# Subtitle Generator (SRT, VTT, ASS)

Subtitle generator for your own audio or video file: readable SRT, VTT and ASS, two lines of 42 characters at most per cue.

Send a direct link to an audio or video file, or the file itself as base64 when it fits in 2 MB. You get cues of at most two 42-character lines, at no more than 20 characters a second, as SRT, VTT and ASS, usually within minutes and always within 24 hours. Pay per second of audio; if we miss the deadline it's free.

- Cues people can read: at most two 42-character lines, at no more than 20 characters a second, ending where a sentence ends when the sentences allow it.
- SRT, VTT and ASS from one job.
- Pay per second of audio, and free if we miss the deadline.

## Calls

### `POST https://readymadeapi.com/v1/subtitles/subtitle`

Queue subtitles. max_minutes is the most the audio may last; you are charged only for the seconds it actually runs.

- Price: $0.0002 per second, up to 10800 per call
- MCP tool: `subtitle_studio_subtitle`
- Queued: answers 202 with a job; poll `GET /v1/jobs/{id}`, fetch `GET /v1/jobs/{id}/result`. Charged up front, and what does not run is refunded.

Request:

```json
{
  "audio_url": "https://readymadeapi.com/samples/voice-note.mp3",
  "max_minutes": 30
}
```

The finished job:

```json
{
  "job_id": "01a1f553-82bc-7676-a558-74ff5a617acf",
  "status": "succeeded",
  "late": false,
  "deadline": "2026-11-20T19:40:53.305358Z",
  "completed_at": "2026-11-19T19:40:53.978168Z",
  "error": null,
  "result": {
    "language": "en",
    "duration_s": 6.525,
    "cues": [
      {
        "start_ms": 0,
        "end_ms": 1817,
        "lines": ["Hi, this is a short voice note."]
      },
      {
        "start_ms": 1900,
        "end_ms": 5980,
        "lines": ["Please move our meeting to Thursday at 10", "and bring the signed contract."]
      }
    ],
    "srt": "1\n00:00:00,000 --> 00:00:01,817\nHi, this is a short voice note.\n\n2\n00:00:01,900 --> 00:00:05,980\nPlease move our meeting to Thursday at 10\nand bring the signed contract.\n\n",
    "vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:01.817\nHi, this is a short voice note.\n\n00:00:01.900 --> 00:00:05.980\nPlease move our meeting to Thursday at 10\nand bring the signed contract.\n\n",
    "ass": "[Script Info]\nScriptType: v4.00+\nPlayResX: 1920\nPlayResY: 1080\nWrapStyle: 2\n\n[V4+ Styles]\nFormat: Name, Fontname, Fontsize, PrimaryColour, OutlineColour, BackColour, Bold, Italic, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV\nStyle: Default,Arial,64,&H00FFFFFF,&H00000000,&H80000000,0,0,1,3,0,2,60,60,60\n\n[Events]\nFormat: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\nDialogue: 0,0:00:00.00,0:00:01.81,Default,,0,0,0,,Hi, this is a short voice note.\nDialogue: 0,0:00:01.90,0:00:05.98,Default,,0,0,0,,Please move our meeting to Thursday at 10\\Nand bring the signed contract.\n"
  }
}
```

## Limits

- Up to 3 hours of audio per call; by link, files up to 350 MB.

## Questions

**What is max_minutes for?**

It is your ceiling. Audio longer than that is refused and not charged; shorter audio is charged for its real length.

**Does it fetch YouTube captions?**

No. It makes subtitles from the audio of a file you link to.

**Which languages?**

The 99 languages of the Whisper model behind it; subtitles come out in the language spoken. We test in English.

**How long does it take?**

It is a queued job, up to three hours of audio per call. Most finish within minutes; the promise is 24 hours.

## Using it

- Send `Authorization: Bearer <key>` and a JSON body. Keys and credit: https://readymadeapi.com/account
- Every answer carries `X-Request-Id`, `X-Units` and `X-Charged-Usd`.
- An error is a JSON problem with a `title` to act on and a `detail` in plain words; nothing is charged for it.
- Full schema: https://readymadeapi.com/openapi.json
