# Subtitles API

> Incorpora legendas estilizadas num vídeo, a partir de transcrição automática ou do seu próprio SRT, com tradução opcional

Adiciona legendas renderizadas a um vídeo (`video_url`) usando um `preset` de estilo obrigatório, com 30 predefinições disponíveis. Transcreve automaticamente ou ignora essa etapa se fornecer `srt_file_url` ou `srt_content`. `language` define o idioma de origem para maior precisão, e `translation_language` traduz as legendas. Uma lista `vocabulary` com até 100 termos e substituições em `customization` permitem aperfeiçoar o resultado.

- Model id: `veed/subtitles`
- Made by: VEED
- Category: Video to Video
- Output: video
- Price per minute of your input video: from $0.10 / minute of input video (cheapest run $0.10 (100 API credits))
- Run: `POST https://api.doitong.com/v1/run/veed/subtitles`
- Quote: `POST https://api.doitong.com/v1/quote/veed/subtitles`
- Docs page: https://doitong.com/pt-PT/developers/models/veed/subtitles

## Pricing

Price: **from $0.10 / minute of input video** (the lowest tier; the quote prices your exact input). Price per minute of your input video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

Price by tier:

- base rate: $0.10 / minute of input video
- above 1080p: $0.20 / minute of input video

The full example input below costs $0.20 = 200 API credits (1 min input video × $0.20).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/veed/subtitles` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `video_url` | `video` | string (video URL) | yes |  | 1 – 2083 characters | Vídeo de origem para legendagem; carregue o ficheiro ou cole a respetiva URL. |
| `preset` |  | enum (string) | yes |  | `glass`, `whisper`, `glide2`, `fusion`, `glide`, `terminal`, `handwritten`, `backdrop`, `backdrop2`, `simple`, `plain`, `beans`, `corpo`, `boo`, `shadeplay`, `casper`, `capri`, `lowkey`, `vinta`, `diego`, `ali`, `slay`, `kitty`, `hustle`, `karl`, `sprout`, `flex`, `mint`, `rizz`, `vegas` | Seleção de estilo que define tipografia, cor, disposição e animação, com rendering mais rico adaptado ao contexto da entrada. As predefinições básicas utilizam um multiplicador de 1 e fornecem resultados previsíveis através de um estilo fixo e leve: vegas, rizz, mint, flex, sprout, karl, hustle, kitty, slay, ali, diego, vinta, lowkey, capri, casper, shadeplay, boo, corpo, beans, plain, simple. |
| `language` |  | enum (string) \| null | no |  | `af-ZA`, `am-ET`, `ar-AE`, `ar-BH`, `ar-DZ`, `ar-EG`, `ar-IL`, `ar-IQ`, `ar-JO`, `ar-KW`, `ar-LB`, `ar-MA`, `ar-OM`, `ar-PS`, `ar-QA`, `ar-SA`, `ar-TN`, `ast-ES`, `az-AZ`, `ba`, `bas`, `be-BY`, `bg-BG`, `br`, `bs-BA`, `ca-ES`, `ceb-PH`, `ckb-IQ`, `cs-CZ`, `cy-GB`, `da-DK`, `de-DE`, `dyu`, `el-GR`, `en-AU`, `en-GB`, `en-IN`, `en-NZ`, `en-US`, `eo`, `es-AR`, `es-BO`, `es-CL`, `es-CO`, `es-CR`, `es-DO`, `es-EC`, `es-ES`, `es-GT`, `es-HN`, `es-MX`, `es-NI`, `es-PA`, `es-PE`, `es-PR`, `es-PY`, `es-SV`, `es-US`, `es-UY`, `es-VE`, `et-EE`, `eu-ES`, `fa-IR`, `ff`, `fi-FI`, `fil-PH`, `fo`, `fr-CA`, `fr-FR`, `fy`, `ga`, `gd`, `gl-ES`, `ha-NG`, `haw`, `he-IL`, `hr-HR`, `hsb`, `ht`, `hu-HU`, `hy-AM`, `id-ID`, `ig`, `is-IS`, `it-IT`, `ja-JP`, `ja-Latn-JP`, `jv-ID`, `ka-GE`, `kab`, `kam-KE`, `kea-CV`, `kk-KZ`, `ko-KR`, `ku`, `ky-KG`, `la`, `lb-LU`, `lg`, `lij`, `ln-CD`, `lo-LA`, `lt-LT`, `luo-KE`, `lv-LV`, `mg`, `mi-NZ`, `mk-MK`, `mn-MN`, `ms-MY`, `mt-MT`, `nb-NO`, `nl-NL`, `nso-ZA`, `ny-MW`, `oc-FR`, `pl-PL`, `ps-AF`, `pt-BR`, `pt-PT`, `ro-RO`, `roh`, `ru-RU`, `rw-RW`, `sah`, `sk-SK`, `sl-SI`, `sm`, `sn-ZW`, `so-SO`, `sq-AL`, `sr-Latn-RS`, `sr-RS`, `srd`, `ss`, `su-ID`, `sv-SE`, `sw-KE`, `sw-TZ`, `tg-TJ`, `th-TH`, `tk`, `tn`, `tok`, `ton`, `tr-TR`, `ts-ZA`, `tt`, `uk-UA`, `umb-AO`, `ur-IN`, `ur-PK`, `uz-UZ`, `vi-VN`, `vro`, `wo-SN`, `xh-ZA`, `yi`, `yo-NG`, `yue-Hant-HK`, `zh`, `zh-HK`, `zh-TW`, `zu-ZA` | Idioma do áudio de origem, não das legendas geradas. Correspondê-lo ao áudio melhora a precisão da transcrição. |
| `translation_language` |  | enum (string) \| null | no |  | `ab`, `ace`, `ach`, `af-ZA`, `ak`, `alz`, `am-ET`, `ar-AE`, `ar-BH`, `ar-DZ`, `ar-EG`, `ar-IL`, `ar-IQ`, `ar-JO`, `ar-KW`, `ar-LB`, `ar-MA`, `ar-OM`, `ar-PS`, `ar-QA`, `ar-SA`, `ar-TN`, `awa`, `ay`, `az-AZ`, `ban`, `bbc`, `be-BY`, `bem`, `bew`, `bg-BG`, `bho`, `bik`, `bm`, `bs-BA`, `bts`, `btx`, `bua`, `ca-ES`, `ceb-PH`, `cgg`, `chm`, `ckb-IQ`, `cnh`, `co`, `crh`, `crs`, `cs-CZ`, `cv`, `cy-GB`, `da-DK`, `de-DE`, `din`, `doi`, `dov`, `dv`, `dz`, `ee`, `el-GR`, `en-AU`, `en-GB`, `en-IN`, `en-NZ`, `en-US`, `eo`, `es-AR`, `es-BO`, `es-CL`, `es-CO`, `es-CR`, `es-DO`, `es-EC`, `es-ES`, `es-GT`, `es-HN`, `es-MX`, `es-NI`, `es-PA`, `es-PE`, `es-PR`, `es-PY`, `es-SV`, `es-US`, `es-UY`, `es-VE`, `et-EE`, `eu-ES`, `fa-IR`, `ff`, `fi-FI`, `fil-PH`, `fj`, `fr-CA`, `fr-FR`, `fy`, `ga`, `gaa`, `gd`, `gl-ES`, `gn`, `gom`, `ha-NG`, `haw`, `he-IL`, `hil`, `hmn`, `hr-HR`, `hrx`, `ht`, `hu-HU`, `hy-AM`, `id-ID`, `ig`, `ilo`, `is-IS`, `it-IT`, `ja-JP`, `ja-Latn-JP`, `jv-ID`, `ka-GE`, `kk-KZ`, `ko-KR`, `kri`, `ktu`, `ku`, `ky-KG`, `la`, `lb-LU`, `lg`, `li`, `lij`, `lmo`, `ln-CD`, `lo-LA`, `lt-LT`, `ltg`, `luo-KE`, `lus`, `lv-LV`, `mai`, `mak`, `mg`, `mi-NZ`, `min`, `mk-MK`, `mn-MN`, `mni-Mtei`, `ms-Arab`, `ms-MY`, `mt-MT`, `nb-NO`, `new`, `nl-NL`, `nr`, `nso-ZA`, `nus`, `ny-MW`, `oc-FR`, `om`, `pag`, `pam`, `pap`, `pl-PL`, `ps-AF`, `pt-BR`, `pt-PT`, `qu`, `rn`, `ro-RO`, `rom`, `ru-RU`, `rw-RW`, `scn`, `sg`, `shn`, `sk-SK`, `sl-SI`, `sm`, `sn-ZW`, `so-SO`, `sq-AL`, `sr-Latn-RS`, `sr-RS`, `ss`, `st`, `su-ID`, `sv-SE`, `sw-KE`, `sw-TZ`, `szl`, `tet`, `tg-TJ`, `th-TH`, `ti`, `tk`, `tn`, `tr-TR`, `ts-ZA`, `tt`, `ug`, `uk-UA`, `ur-IN`, `ur-PK`, `uz-UZ`, `vi-VN`, `xh-ZA`, `yi`, `yo-NG`, `yua`, `yue-Hant-HK`, `zh`, `zh-HK`, `zh-TW`, `zu-ZA` | Idioma para o qual traduzir as legendas; para obter a tradução mais fiável com `srt_content` ou `srt_file_url`, forneça também o idioma de origem em `language`. Sem um destino, as legendas permanecem no idioma falado original. |
| `srt_file_url` |  | string (file URL) \| null | no |  | 1 – 2083 characters | Forneça legendas em vez de executar a transcrição, carregando um ficheiro .srt ou colando a respetiva URL. |
| `srt_content` |  | string \| null | no |  |  | Texto de legendas bruto no formato SRT, fornecido em vez de srt_file_url. Fornecê-lo ignora a transcrição. |
| `vocabulary` |  | array of object {word, replaces} \| null | no |  | ≤ 100 items | Vocabulário de transcrição opcional, ativo apenas quando não é fornecido srt_content nem srt_file_url. Inclua nomes de marcas e jargão especializado que os fornecedores de transcrição frequentemente escrevem incorretamente, por exemplo "VEED" → "vid". |
| `vocabulary[].word` |  | string | yes |  | 1 – 100 characters | Forneça a grafia correta do termo, de preferência uma marca, nome de produto ou termo especializado do seu domínio. |
| `vocabulary[].replaces` |  | array of string | yes |  | 1 – 20 items | Indique cada erro ortográfico uma vez para que seja substituído por `word`. A correspondência requer uma palavra completa, mas ignora maiúsculas e minúsculas: `['vid']` corresponde a `vid`, `Vid` e `VID`, sem entradas separadas para cada caso. |
| `customization` |  | object {position, shadow, text_customizations} \| null | no |  |  | Personalização opcional da predefinição, mantendo os valores predefinidos sempre que os campos são omitidos. As substituições podem ajustar a posição vertical e a intensidade da sombra, além do tipo de letra, peso e cor hexadecimal separadamente para cada nível de importância das palavras. |
| `customization.position` |  | enum (string) \| null | no |  | `top`, `center`, `bottom` | Posição do ecrã ao longo do eixo vertical para legendas estáticas. |
| `customization.shadow` |  | enum (string) \| null | no |  | `none`, `min`, `mid`, `max` | Melhoria da legibilidade das legendas sobre fundos claros ou visualmente complexos. |
| `customization.text_customizations` |  | object {baseline, highlighted} \| null | no |  |  | Definições do aspeto do texto por nível, abrangendo palavras base e palavras destacadas. |
| `customization.text_customizations.baseline` |  | object {font, weight, color} \| null | no |  |  | Aspeto predefinido do texto para todas as palavras da transcrição, visível antes de qualquer palavra individual receber ênfase. |
| `customization.text_customizations.highlighted` |  | object {font, weight, color} \| null | no |  |  | Estilo para o nível intermédio de palavras, que as predefinições normalmente destacam com maior tamanho ou peso. As palavras entram automaticamente neste nível quando são marcadas como relevantes, incluindo substantivos essenciais, verbos de ação e adjetivos importantes. |

File parameters (`video`, `srt_file_url`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
  "preset": "glass"
}
```

A fuller example:

```json
{
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
  "preset": "glass"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/veed/subtitles?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "preset": "glass"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/veed/subtitles?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "preset": "glass"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "preset": "glass",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/veed/subtitles", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "veed/subtitles",
      "input": {
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
        "preset": "glass"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "veed/subtitles",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 200,
    "usd": "0.20",
    "charged": 200,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "preset": "glass"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Vídeo renderizado que contém legendas estilizadas. |

## Related models

- [Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0/text.md) (`veed/fabric-1.0/text`): from $2.40 / run
- [Fabric 1.0 Fast](https://doitong.com/developers/models/veed/fabric-1.0/fast.md) (`veed/fabric-1.0/fast`): from $0.10 / second of input audio
- [Lipsync](https://doitong.com/developers/models/veed/lipsync.md) (`veed/lipsync`): $0.40 / minute of output video
- [VEED Fabric 1.0](https://doitong.com/developers/models/veed/fabric-1.0.md) (`veed/fabric-1.0`): from $0.08 / second of input audio
- [VEED Clean Audio](https://doitong.com/developers/models/veed/clean-audio.md) (`veed/clean-audio`): $0.0125 / minute of input audio
- [AMT Interpolation](https://doitong.com/developers/models/amt-interpolation.md) (`amt-interpolation`): $0.000575 / second of processing time
- [AnimateDiff Turbo · Video to Video](https://doitong.com/developers/models/fast-animatediff/turbo/video-to-video.md) (`fast-animatediff/turbo/video-to-video`): $0.00125 / second of processing time
- [AnimateDiff · Video to Video](https://doitong.com/developers/models/fast-animatediff/video-to-video.md) (`fast-animatediff/video-to-video`): $0.00125 / second of processing time

## Links

- HTML page: https://doitong.com/developers/models/veed/subtitles
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=veed/subtitles
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/veed/subtitles