# HeyGen

> Make AI avatar videos with HeyGen: have an avatar or a photo speak your script, generate videos from a prompt or a template, translate videos with lip-sync, and turn text into speech. Start workflows when a video or translation is ready.

App · 22 actions. Web page: https://docs.lodol.com/docs/integrations/heygen

## Actions

### Create avatar video

Start a video of an avatar speaking your script (or lip-syncing audio). It is paid for from your HeyGen balance and takes a few minutes: follow with 'Wait for video' to get the file.

**Inputs**

- Avatar (`avatar_id`, text, required): The avatar look to appear in the video. Pick one, or give a look id from 'List avatar looks'.
- Script (`script`, text): What to say, up to 5,000 characters. Leave empty only when giving an audio link to lip-sync instead.
- Voice (`voice_id`, text): The voice that speaks the script. Leave empty to use the avatar's own voice.
- Audio link (`audio_url`, text): Instead of a script: a public link to an MP3 or WAV file (up to 10 minutes) to lip-sync.
- Title (`title`, text): The video's title in HeyGen.
- Shape (`aspect_ratio`, text): The video's shape. Defaults to 16:9 landscape. One of: `16:9` (16:9 landscape (default)), `9:16` (9:16 portrait, for Reels, Shorts and TikTok), `1:1` (1:1 square), `4:5` (4:5 portrait, for feeds), `5:4` (5:4 landscape), `auto` (Match the avatar or photo).
- Resolution (`resolution`, text): The video's resolution. Higher costs more. One of: `720p`, `1080p` (1080p (full HD)), `4k` (4K (Avatar III digital twins and studio avatars only)).
- Background colour (`background_color`, text): A solid background as a hex colour, such as #FFFFFF for white. Leave empty to keep the avatar's own background.
- Burn in captions (`captions`, true/false): Yes shows captions in the video. A caption file comes back either way.
- Voice speed (`voice_speed`, number): How fast the script is spoken, 0.5 to 1.5. Defaults to 1. From 0.5 to 1.5.
- Engine (`engine`, text): Which HeyGen model animates the avatar. Defaults to Avatar IV; 'List avatar looks' shows which a look supports. One of: `avatar_iv` (Avatar IV (default)), `avatar_v` (Avatar V, the most natural (supported looks only)), `avatar_iii` (Avatar III).

**Outputs**

- `status` (text): Where it is up to, such as pending
- `video_id` (text): The new video's id, for 'Wait for video' or 'Get video'

**Example output**

```json
{
  "status": "pending",
  "video_id": "8f3c2b1a9d4e4c7b"
}
```

### Create talking photo video

Start a video of the person in a photo speaking your script (or lip-syncing audio), with no avatar to set up. Paid for from your HeyGen balance; follow with 'Wait for video'.

**Inputs**

- Photo link (`image_url`, text, required): A public link to a JPG or PNG of one person facing the camera. 'Upload file' gives one for a file you have.
- Script (`script`, text): What to say, up to 5,000 characters. Leave empty only when giving an audio link to lip-sync instead.
- Voice (`voice_id`, text): The voice that speaks the script. Needed with a script.
- Audio link (`audio_url`, text): Instead of a script: a public link to an MP3 or WAV file (up to 10 minutes) to lip-sync.
- Title (`title`, text): The video's title in HeyGen.
- Shape (`aspect_ratio`, text): The video's shape. Defaults to 16:9 landscape. One of: `16:9` (16:9 landscape (default)), `9:16` (9:16 portrait, for Reels, Shorts and TikTok), `1:1` (1:1 square), `4:5` (4:5 portrait, for feeds), `5:4` (5:4 landscape), `auto` (Match the avatar or photo).
- Resolution (`resolution`, text): The video's resolution. Higher costs more. One of: `720p`, `1080p` (1080p (full HD)), `4k` (4K (Avatar III digital twins and studio avatars only)).
- Burn in captions (`captions`, true/false): Yes shows captions in the video. A caption file comes back either way.
- Voice speed (`voice_speed`, number): How fast the script is spoken, 0.5 to 1.5. Defaults to 1. From 0.5 to 1.5.
- Expressiveness (`expressiveness`, text): How animated the face is. Defaults to low. One of: `low` (Low (default)), `medium`, `high`.
- Motion (`motion_prompt`, text): How the person should move, such as 'nods and smiles'.

**Outputs**

- `status` (text): Where it is up to, such as pending
- `video_id` (text): The new video's id, for 'Wait for video' or 'Get video'

**Example output**

```json
{
  "status": "pending",
  "video_id": "8f3c2b1a9d4e4c7b"
}
```

### Create video from prompt

Describe a video and HeyGen's Video Agent writes the script, picks the avatar and voice (unless you do) and renders it. Paid for from your HeyGen balance; follow with 'Get prompt video'.

**Inputs**

- Prompt (`prompt`, text, required): What the video should be, up to 10,000 characters: its topic, length, tone and any lines to say.
- Avatar (`avatar_id`, text): The avatar look to use. Leave empty to let HeyGen pick.
- Voice (`voice_id`, text): The voice to narrate with. Leave empty to let HeyGen pick.
- Style (`style_id`, text): A visual style. Leave empty to let HeyGen pick.
- Orientation (`orientation`, text): Landscape or portrait. Chosen from the prompt if empty. One of: `landscape`, `portrait`.

**Outputs**

- `session_id` (text): The prompt video's id, for 'Get prompt video'
- `status` (text): Where it is up to, such as thinking
- `video_id` (text): The video's id if rendering has started; empty until then

**Example output**

```json
{
  "session_id": "sess_abc123",
  "status": "generating",
  "video_id": ""
}
```

### Create video from template

Start a video from a template, filling in its values by name. Paid for from your HeyGen balance; follow with 'Wait for video'.

**Inputs**

- Template (`template_id`, text, required): The template. Pick one, or give its id.
- Values (`values`, object): Each value's name with what to put in it, such as {"first_name": "Sam"}. Text takes words, an image, video or audio a public link, a character an avatar look id, a voice a voice id. Every text value must be filled in; 'Get template' lists them.
- Title (`title`, text): The video's title in HeyGen.
- Burn in captions (`captions`, true/false): Yes shows captions in the video. A caption file comes back either way.

**Outputs**

- `status` (text): Where it is up to, such as pending
- `video_id` (text): The new video's id, for 'Wait for video' or 'Get video'

**Example output**

```json
{
  "status": "pending",
  "video_id": "8f3c2b1a9d4e4c7b"
}
```

### Delete video

Delete a video and its files from HeyGen. There is no undo.

**Inputs**

- Video ID (`video_id`, text, required): The video's id, from a create step or 'List videos'.

**Outputs**

- `deleted` (true/false): Always true once deleted
- `video_id` (text): The video deleted

**Example output**

```json
{
  "deleted": true,
  "video_id": "8f3c2b1a9d4e4c7b"
}
```

### Generate speech

Turn text into speech with a HeyGen voice and get a link to the audio file.

**Inputs**

- Text (`text`, text, required): What to say, up to 5,000 characters.
- Voice (`voice_id`, text, required): The voice to speak with.
- Speed (`speed`, number): How fast to speak, 0.5 to 2. Defaults to 1. From 0.5 to 2.
- Language code (`language`, text): The text's language as a code such as en, es or pt. Detected from the text if empty.

**Outputs**

- `audio_url` (text): Link to the audio file
- `duration` (number): Length in seconds
- `engine` (text): The speech engine HeyGen used

**Example output**

```json
{
  "audio_url": "https://files.heygen.ai/speech/7c1e2d3f.mp3",
  "duration": 2.1,
  "engine": "starfish"
}
```

### Get account

Get the HeyGen account the API key belongs to and how much it has left to spend: its API balance in dollars or its credits.

**Inputs**: None.

**Outputs**

- `balance_unit` (text): USD or credits
- `plan` (text): The plan, for an account paying with plan credits; empty otherwise
- `remaining_balance` (number): What the account has left: dollars for an API balance, or credits
- `user` (object): The HeyGen account the API key belongs to

**Example output**

```json
{
  "balance_unit": "USD",
  "plan": "",
  "remaining_balance": 42.5,
  "user": {
    "billing_type": "wallet",
    "email": "jane@example.com",
    "first_name": "Jane",
    "last_name": "Doe",
    "username": "jane_doe"
  }
}
```

### Get prompt video

See how far a prompt video has got. Once HeyGen starts rendering it, its video id is here for 'Wait for video'.

**Inputs**

- Prompt video ID (`session_id`, text, required): The id 'Create video from prompt' returned.

**Outputs**

- `session` (object): The prompt video's progress
- `session_id` (text): The prompt video's id
- `status` (text): thinking, waiting_for_input, reviewing, generating, completed or failed
- `video_id` (text): The video's id once rendering has started; empty until then

**Example output**

```json
{
  "session": {
    "created_at": 1761300000,
    "error": null,
    "progress": 40,
    "session_id": "sess_abc123",
    "status": "generating",
    "title": "New dashboard update",
    "video_id": "8f3c2b1a9d4e4c7b"
  },
  "session_id": "sess_abc123",
  "status": "generating",
  "video_id": "8f3c2b1a9d4e4c7b"
}
```

### Get template

Get a template and the values it lets you fill in, with their names, kinds and current values.

**Inputs**

- Template (`template_id`, text, required): The template. Pick one, or give its id.

**Outputs**

- `template` (object): A template
- `variable_names` (list): Just the values' names
- `variables` (list): The values you can fill in

**Example output**

```json
{
  "template": {
    "aspect_ratio": "16:9",
    "created_at": 1761200000,
    "id": "3e9d1c7b5a2f4e8d",
    "name": "Customer welcome",
    "thumbnail_url": "https://files.heygen.ai/template/3e9d1c7b5a2f4e8d.jpg",
    "updated_at": 1761250000
  },
  "variable_names": [
    "first_name",
    "logo"
  ],
  "variables": [
    {
      "current_value": "Sam",
      "name": "first_name",
      "type": "text"
    },
    {
      "current_value": "https://files.heygen.ai/asset/logo.png",
      "name": "logo",
      "type": "image"
    }
  ]
}
```

### Get translation

Get a translation's status and, once it's ready, its video, audio and caption links.

**Inputs**

- Translation ID (`video_translation_id`, text, required): The translation's id, from 'Translate video' or 'List translations'.

**Outputs**

- `ready` (true/false): True once the translation is finished
- `status` (text): pending, running, completed or failed
- `translation` (object): The translation
- `video_translation_id` (text): The translation's id
- `video_url` (text): Download link for the translated video, empty until it is ready

**Example output**

```json
{
  "ready": true,
  "status": "completed",
  "translation": {
    "audio_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp3",
    "created_at": 1761300300,
    "duration": 12.4,
    "failure_code": null,
    "failure_message": null,
    "id": "5b2a7c9e1f3d4a6b",
    "input_language": "en",
    "output_language": "Spanish (Spain)",
    "srt_caption_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.srt",
    "status": "completed",
    "title": "Welcome, Sam (Spanish)",
    "translate_audio_only": false,
    "video_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp4",
    "vtt_caption_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.vtt"
  },
  "video_translation_id": "5b2a7c9e1f3d4a6b",
  "video_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp4"
}
```

### Get video

Get a video's status and, once it's ready, its download link, thumbnail and captions.

**Inputs**

- Video ID (`video_id`, text, required): The video's id, from a create step or 'List videos'.

**Outputs**

- `ready` (true/false): True once the video is finished
- `status` (text): pending, processing, completed or failed
- `video` (object): The video
- `video_id` (text): The video's id
- `video_url` (text): Download link for the finished video, empty until it is ready. It expires after a while.

**Example output**

```json
{
  "ready": true,
  "status": "completed",
  "video": {
    "captioned_video_url": null,
    "completed_at": 1761300180,
    "created_at": 1761300000,
    "duration": 12.4,
    "failure_code": null,
    "failure_message": null,
    "folder_id": null,
    "gif_url": null,
    "id": "8f3c2b1a9d4e4c7b",
    "output_language": null,
    "status": "completed",
    "subtitle_url": "https://files.heygen.ai/caption/8f3c2b1a9d4e4c7b.srt",
    "thumbnail_url": "https://files.heygen.ai/thumbnail/8f3c2b1a9d4e4c7b.jpg",
    "title": "Welcome, Sam",
    "video_page_url": "https://app.heygen.com/videos/8f3c2b1a9d4e4c7b",
    "video_url": "https://files.heygen.ai/video/8f3c2b1a9d4e4c7b.mp4"
  },
  "video_id": "8f3c2b1a9d4e4c7b",
  "video_url": "https://files.heygen.ai/video/8f3c2b1a9d4e4c7b.mp4"
}
```

### List avatar looks

List avatar looks (outfits and styles). A look's id is what 'Create avatar video' takes as its Avatar.

**Inputs**

- Avatar (`avatar_group_id`, text): Only the looks of this avatar.
- Kind (`avatar_type`, text): Only looks of this kind. One of: `studio_avatar` (Studio avatar), `digital_twin` (Digital twin), `photo_avatar` (Photo avatar).
- Whose (`ownership`, text): Only your own avatars, or only HeyGen's stock ones. Both if empty. One of: `private` (My own avatars), `public` (HeyGen's stock avatars).
- Page size (`limit`, number): How many to return, 1 to 50. HeyGen's default is 20. From 1 to 50.
- Next page (`page_token`, text): The 'next_page_token' an earlier run of this step gave, to get the page after it.

**Outputs**

- `count` (number): How many on this page
- `has_more` (true/false): True when there are more after this page
- `looks` (list): The avatar looks
- `next_page_token` (text): Give this as the Next page field to get the next page; empty on the last one

**Example output**

```json
{
  "count": 1,
  "has_more": false,
  "looks": [
    {
      "avatar_type": "studio_avatar",
      "default_voice_id": "f38a635bee7a4d1f9b0a654a31d050d2",
      "gender": "female",
      "group_id": "a1b2c3d4e5f6",
      "id": "Abigail_expressive_2024112501",
      "name": "Abigail (Upper Body)",
      "preferred_orientation": "landscape",
      "preview_image_url": "https://files.heygen.ai/avatar/abigail.webp",
      "preview_video_url": "https://files.heygen.ai/avatar/abigail.mp4",
      "status": "completed",
      "supported_api_engines": [
        "avatar_iv",
        "avatar_iii"
      ],
      "tags": [
        "professional"
      ]
    }
  ],
  "next_page_token": ""
}
```

### List avatars

List avatars (the characters), your own and HeyGen's stock ones. Each has one or more looks: use 'List avatar looks' for the ids a video takes.

**Inputs**

- Whose (`ownership`, text): Only your own avatars, or only HeyGen's stock ones. Both if empty. One of: `private` (My own avatars), `public` (HeyGen's stock avatars).
- Page size (`limit`, number): How many to return, 1 to 50. HeyGen's default is 20. From 1 to 50.
- Next page (`page_token`, text): The 'next_page_token' an earlier run of this step gave, to get the page after it.

**Outputs**

- `avatars` (list): The avatars
- `count` (number): How many on this page
- `has_more` (true/false): True when there are more after this page
- `next_page_token` (text): Give this as the Next page field to get the next page; empty on the last one

**Example output**

```json
{
  "avatars": [
    {
      "created_at": 1730000000,
      "default_voice_id": "f38a635bee7a4d1f9b0a654a31d050d2",
      "gender": "female",
      "id": "a1b2c3d4e5f6",
      "looks_count": 3,
      "name": "Abigail",
      "preview_image_url": "https://files.heygen.ai/avatar/abigail.webp",
      "preview_video_url": "https://files.heygen.ai/avatar/abigail.mp4",
      "status": "completed"
    }
  ],
  "count": 1,
  "has_more": false,
  "next_page_token": ""
}
```

### List templates

List the templates you can make videos from: those built in HeyGen's editor with values to fill in.

**Inputs**

- Page size (`limit`, number): How many to return, 1 to 100. From 1 to 100.
- Next page (`page_token`, text): The 'next_page_token' an earlier run of this step gave, to get the page after it.

**Outputs**

- `count` (number): How many on this page
- `has_more` (true/false): True when there are more after this page
- `next_page_token` (text): Give this as the Next page field to get the next page; empty on the last one
- `templates` (list): The templates

**Example output**

```json
{
  "count": 1,
  "has_more": false,
  "next_page_token": "",
  "templates": [
    {
      "aspect_ratio": "16:9",
      "created_at": 1761200000,
      "id": "3e9d1c7b5a2f4e8d",
      "name": "Customer welcome",
      "thumbnail_url": "https://files.heygen.ai/template/3e9d1c7b5a2f4e8d.jpg",
      "updated_at": 1761250000
    }
  ]
}
```

### List translation languages

List the languages HeyGen can translate a video into.

**Inputs**: None.

**Outputs**

- `count` (number): How many
- `languages` (list): The language names 'Translate video' takes

**Example output**

```json
{
  "count": 3,
  "languages": [
    "English",
    "Spanish (Spain)",
    "French (France)"
  ]
}
```

### List translations

List the account's video translations with their status and links.

**Inputs**

- Page size (`limit`, number): How many to return, 1 to 100. From 1 to 100.
- Next page (`page_token`, text): The 'next_page_token' an earlier run of this step gave, to get the page after it.

**Outputs**

- `count` (number): How many on this page
- `has_more` (true/false): True when there are more after this page
- `next_page_token` (text): Give this as the Next page field to get the next page; empty on the last one
- `translations` (list): The translations

**Example output**

```json
{
  "count": 1,
  "has_more": false,
  "next_page_token": "",
  "translations": [
    {
      "audio_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp3",
      "created_at": 1761300300,
      "duration": 12.4,
      "failure_code": null,
      "failure_message": null,
      "id": "5b2a7c9e1f3d4a6b",
      "input_language": "en",
      "output_language": "Spanish (Spain)",
      "srt_caption_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.srt",
      "status": "completed",
      "title": "Welcome, Sam (Spanish)",
      "translate_audio_only": false,
      "video_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp4",
      "vtt_caption_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.vtt"
    }
  ]
}
```

### List videos

List the account's videos with their status and download links, optionally only those whose title contains some text.

**Inputs**

- Title contains (`title`, text): Only videos whose title contains this.
- Page size (`limit`, number): How many to return, 1 to 100. From 1 to 100.
- Next page (`page_token`, text): The 'next_page_token' an earlier run of this step gave, to get the page after it.

**Outputs**

- `count` (number): How many on this page
- `has_more` (true/false): True when there are more after this page
- `next_page_token` (text): Give this as the Next page field to get the next page; empty on the last one
- `videos` (list): The videos

**Example output**

```json
{
  "count": 1,
  "has_more": false,
  "next_page_token": "",
  "videos": [
    {
      "captioned_video_url": null,
      "completed_at": 1761300180,
      "created_at": 1761300000,
      "duration": 12.4,
      "failure_code": null,
      "failure_message": null,
      "folder_id": null,
      "gif_url": null,
      "id": "8f3c2b1a9d4e4c7b",
      "output_language": null,
      "status": "completed",
      "subtitle_url": "https://files.heygen.ai/caption/8f3c2b1a9d4e4c7b.srt",
      "thumbnail_url": "https://files.heygen.ai/thumbnail/8f3c2b1a9d4e4c7b.jpg",
      "title": "Welcome, Sam",
      "video_page_url": "https://app.heygen.com/videos/8f3c2b1a9d4e4c7b",
      "video_url": "https://files.heygen.ai/video/8f3c2b1a9d4e4c7b.mp4"
    }
  ]
}
```

### List voices

List voices from HeyGen's library or your own, by language and gender, with a sample of each.

**Inputs**

- Library (`voice_type`, text): HeyGen's voice library, or your own voices. One of: `public` (HeyGen's voice library (default)), `private` (My own voices).
- Language (`language`, text): Only voices in this language, such as English.
- Gender (`gender`, text): Only voices of this gender. One of: `female`, `male`.
- Page size (`limit`, number): How many to return, 1 to 100. From 1 to 100.
- Next page (`page_token`, text): The 'next_page_token' an earlier run of this step gave, to get the page after it.

**Outputs**

- `count` (number): How many on this page
- `has_more` (true/false): True when there are more after this page
- `next_page_token` (text): Give this as the Next page field to get the next page; empty on the last one
- `voices` (list): The voices

**Example output**

```json
{
  "count": 1,
  "has_more": false,
  "next_page_token": "",
  "voices": [
    {
      "default_engine": "starfish",
      "gender": "female",
      "language": "English",
      "name": "Allison",
      "preview_audio_url": "https://files.heygen.ai/voice/allison.mp3",
      "support_pause": true,
      "type": "public",
      "voice_id": "f38a635bee7a4d1f9b0a654a31d050d2"
    }
  ]
}
```

### Translate video

Translate a video into one or more languages in the speaker's own voice, with lip-sync. Paid for by the minute from your HeyGen balance; follow with 'Wait for translation'.

**Inputs**

- Video link (`video_url`, text, required): A public link to the MP4 or WebM to translate, such as a HeyGen video's download link.
- Translate into (`output_languages`, list, required): The languages to translate into: one translation each.
- Title (`title`, text): The video's title in HeyGen.
- Quality (`mode`, text): Faster, or better lip-sync. Defaults to speed. One of: `speed` (Speed: faster (default)), `precision` (Precision: better lip-sync).
- Audio only (`translate_audio_only`, true/false): Yes translates the voice but leaves the lips as they are.
- Speakers (`speaker_count`, number): How many people speak, 1 to 10. Helps tell voices apart. From 1 to 10.
- Remove background music (`remove_background_music`, true/false): Yes drops the music track from the translation.

**Outputs**

- `count` (number): How many translations started
- `video_translation_id` (text): The first translation's id, for 'Wait for translation'
- `video_translation_ids` (list): One translation id per language, in order

**Example output**

```json
{
  "count": 1,
  "video_translation_id": "5b2a7c9e1f3d4a6b",
  "video_translation_ids": [
    "5b2a7c9e1f3d4a6b"
  ]
}
```

### Upload file

Upload an image, video, audio file or PDF (up to 32 MB) to HeyGen and get a public link the photo, video and translation steps take.

**Inputs**

- File (`file`, text, required): The file: upload one, pick one from an earlier step, or paste a public link to it. PNG, JPEG, MP4, WebM, MP3, WAV or PDF.

**Outputs**: The uploaded file

- `asset_id` (text): The file's id in HeyGen
- `mime_type` (text): The file's type, such as image/png
- `size_bytes` (number): The file's size in bytes
- `url` (text): The file's public link, which video, photo and translation steps take

**Example output**

```json
{
  "asset_id": "asset_abc123def456",
  "mime_type": "image/png",
  "size_bytes": 245760,
  "url": "https://files.heygen.ai/assets/asset_abc123def456.png"
}
```

### Wait for translation

Wait until a translation is ready, then return its links. Fails with HeyGen's reason if it fails, or if it is still running when the wait runs out.

**Inputs**

- Translation ID (`video_translation_id`, text, required): The translation's id, from 'Translate video' or 'List translations'.
- Wait up to (minutes) (`max_minutes`, number): How long to wait, 1 to 30 minutes. Defaults to 10. A short video usually takes a few. From 1 to 30.

**Outputs**

- `ready` (true/false): True once the translation is finished
- `status` (text): pending, running, completed or failed
- `translation` (object): The translation
- `video_translation_id` (text): The translation's id
- `video_url` (text): Download link for the translated video, empty until it is ready

**Example output**

```json
{
  "ready": true,
  "status": "completed",
  "translation": {
    "audio_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp3",
    "created_at": 1761300300,
    "duration": 12.4,
    "failure_code": null,
    "failure_message": null,
    "id": "5b2a7c9e1f3d4a6b",
    "input_language": "en",
    "output_language": "Spanish (Spain)",
    "srt_caption_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.srt",
    "status": "completed",
    "title": "Welcome, Sam (Spanish)",
    "translate_audio_only": false,
    "video_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp4",
    "vtt_caption_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.vtt"
  },
  "video_translation_id": "5b2a7c9e1f3d4a6b",
  "video_url": "https://files.heygen.ai/translate/5b2a7c9e1f3d4a6b.mp4"
}
```

### Wait for video

Wait until a video is ready, then return its download link. Fails with HeyGen's reason if the video fails, or if it is still rendering when the wait runs out.

**Inputs**

- Video ID (`video_id`, text, required): The video's id, from a create step or 'List videos'.
- Wait up to (minutes) (`max_minutes`, number): How long to wait, 1 to 30 minutes. Defaults to 10. A short video usually takes a few. From 1 to 30.

**Outputs**

- `ready` (true/false): True once the video is finished
- `status` (text): pending, processing, completed or failed
- `video` (object): The video
- `video_id` (text): The video's id
- `video_url` (text): Download link for the finished video, empty until it is ready. It expires after a while.

**Example output**

```json
{
  "ready": true,
  "status": "completed",
  "video": {
    "captioned_video_url": null,
    "completed_at": 1761300180,
    "created_at": 1761300000,
    "duration": 12.4,
    "failure_code": null,
    "failure_message": null,
    "folder_id": null,
    "gif_url": null,
    "id": "8f3c2b1a9d4e4c7b",
    "output_language": null,
    "status": "completed",
    "subtitle_url": "https://files.heygen.ai/caption/8f3c2b1a9d4e4c7b.srt",
    "thumbnail_url": "https://files.heygen.ai/thumbnail/8f3c2b1a9d4e4c7b.jpg",
    "title": "Welcome, Sam",
    "video_page_url": "https://app.heygen.com/videos/8f3c2b1a9d4e4c7b",
    "video_url": "https://files.heygen.ai/video/8f3c2b1a9d4e4c7b.mp4"
  },
  "video_id": "8f3c2b1a9d4e4c7b",
  "video_url": "https://files.heygen.ai/video/8f3c2b1a9d4e4c7b.mp4"
}
```
