Auto Captions

Captions in minutes, in 30+ languages.

Auto Captions listens to your video and writes timed captions. Download an SRT or WebVTT file, translate it into another language, show both languages, or burn the captions into the picture.

Open Auto Captions

$0.006 per minute for a caption file · billed by the second

A podcast host with large boxed English captions burned into the video
Real Noryva output: English captions burned in with the “Large boxed” style (Mixkit stock footage with a synthetic voice-over).

How it works

Three steps, no software to install.

  1. 1

    Upload a video or paste a link.

  2. 2

    Choose the spoken language, a translation and the output.

  3. 3

    Download the SRT or the captioned MP4.

Use cases

Where it helps.

  • A commuter watching his phone on a train

    Social video

    Most feeds play muted. Burned-in captions keep viewers watching.

  • A creator talking to a camera on a tripod

    YouTube and courses

    Upload SRT files for every language you want to reach.

  • A person watching a laptop in a dark room

    Accessibility

    Captions for viewers who are deaf or hard of hearing.

Part of these workflows

Settings

What you can choose.

Spoken language
Detect automatically, or choose from 35 languages and dialects.
Translate to
Keep the original language, or translate into one of 36 languages.
Show both languages
The original line with the translation below it.
Burn captions into the video
Get a video with captions on screen, in one of four styles, instead of a file.
Caption file
SRT for editors and YouTube; WebVTT for web players.

Pricing

Pay for the seconds you process.

No subscription. Add Credits from $10 and use them on any tool or the API. Failed runs are refunded.

Burned-in captions are priced by your clip's resolution.

Caption file$0.006 / min
Translated file$0.058 / min
Burned in, 1080p$0.035 / min
Burned in, 4K$0.065 / min
Translated and burned in, 1080p$0.087 / min

API

The same tool, as one API call.

Call video-captions from your own app or pipeline at the same price. The studio and the API share one balance.

POST /v1/videoscURL
curl https://noryva.ai/api/v1/videos \
  -H "Authorization: Bearer $NORYVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "video-captions",
      "video": "https://example.com/talk.mp4",
      "seconds": 60,
      "language": "en",
      "translate_to": "es",
      "format": "srt"
    }'

# Poll GET /v1/videos/{id}, then download
# GET /v1/videos/{id}/content

Questions

Good to know.

How accurate is it?

Clear speech transcribes very accurately. People's names and brand names can be misheard; edit the SRT if you need them exact.

Can I upload just audio?

Through the API, yes: MP3, M4A, WAV and FLAC work for caption files. The studio takes video files (MP4, MOV, WebM or MKV).

How is it priced?

By the length of your clip. A caption file is the cheapest output; translation and burning in cost more.

How long can a clip be?

In the studio, up to 10 minutes and 2 GB per run. The whole clip is processed, so trim longer videos first.

Try Auto Captions on a clip you already have.