. Manual transcription runs roughly 4-6 hours per audio hour, so automate it.

1. Open PlainScribe and sign up. The first 30 minutes are free with no card.
2. Upload your video. The web app accepts files up to 200MB in MP4, MOV, WebM, MKV and other common formats.
3. Let it process. Language is auto-detected across 47 languages; you get an email when the transcript is ready.

The AI does the timing and the words at once, so you skip the slowest part of subtitling.

Step 2: Review and Tidy the Text

AI transcription reaches up to 99% accuracy on clean audio, but always scan the result before exporting:

• Fix proper nouns, brand names, and jargon the model could not know.
• Keep each subtitle to one or two lines of around 32-42 characters so it reads at a glance.
• Split long sentences at natural pauses so captions do not flash by faster than they can be read.

Step 3: Export SRT or VTT

When the text is clean, download the subtitle file:

• SRT is the universal choice. It works in VLC, Premiere, Final Cut, YouTube, and almost every player.
• VTT is the web-native HTML5 format, required by some streaming players and supporting light styling.

PlainScribe exports both, plus plain TXT and CSV. Not sure which to pick? See SRT vs VTT.

Step 4: Attach the Subtitles

• YouTube: in Studio, open the video, go to Subtitles, and upload the SRT.
• Vimeo: Settings → Advanced → captions; see the Vimeo closed-captions walkthrough.
• An editor (Premiere/Final Cut): import the SRT as a caption track, or burn it in as open captions.

What It Costs

| Clip length | PlainScribe ($0.067/min) | Rev AI ($0.25/min) | Sonix PAYG ($0.167/min) | |---|---|---|---| | 10 min | $0.67 | $2.50 | $1.67 | | 30 min | $2.01 | $7.50 | $5.01 | | 60 min | $4.02 | $15.00 | $10.02 |

Verdict: for one-off or variable subtitling, pure pay-as-you-go beats both per-minute rivals and locked monthly plans. See the full pricing page and the 2026 cost comparison.

FAQs

How do I get subtitles from a video automatically? Upload the video to an AI transcription tool like PlainScribe, which detects the language, transcribes the audio at up to 99% accuracy, and lets you export a timed SRT or VTT file. The whole flow is upload, review, download.

What is the difference between subtitles and captions? Subtitles assume the viewer can hear and usually carry only dialogue, often translated. Captions (closed captions) target deaf and hard-of-hearing viewers and include speaker labels and sound cues. Both ship as SRT or VTT.

Can I make subtitles in another language? Yes. PlainScribe translates across 47 languages, so you can transcribe in the original language and export subtitles in a different one. See subtitle translation.

How much does it cost to subtitle a video? PlainScribe charges $0.067 per minute, or $4 per audio hour, with a $10 minimum that buys about 150 minutes of credit. A 10-minute video costs roughly $0.67.

Is it private? Yes. Uploaded files and transcripts auto-delete after 7 days, and the offline desktop app keeps sensitive footage fully on your machine.

Ready to caption your first video? Start free with 30 minutes, no credit card required.