Combien d'outils expose io.github.magichourhq/magic-hour ?

io.github.magichourhq/magic-hour expose 46 outil(s). Le coût de contexte pour les charger tous est d'environ 42824 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Médias / io.github.magichourhq/magic-hour

io.github.magichourhq/magic-hour

serveur MCP (Model Context Protocol) · magic-hour 0.1.0

▸ Médias

[ Non encore testé ]

Verdict MCP Hub
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.

streamable-httpType / transport

directAccès

~42824 tokensCoût de contexte

46Outils

Est-ce que io.github.magichourhq/magic-hour est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.magichourhq/magic-hour » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 46 outils

account_retrieve≈ 984 tokens

Get the current credit balance and subscription details of the account that owns the API key.

Paramètres, retour & exemple (0)

Exemple d'appel

{"name": "account_retrieve", "arguments": {}}

Exemple de retour

{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "tier": "free", "email": "texte", "credits": 1, "subscription": {}}}

ai_clothes_changer_create_image≈ 892 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Change outfits in photos in seconds with just a photo reference. Each photo costs 25 credits.
Paramètres, retour & exemple (2)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- assets · object · requis
  Provide the assets for clothes changer
Exemple d'appel
```
{"name": "ai_clothes_changer_create_image", "arguments": {"assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_face_editor_edit_image≈ 1370 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Edit facial features of an image using AI. Each edit costs 1 frame. The height/width of the output image depends on your subscription. Please refer to our [pricing](https://magichour.ai/pricing) page for more details
Paramètres, retour & exemple (3)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- style · object · requis
  Face editing parameters
- assets · object · requis
  Provide the assets for face editor
Exemple d'appel
```
{"name": "ai_face_editor_edit_image", "arguments": {"style": {}, "assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_gif_generator_create_image≈ 486 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI GIF. Each GIF costs 50 credits.
Paramètres, retour & exemple (3)
Paramètres
- name · string · optionnel
  Give your gif a custom name for easy identification.
- style · object · requis
- output_format · string · optionnel · gif | mp4 | webm
  The output file format for the generated animation.
Exemple d'appel
```
{"name": "ai_gif_generator_create_image", "arguments": {"style": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_headshot_generator_create_image≈ 748 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create an AI headshot. Each headshot costs 50 credits.
Paramètres, retour & exemple (3)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- style · object · optionnel
- assets · object · requis
  Provide the assets for headshot photo
Exemple d'appel
```
{"name": "ai_headshot_generator_create_image", "arguments": {"assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_image_editor_create_image≈ 1822 tokens
MCP guidance: - Requires one or more source images in `assets.image_file_paths`. For prompt-only creation, use `ai_image_generator_create_image` instead. - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Edit images with AI.
Paramètres, retour & exemple (7)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- model · string · optionnel · default | qwen-image-2.1 | qwen-edit | flux-2-klein | nano-banana-2-lite | nano-banana-2 | nano-banana-2.1 | krea-2
  The AI model to use for image editing. Each model has different capabilities and costs. **Models:** - `default` - Use the model we recommend, which will change over time. This is recommended unless you need a specific model. This is the default behavior. - `flux-2-klein` - from 5 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Max additional input images: 5 - `gpt-image-2` - from 50 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Max additional input images: 9 - `gpt-image-2.5-flare` - from 100 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Max additional input images: 9 - `krea-2` - from 10 credits/image - Supported resolutions: 640px, 1k - Available for tiers: free, creator, pro, business - Max additional input images: 1 - `nano-banana` - from 50 credits/image - Supported resolutions: 640px, 1k - Available for tiers: creator, pro, business - Max additional input images: 9 - `nano-banana-2` - from 100 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Max additional input images: 9 - `nano-banana-2-lite` - from 50 credits/image - Supported resolutions: 640px, 1k - Available for tiers: creator, pro, business - Max additional input images: 9 - `nano-banana-2.1` - from 50 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Max additional input images: 9 - `nano-banana-pro` - from 150 credits/image - Supported resolutions: 1k, 2k, 4k - Available for tiers: creator, pro, business - Max additional input images: 9 - `qwen-edit` - from 10 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Max additional input images: 2 - `qwen-image-2.1` - from 10 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Max additional input images: 2 - `seedream-v4` - from 40 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Max additional input images: 9 - `seedream-v4.5` - from 50 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Max additional input images: 9 - `seedream-v5-pro` - from 75 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: creator, pro, business - Max additional input images: 9
- style · object · requis
- assets · object · requis
  Provide the assets for image edit
- resolution · string · optionnel · auto | 640px | 1k | 2k | 4k
  Maximum resolution (longest edge) for the output image. **Options:** - `640px` — up to 640px - `1k` — up to 1024px - `2k` — up to 2048px - `4k` — up to 4096px - `auto` — **Deprecated.** Mapped server-side from your subscription tier to the best matching resolution the model supports **Per-model support:** - `flux-2-klein` - 640px, 1k, 2k - `gpt-image-2` - 640px, 1k, 2k, 4k - `gpt-image-2.5-flare` - 640px, 1k, 2k, 4k - `krea-2` - 640px, 1k - `nano-banana` - 640px, 1k - `nano-banana-2` - 640px, 1k, 2k, 4k - `nano-banana-2-lite` - 640px, 1k - `nano-banana-2.1` - 640px, 1k, 2k, 4k - `nano-banana-pro` - 1k, 2k, 4k - `qwen-edit` - 640px, 1k, 2k - `qwen-image-2.1` - 640px, 1k, 2k - `seedream-v4` - 640px, 1k, 2k, 4k - `seedream-v4.5` - 640px, 1k, 2k, 4k - `seedream-v5-pro` - 640px, 1k, 2k Note: Resolution availability depends on the model and your subscription tier.
- image_count · number · optionnel · 1 | 4 | 9 | 16
  Number of images to generate. Maximum varies by model. Defaults to 1 if not specified.
- aspect_ratio · string · optionnel · auto | 16:9 | 9:16 | 4:3 | 3:2 | 1:1 | 4:5 | 2:3
  The aspect ratio of the output image(s). If not specified, defaults to `auto`.
Exemple d'appel
```
{"name": "ai_image_editor_create_image", "arguments": {"style": {}, "assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_image_generator_create_image≈ 1842 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI image with advanced model selection and quality controls.
Paramètres, retour & exemple (6)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- model · string · optionnel · default | z-image-turbo | qwen-image-2.1 | flux-2-klein | nano-banana-2-lite | nano-banana-2 | nano-banana-2.1 | krea-2
  The AI model to use for image generation. Each model has different capabilities and costs. **Models:** - `default` - Use the model we recommend, which will change over time. This is recommended unless you need a specific model. This is the default behavior. - `flux-2-klein` - from 5 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Image count allowed: 1 - `flux-schnell` - from 5 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Image count allowed: 1, 2, 3, 4 - `gpt-image-2` - from 50 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `gpt-image-2.5-flare` - from 100 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `krea-2` - from 10 credits/image - Supported resolutions: 640px, 1k - Available for tiers: free, creator, pro, business - Image count allowed: 1 - `nano-banana` - from 50 credits/image - Supported resolutions: 640px, 1k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `nano-banana-2` - from 100 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 4, 9, 16 - `nano-banana-2-lite` - from 50 credits/image - Supported resolutions: 640px, 1k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `nano-banana-2.1` - from 50 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 4, 9, 16 - `nano-banana-pro` - from 150 credits/image - Supported resolutions: 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 4, 9, 16 - `qwen-image-2.1` - from 10 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Image count allowed: 1, 2, 3, 4 - `seedream-v4` - from 40 credits/image - Supported resolutions: 640px, 1k, 2k, 4k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `seedream-v5-pro` - from 75 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: creator, pro, business - Image count allowed: 1, 2, 3, 4 - `z-image-turbo` - from 5 credits/image - Supported resolutions: 640px, 1k, 2k - Available for tiers: free, creator, pro, business - Image count allowed: 1, 2, 3, 4 **Deprecated Enum Values:** - `seedream` - Use `seedream-v4` instead.
- style · object · requis
  The art style to use for image generation.
- resolution · string · optionnel · auto | 640px | 1k | 2k | 4k
  Maximum resolution (longest edge) for the output image. **Options:** - `640px` — up to 640px - `1k` — up to 1024px - `2k` — up to 2048px - `4k` — up to 4096px - `auto` — **Deprecated.** Mapped server-side from your subscription tier to the best matching resolution the model supports **Per-model support:** - `flux-2-klein` - 640px, 1k, 2k - `flux-schnell` - 640px, 1k, 2k - `gpt-image-2` - 640px, 1k, 2k, 4k - `gpt-image-2.5-flare` - 640px, 1k, 2k, 4k - `krea-2` - 640px, 1k - `nano-banana` - 640px, 1k - `nano-banana-2` - 640px, 1k, 2k, 4k - `nano-banana-2-lite` - 640px, 1k - `nano-banana-2.1` - 640px, 1k, 2k, 4k - `nano-banana-pro` - 1k, 2k, 4k - `qwen-image-2.1` - 640px, 1k, 2k - `seedream-v4` - 640px, 1k, 2k, 4k - `seedream-v5-pro` - 640px, 1k, 2k - `z-image-turbo` - 640px, 1k, 2k Note: Resolution availability depends on the model and your subscription tier.
- image_count · integer · requis
  Number of images to generate. Maximum varies by model.
- aspect_ratio · string · optionnel · 1:1 | 16:9 | 9:16
  The aspect ratio of the output image(s). If not specified, defaults to `1:1` (square).
Exemple d'appel
```
{"name": "ai_image_generator_create_image", "arguments": {"style": {}, "image_count": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_image_upscaler_create_image≈ 905 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Upscale your image using AI. Each 2x upscale costs 50 credits for balanced/creative modes, and 25 credits for preserve. 4x upscale costs 200 and 100 credits respectively.
Paramètres, retour & exemple (4)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- style · object · optionnel
  Style settings for the upscale. Use `mode` (`"preserve"`, `"balanced"`, or `"creative"`). Defaults to `"balanced"`.
- assets · object · requis
  Provide the assets for upscaling
- scale_factor · number · requis
  How much to scale the image. Must be either 2 or 4. Note: 4x upscale is only available on Creator, Pro, or Business tier.
Exemple d'appel
```
{"name": "ai_image_upscaler_create_image", "arguments": {"assets": {}, "scale_factor": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_meme_generator_create_image≈ 489 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI generated meme. Each meme costs 10 credits.
Paramètres, retour & exemple (2)
Paramètres
- name · string · optionnel
  The name of the meme.
- style · object · requis
Exemple d'appel
```
{"name": "ai_meme_generator_create_image", "arguments": {"style": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_qr_code_generator_create_image≈ 519 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI QR code. Each QR code costs 0 credits.
Paramètres, retour & exemple (3)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- style · object · requis
- content · string · requis
  The content of the QR code.
Exemple d'appel
```
{"name": "ai_qr_code_generator_create_image", "arguments": {"style": {}, "content": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_talking_photo_create_talking_photo≈ 1231 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create a talking photo video from an image and an audio file.
Paramètres, retour & exemple (6)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- style · object · optionnel
  Attributes used to dictate the style of the output
- assets · object · requis
  Provide the assets for creating a talking photo
- end_seconds · number · requis
  The end time of the input audio in seconds. Maximum clip length depends on style.generation_mode: realistic 300s, prompted 45s.
- start_seconds · number · requis
  The start time of the input audio in seconds. Maximum clip length depends on style.generation_mode: realistic 300s, prompted 45s.
- max_resolution · integer · optionnel
  Constrains the larger dimension (height or width) of the output video. Allows you to set a lower resolution than your plan's maximum if desired. The value is capped by your plan's max resolution.
Exemple d'appel
```
{"name": "ai_talking_photo_create_talking_photo", "arguments": {"assets": {}, "end_seconds": 1, "start_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_ugc_ad_create_video≈ 1036 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create a spoken UGC video from a prepared image and script. Returns a project ID; poll GET /v1/video-projects/{id} for status and downloads. To compose an image, generate the image separately with the Image Editor API and supply its download URL.
Paramètres, retour & exemple (5)
Paramètres
- model · string · optionnel · kling-3.0 | ltx-2.5 | veo3.1
  Defaults to kling-3.0 on paid plans and ltx-2.5 on free plans.
- assets · object · requis
- script · string · requis
  The words the actor should speak. Character limits apply after trimming: * kling-3.0: 2500 characters. * ltx-2.5: 1981 characters. * veo3.1: 2500 characters. LTX's dialogue wrapper counts toward its model prompt limit.
- resolution · string · optionnel · 480p | 720p | 1080p
  Defaults to 720p on paid plans and 480p on free plans. Unsupported model/resolution combinations and resolutions unavailable for your plan are rejected.
- end_seconds · number · requis
  Video duration in seconds. Supported values by model: * kling-3.0: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 seconds. * ltx-2.5: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60 seconds. * veo3.1: 4, 6, 8, 15, 22, 29, 36, 43, 50, 57, 64, 71, 78, 85, 92, 99, 106, 113, 120, 127, 134, 141 seconds. Free plans are limited to 5 seconds unless a credit pack has been purchased.
Exemple d'appel
```
{"name": "ai_ugc_ad_create_video", "arguments": {"assets": {}, "script": "texte", "end_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1, "estimated_frame_cost": 1}}
```
ai_video_editor_create_video≈ 1238 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Video Editor you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding video editor into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a video editor job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/ai-video-editor).
Paramètres, retour & exemple (7)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- model · string · optionnel · gemini-omni-1.1 | gemini-omni | ltx-2.5 | ltx-2.3
  Editing model. Defaults to LTX 2.5 for free tier and `gemini-omni-1.1` for paid. `gemini-omni` is deprecated; use `gemini-omni-1.1` instead.
- style · object · requis
- assets · object · requis
  Provide the assets for video editing.
- resolution · string · optionnel · 480p | 720p | 1080p
  Output resolution. Defaults to `480p` for free tier and `720p` for paid. `gemini-omni-1.1` and deprecated `gemini-omni` support 720p and 1080p; LTX 2.5 supports 480p, 720p, and 1080p.
- end_seconds · number · requis
  End time of your clip in seconds. Must be greater than `start_seconds`. Minimum duration depends on model: `gemini-omni-1.1`: 3s, LTX 2.5: 0.5s. Maximum duration depends on model: `gemini-omni-1.1`: 10s, LTX 2.5: 20s.
- start_seconds · number · optionnel
  Start time of your clip (seconds). Must be ≥ 0.
Exemple d'appel
```
{"name": "ai_video_editor_create_video", "arguments": {"style": {}, "assets": {}, "end_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ai_video_translator_create_video≈ 1268 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Video Translator you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding video translator into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a video translator job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/ai-video-translator).
Paramètres, retour & exemple (6)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- assets · object · requis
  Source video for the translation job.
- resolution · string · optionnel · 480p | 720p | 1080p
  Output video resolution. Defaults to 480p. 720p and 1080p require a paid plan.
- end_seconds · number · requis
  End time of your clip (seconds). Must be greater than start_seconds. The clip must be 1-30 seconds long.
- start_seconds · number · optionnel
  Start time of your clip (seconds). Must be ≥ 0.
- target_language · string · requis · English | Chinese (Simplified) | Hindi | Spanish | Arabic | French | Afrikaans | Bengali
  Language to translate the video's speech into.
Exemple d'appel
```
{"name": "ai_video_translator_create_video", "arguments": {"assets": {}, "end_seconds": 1, "target_language": "English"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
animation_create_video≈ 1948 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create a Animation video. The estimated frame cost is calculated based on the `fps` and `end_seconds` input.
Paramètres, retour & exemple (7)
Paramètres
- fps · number · requis
  The desire output video frame rate
- name · string · optionnel
  Give your video a custom name for easy identification.
- style · object · requis
  Defines the style of the output video
- width · integer · requis
  The width of the final output video. The maximum width depends on your subscription. Please refer to our [pricing page](https://magichour.ai/pricing) for more details
- assets · object · requis
  Provide the assets for animation.
- height · integer · requis
  The height of the final output video. The maximum height depends on your subscription. Please refer to our [pricing page](https://magichour.ai/pricing) for more details
- end_seconds · number · requis
  This value determines the duration of the output video.
Exemple d'appel
```
{"name": "animation_create_video", "arguments": {"fps": 1, "style": {}, "width": 1, "assets": {}, "height": 1, "end_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
audio_projects_delete≈ 136 tokens
Permanently delete the rendered audio file(s). This action is not reversible, please be sure before deleting.
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  Unique ID of the audio project. This value is returned by all of the POST APIs that create an audio.
Exemple d'appel
```
{"name": "audio_projects_delete", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
audio_projects_retrieve_details≈ 1026 tokens
MCP guidance: - Use this after a create tool to poll job status. When status is `complete`, surface the `downloads` URLs to the user; if status is `error`, surface the error message. - Each `downloads[n].url` is already the full signed download URL. Use it exactly as returned. Do not shorten it, strip query parameters, or append `expires_at` onto the URL string. Check the progress of a audio project. The `downloads` field is populated after a successful render. **Statuses** - `queued` — waiting to start - `rendering` — in progress - `complete` — ready; see `downloads` - `error` — a failure occurred (see `error`) - `canceled` — user canceled - `draft` — not used
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  Unique ID of the audio project. This value is returned by all of the POST APIs that create an audio.
Exemple d'appel
```
{"name": "audio_projects_retrieve_details", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "type": "texte", "error": {}, "status": "draft", "enabled": true, "downloads": [], "created_at": "texte", "credits_charged": 1}}
```
audio_to_video_create_video≈ 1245 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Audio To Video you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding audio to video into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a audio to video job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/audio-to-video).
Paramètres, retour & exemple (6)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- style · object · optionnel
  Attributes used to dictate the style of the output
- assets · object · requis
  Provide the audio file and an optional reference image.
- resolution · string · optionnel · 480p | 720p | 1080p
  Output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers.
- end_seconds · number · requis
  End time of your clip (seconds). Must be greater than start_seconds.
- start_seconds · number · optionnel
  Start time of your clip (seconds). Must be ≥ 0.
Exemple d'appel
```
{"name": "audio_to_video_create_video", "arguments": {"assets": {}, "end_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
auto_subtitle_generator_create_video≈ 1364 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Automatically generate subtitles for your video in multiple languages.
Paramètres, retour & exemple (5)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- style · object · requis
  Style of the subtitle. At least one of `.style.template` or `.style.custom_config` must be provided. * If only `.style.template` is provided, default values for the template will be used. * If both are provided, the fields in `.style.custom_config` will be used to overwrite the fields in `.style.template`. * If only `.style.custom_config` is provided, then all fields in `.style.custom_config` will be used. To use custom config only, the following `custom_config` params are required: * `.style.custom_config.font` * `.style.custom_config.text_color` * `.style.custom_config.vertical_position` * `.style.custom_config.horizontal_position`
- assets · object · requis
  Provide the assets for auto subtitle generator
- end_seconds · number · requis
  End time of your clip (seconds). Must be greater than start_seconds.
- start_seconds · number · requis
  Start time of your clip (seconds). Must be ≥ 0.
Exemple d'appel
```
{"name": "auto_subtitle_generator_create_video", "arguments": {"style": {}, "assets": {}, "end_seconds": 1, "start_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
body_swap_create_image≈ 848 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Swap a person into a scene image using Nano Banana 2 Lite (640px/1k) or Nano Banana 2 (2k/4k). Credits depend on `resolution` (from 50 credits at 640px upward).
Paramètres, retour & exemple (3)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- assets · object · requis
  Person image and scene image for body swap
- resolution · string · requis · 640px | 1k | 2k | 4k
  Output resolution. Determines credits charged for the run.
Exemple d'appel
```
{"name": "body_swap_create_image", "arguments": {"assets": {}, "resolution": "640px"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
character_replace_create_video≈ 1788 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Character Replace you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding character replace into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a character replace job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/character-replace).
Paramètres, retour & exemple (7)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- model · string · optionnel · wan-animate | kling-3.0
  Model to use. Defaults to `wan-animate`. * **`wan-animate`**: 480p, 720p. Supports `points` subject selection. * **`kling-3.0`**: 720p, 1080p. Clips of 3–10 seconds in `replace` mode or 3–30 seconds in `animate` mode. Picks the main person automatically, so `points` are rejected.
- style · object · optionnel
  Optional style controls for replace vs animate mode and subject selection.
- assets · object · requis
  Source video and reference character image for the job.
- resolution · string · optionnel · 480p | 720p | 1080p
  Output video resolution. Must be supported by `model`. Defaults to the lowest resolution available on your plan for that model.
- end_seconds · number · requis
  End time of your clip (seconds). Must be greater than start_seconds.
- start_seconds · number · optionnel
  Start time of your clip (seconds). Must be ≥ 0.
Exemple d'appel
```
{"name": "character_replace_create_video", "arguments": {"assets": {}, "end_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
face_detection_detect_faces≈ 665 tokens
MCP guidance: - This starts an async face-detection task and returns an `id`. Use the face-detection details endpoint with that id to retrieve detected faces before doing individual face swaps. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Detect faces in an image or video. Use this API to get the list of faces detected in the image or video to use in the [face swap photo](https://docs.magichour.ai/api-reference/image-projects/face-swap-photo) or [face swap video](https://docs.magichour.ai/api-reference/video-projects/face-swap-video) API calls for multi-face swaps. Note: Face detection is free to use for the near future. Pricing may change in the future.
Paramètres, retour & exemple (2)
Paramètres
- assets · object · requis
  Provide the assets for face detection
- confidence_score · number · optionnel
  Confidence threshold for filtering detected faces. * Higher values (e.g., 0.9) include only faces detected with high certainty, reducing false positives. * Lower values (e.g., 0.3) include more faces, but may increase the chance of incorrect detections.
Exemple d'appel
```
{"name": "face_detection_detect_faces", "arguments": {"assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
face_detection_retrieve_details≈ 540 tokens
Get the details of a face detection task. Use this API to get the list of faces detected in the image or video to use in the [face swap photo](https://docs.magichour.ai/api-reference/image-projects/face-swap-photo) or [face swap video](https://docs.magichour.ai/api-reference/video-projects/face-swap-video) API calls for multi-face swaps.
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  The id of the task. This value is returned by the [face detection API](https://docs.magichour.ai/api-reference/files/face-detection#response-id).
Exemple d'appel
```
{"name": "face_detection_retrieve_details", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "faces": [], "status": "queued", "credits_charged": 1}}
```
face_swap_create_video≈ 1902 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Face Swap you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding face swap into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a face swap job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/face-swap).
Paramètres, retour & exemple (5)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- style · object · optionnel
  Style of the face swap video.
- assets · object · requis
  Provide the assets for face swap. For video, The `video_source` field determines whether `video_file_path` or `youtube_url` field is used
- end_seconds · number · requis
  End time of your clip (seconds). Must be greater than start_seconds.
- start_seconds · number · requis
  Start time of your clip (seconds). Must be ≥ 0.
Exemple d'appel
```
{"name": "face_swap_create_video", "arguments": {"assets": {}, "end_seconds": 1, "start_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
face_swap_photo_create_image≈ 1322 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create a face swap photo. Each photo costs 10 credits. The height/width of the output image depends on your subscription. Please refer to our [pricing](https://magichour.ai/pricing) page for more details
Paramètres, retour & exemple (2)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- assets · object · requis
  Provide the assets for face swap photo
Exemple d'appel
```
{"name": "face_swap_photo_create_image", "arguments": {"assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
fetch_audio_download≈ 192 tokens
Fetch a audio `downloads[n].url` from a completed audio project and return it as inline MCP audio content for compatible clients. Pass the exact full signed URL from `downloads[n].url` without trimming query parameters; `expires_at` is separate metadata, not part of the URL. Inline media is capped at 8 MiB; use the signed URL directly for larger downloads.
Paramètres, retour & exemple (2)
Paramètres
- max_bytes · integer · optionnel
- download_url · string · requis
Exemple d'appel
```
{"name": "fetch_audio_download", "arguments": {"download_url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
fetch_image_download≈ 192 tokens
Fetch a image `downloads[n].url` from a completed image project and return it as inline MCP image content for compatible clients. Pass the exact full signed URL from `downloads[n].url` without trimming query parameters; `expires_at` is separate metadata, not part of the URL. Inline media is capped at 8 MiB; use the signed URL directly for larger downloads.
Paramètres, retour & exemple (2)
Paramètres
- max_bytes · integer · optionnel
- download_url · string · requis
Exemple d'appel
```
{"name": "fetch_image_download", "arguments": {"download_url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
fetch_video_download≈ 193 tokens
Fetch a video `downloads[n].url` from a completed video project and return it as an embedded MCP binary resource for compatible clients. Pass the exact full signed URL from `downloads[n].url` without trimming query parameters; `expires_at` is separate metadata, not part of the URL. Inline media is capped at 8 MiB; use the signed URL directly for larger downloads.
Paramètres, retour & exemple (2)
Paramètres
- max_bytes · integer · optionnel
- download_url · string · requis
Exemple d'appel
```
{"name": "fetch_video_download", "arguments": {"download_url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
head_swap_create_image≈ 876 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Swap a head onto a body image. Each image costs 10 credits. Output resolution depends on your subscription; you may set `max_resolution` lower than your plan maximum if desired.
Paramètres, retour & exemple (3)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- assets · object · requis
  Provide the body and head images for head swap
- max_resolution · integer · optionnel
  Constrains the larger dimension (height or width) of the output. Omit to use the maximum allowed for your plan (capped at 2048px). Values above your plan maximum are clamped down to your plan's maximum.
Exemple d'appel
```
{"name": "head_swap_create_image", "arguments": {"assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
image_background_remover_create_image≈ 778 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Remove background from image. Each image costs 5 credits.
Paramètres, retour & exemple (2)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- assets · object · requis
  Provide the assets for background removal
Exemple d'appel
```
{"name": "image_background_remover_create_image", "arguments": {"assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
image_projects_delete≈ 134 tokens
Permanently delete the rendered image(s). This action is not reversible, please be sure before deleting.
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  Unique ID of the image project. This value is returned by all of the POST APIs that create an image.
Exemple d'appel
```
{"name": "image_projects_delete", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
image_projects_retrieve_details≈ 1098 tokens
MCP guidance: - Use this after a create tool to poll job status. When status is `complete`, surface the `downloads` URLs to the user; if status is `error`, surface the error message. - Each `downloads[n].url` is already the full signed download URL. Use it exactly as returned. Do not shorten it, strip query parameters, or append `expires_at` onto the URL string. Check the progress of a image project. The `downloads` field is populated after a successful render. **Statuses** - `queued` — waiting to start - `rendering` — in progress - `complete` — ready; see `downloads` - `error` — a failure occurred (see `error`) - `canceled` — user canceled - `draft` — not used
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  Unique ID of the image project. This value is returned by all of the POST APIs that create an image.
Exemple d'appel
```
{"name": "image_projects_retrieve_details", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "type": "texte", "error": {}, "status": "draft", "enabled": true, "downloads": [], "created_at": "texte", "image_count": 1, "credits_charged": 1}}
```
image_to_video_create_video≈ 2302 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Image To Video you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding image to video into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a image to video job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/image-to-video).
Paramètres, retour & exemple (7)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- audio · boolean · optionnel
  Whether to include audio in the video. Defaults to `false` if not specified. Audio support varies by model: * **`gemini-omni-1.1`**: Not supported * **`kling-2.6`**: Not supported * **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled * **`ltx-2.5`**: Toggle-able: no additional credits for audio * **`minimax-h3`**: Toggle-able: no additional credits for audio * **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled * **`seedance-2.0`**: Toggle-able: no additional credits for audio * **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio * **`seedance-2.5`**: Toggle-able: no additional credits for audio * **`veo3.1`**: Toggle-able: audio adds extra credits when enabled * **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled * **`wan-2.2`**: Not supported * **`wan-3.0`**: Toggle-able: no additional credits for audio
- model · string · optionnel · default | kling-3.0 | ltx-2.5 | seedance-2.0-mini | wan-3.0 | seedance-2.5 | gemini-omni-1.1 | minimax-h3
  The AI model to use for video generation. * `default`: uses our currently recommended model for general use. For paid tiers, defaults to `kling-3.0`. For free tiers, it defaults to `ltx-2.5`. * `gemini-omni-1.1`: Best for precise short clips, first/last frames, and high-resolution output. * `kling-2.6`: Best for action, motion blur, and controlled camera moves. * `kling-3.0`: Best for cinematic stories, references, and optional audio. * `ltx-2.5`: Fastest for general scenes, long clips, audio, and rapid iteration. * `minimax-h3`: Great for reference-driven clips with native audio and longer durations. * `seedance-1.5`: Best for smooth, consistent motion with an end frame. * `seedance-2.0`: Best for reference-led clips with precise subject control. * `seedance-2.0-mini`: Faster reference-led clips with consistent motion and audio. * `seedance-2.5`: Best for premium realism, detail, and natural motion. * `veo3.1`: Best for romantic interactions and expressive action, with realistic detail. * `veo3.1-lite`: Balanced realism and audio at a lower cost than Veo 3.1. * `wan-2.2`: Best for physical motion, action, and camera movement. * `wan-3.0`: High-quality video with native audio, long clips, and end-frame control. If you specify the deprecated model value that includes the `-audio` suffix, this will be the same as included `audio` as `true`.
- style · object · optionnel
  Attributed used to dictate the style of the output
- assets · object · requis
  Provide the assets for image-to-video.
- resolution · string · optionnel · 360p | 480p | 720p | 1080p | 4k
  Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers. * **`gemini-omni-1.1`**: Supports 360p, 720p, 1080p, 4k. * **`kling-2.6`**: Supports 720p, 1080p. * **`kling-3.0`**: Supports 720p, 1080p, 4k. * **`ltx-2.5`**: Supports 480p, 720p, 1080p. * **`minimax-h3`**: Supports 480p, 720p, 1080p. * **`seedance-1.5`**: Supports 480p, 720p, 1080p. * **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k. * **`seedance-2.0-mini`**: Supports 480p, 720p. * **`seedance-2.5`**: Supports 480p, 720p, 1080p. * **`veo3.1`**: Supports 720p, 1080p. * **`veo3.1-lite`**: Supports 720p, 1080p. * **`wan-2.2`**: Supports 480p, 720p, 1080p. * **`wan-3.0`**: Supports 480p, 720p, 1080p.
- end_seconds · number · requis
  The total duration of the output video in seconds. Supported durations depend on the chosen model: * **`gemini-omni-1.1`**: any integer from 3 to 10 * **`kling-2.6`**: 5, 10 * **`kling-3.0`**: any integer from 3 to 15 * **`ltx-2.5`**: any integer from 1 to 60 * **`minimax-h3`**: any integer from 1 to 30 * **`seedance-1.5`**: any integer from 4 to 12 * **`seedance-2.0`**: any integer from 4 to 15 * **`seedance-2.0-mini`**: any integer from 4 to 15 * **`seedance-2.5`**: any integer from 4 to 30 * **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56 * **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56 * **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15 * **`wan-3.0`**: 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30
Exemple d'appel
```
{"name": "image_to_video_create_video", "arguments": {"assets": {}, "end_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
lip_sync_create_video≈ 1640 tokens
Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Lip Sync you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding lip sync into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a lip sync job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/lip-sync).
Paramètres, retour & exemple (6)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- style · object · optionnel
  Attributes used to dictate the style of the output
- assets · object · requis
  Provide the assets for lip-sync. For video, The `video_source` field determines whether `video_file_path` or `youtube_url` field is used
- end_seconds · number · requis
  End time of your clip (seconds). Must be greater than start_seconds.
- max_fps_limit · number · optionnel
  Defines the maximum FPS (frames per second) for the output video. If the input video's FPS is lower than this limit, the output video will retain the input FPS. This is useful for reducing unnecessary frame usage in scenarios where high FPS is not required.
- start_seconds · number · requis
  Start time of your clip (seconds). Must be ≥ 0.
Exemple d'appel
```
{"name": "lip_sync_create_video", "arguments": {"assets": {}, "end_seconds": 1, "start_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
photo_colorizer_create_image≈ 618 tokens
MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Colorize image. Each image costs 10 credits.
Paramètres, retour & exemple (2)
Paramètres
- name · string · optionnel
  Give your image a custom name for easy identification.
- assets · object · requis
  Provide the assets for photo colorization
Exemple d'appel
```
{"name": "photo_colorizer_create_image", "arguments": {"assets": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
ping≈ 107 tokens
Check that the Magic Hour MCP server is reachable.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "ping", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}
```
saved_items_list≈ 693 tokens
Returns active saved items owned by the authenticated account, newest first. Each item includes every saved asset with a durable file_path for reuse in compatible generation APIs and a temporary signed URL for previewing or downloading. Filter by type to find characters, references, voices, moodboards, or brand kits. To fetch the next page, pass the response's next_cursor as cursor.
Paramètres, retour & exemple (3)
Paramètres
- type · string · optionnel · character | reference | voice | moodboard | brand_kit
  Only return saved items of this type.
- limit · integer · optionnel
  Maximum number of saved items to return. Defaults to 20.
- cursor · string · optionnel
  Opaque pagination cursor from the previous response's next_cursor.
Exemple d'appel
```
{"name": "saved_items_list", "arguments": {"type": "character", "limit": 1, "cursor": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"items": [], "next_cursor": "texte"}}
```
text_to_video_create_video≈ 2259 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. **What this API does** Create the same Text To Video you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding text to video into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a text to video job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/text-to-video).
Paramètres, retour & exemple (8)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- audio · boolean · optionnel
  Whether to include audio in the video. Defaults to `false` if not specified. Audio support varies by model: * **`gemini-omni-1.1`**: Not supported * **`kling-2.6`**: Not supported * **`kling-3.0`**: Toggle-able: audio adds extra credits when enabled * **`ltx-2.5`**: Toggle-able: no additional credits for audio * **`minimax-h3`**: Toggle-able: no additional credits for audio * **`seedance-1.5`**: Toggle-able: audio adds extra credits when enabled * **`seedance-2.0`**: Toggle-able: no additional credits for audio * **`seedance-2.0-mini`**: Toggle-able: no additional credits for audio * **`seedance-2.5`**: Toggle-able: no additional credits for audio * **`veo3.1`**: Toggle-able: audio adds extra credits when enabled * **`veo3.1-lite`**: Toggle-able: audio adds extra credits when enabled * **`wan-2.2`**: Not supported * **`wan-3.0`**: Toggle-able: no additional credits for audio
- model · string · optionnel · default | kling-3.0 | ltx-2.5 | seedance-2.0-mini | wan-3.0 | seedance-2.5 | gemini-omni-1.1 | minimax-h3
  The AI model to use for video generation. * `default`: uses our currently recommended model for general use. For paid tiers, defaults to `kling-3.0`. For free tiers, it defaults to `ltx-2.5`. * `gemini-omni-1.1`: Best for precise short clips, first/last frames, and high-resolution output. * `kling-2.6`: Best for action, motion blur, and controlled camera moves. * `kling-3.0`: Best for cinematic stories, references, and optional audio. * `ltx-2.5`: Fastest for general scenes, long clips, audio, and rapid iteration. * `minimax-h3`: Great for reference-driven clips with native audio and longer durations. * `seedance-1.5`: Best for smooth, consistent motion with an end frame. * `seedance-2.0`: Best for reference-led clips with precise subject control. * `seedance-2.0-mini`: Faster reference-led clips with consistent motion and audio. * `seedance-2.5`: Best for premium realism, detail, and natural motion. * `veo3.1`: Best for romantic interactions and expressive action, with realistic detail. * `veo3.1-lite`: Balanced realism and audio at a lower cost than Veo 3.1. * `wan-2.2`: Best for physical motion, action, and camera movement. * `wan-3.0`: High-quality video with native audio, long clips, and end-frame control. If you specify the deprecated model value that includes the `-audio` suffix, this will be the same as included `audio` as `true`.
- style · object · requis
- references · array · optionnel
  Reference media for video generation. Name references without @ and refer to them as @name in style.prompt. Maximum 10 references total. Supported models and reference media: * **`kling-3.0`**: Supports images, videos. * **`minimax-h3`**: Supports images, videos, audio. * **`seedance-2.0`**: Supports images, videos, audio. * **`seedance-2.0-mini`**: Supports images, videos, audio. * **`seedance-2.5`**: Supports images, videos, audio. * **`wan-3.0`**: Supports images, videos, audio.
- resolution · string · optionnel · 360p | 480p | 720p | 1080p | 4k
  Controls the output video resolution. Defaults to `720p` on paid tiers and `480p` on free tiers. * **`gemini-omni-1.1`**: Supports 360p, 720p, 1080p, 4k. * **`kling-2.6`**: Supports 720p, 1080p. * **`kling-3.0`**: Supports 720p, 1080p, 4k. * **`ltx-2.5`**: Supports 480p, 720p, 1080p. * **`minimax-h3`**: Supports 480p, 720p, 1080p. * **`seedance-1.5`**: Supports 480p, 720p, 1080p. * **`seedance-2.0`**: Supports 480p, 720p, 1080p, 4k. * **`seedance-2.0-mini`**: Supports 480p, 720p. * **`seedance-2.5`**: Supports 480p, 720p, 1080p. * **`veo3.1`**: Supports 720p, 1080p. * **`veo3.1-lite`**: Supports 720p, 1080p. * **`wan-2.2`**: Supports 480p, 720p, 1080p. * **`wan-3.0`**: Supports 480p, 720p, 1080p.
- end_seconds · number · requis
  The total duration of the output video in seconds. Supported durations depend on the chosen model: * **`gemini-omni-1.1`**: any integer from 3 to 10 * **`kling-2.6`**: 5, 10 * **`kling-3.0`**: any integer from 3 to 15 * **`ltx-2.5`**: any integer from 1 to 60 * **`minimax-h3`**: any integer from 1 to 30 * **`seedance-1.5`**: any integer from 4 to 12 * **`seedance-2.0`**: any integer from 4 to 15 * **`seedance-2.0-mini`**: any integer from 4 to 15 * **`seedance-2.5`**: any integer from 4 to 30 * **`veo3.1`**: 4, 6, 8, 16, 24, 32, 40, 48, 56 * **`veo3.1-lite`**: 4, 6, 8, 16, 24, 32, 40, 48, 56 * **`wan-2.2`**: 3, 4, 5, 6, 7, 8, 9, 10, 15 * **`wan-3.0`**: 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 20, 25, 30
- aspect_ratio · string · optionnel · 16:9 | 9:16 | 1:1
  Determines the aspect ratio of the output video. * **`gemini-omni-1.1`**: Supports 16:9, 9:16. * **`kling-2.6`**: Supports 9:16, 16:9, 1:1. * **`kling-3.0`**: Supports 9:16, 16:9, 1:1. * **`ltx-2.5`**: Supports 9:16, 16:9, 1:1. * **`minimax-h3`**: Supports 16:9, 9:16, 1:1. * **`seedance-1.5`**: Supports 9:16, 16:9, 1:1. * **`seedance-2.0`**: Supports 9:16, 16:9, 1:1. * **`seedance-2.0-mini`**: Supports 9:16, 16:9, 1:1. * **`seedance-2.5`**: Supports 9:16, 16:9, 1:1. * **`veo3.1`**: Supports 9:16, 16:9. * **`veo3.1-lite`**: Supports 9:16, 16:9. * **`wan-2.2`**: Supports 9:16, 16:9, 1:1. * **`wan-3.0`**: Supports 16:9, 9:16, 1:1.
Exemple d'appel
```
{"name": "text_to_video_create_video", "arguments": {"style": {}, "end_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
video_assets_generate_presigned_url≈ 1000 tokens
MCP guidance: - This only creates presigned upload URLs. For local files, upload the raw bytes to each returned `upload_url` outside the generation call, then pass the matching `file_path` into the create tool. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Generates a list of pre-signed upload URLs for the assets required. This API is only necessary if you want to upload to Magic Hour's storage. Refer to the [Input Files Guide](https://docs.magichour.ai/integration/inputs-and-outputs) for more details. The response array will match the order of items in the request body. **Valid file extensions per asset type**: - video: mp4, m4v, mov, webm - audio: mp3, wav, aac, flac, webm, weba, m4a, opus, ogg, oga, aiff, amr - image: png, jpg, jpeg, jfif, heic, heif, webp, avif, jp2, tiff, tif, bmp - gif: gif, webp, webm > Note: `gif` is only supported for face swap API `video_file_path` field. Once you receive an upload URL, send a `PUT` request to upload the file directly. Example: ``` curl -X PUT --data '@/path/to/file/video.mp4' \ https://videos.magichour.ai/api-assets/id/video.mp4?<auth params from the API response> ```
Paramètres, retour & exemple (1)
Paramètres
- items · array · requis
  The list of assets to upload. The response array will match the order of items in the request body.
Exemple d'appel
```
{"name": "video_assets_generate_presigned_url", "arguments": {"items": []}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"items": []}}
```
video_projects_delete≈ 134 tokens
Permanently delete the rendered video. This action is not reversible, please be sure before deleting.
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  Unique ID of the video project. This value is returned by all of the POST APIs that create a video.
Exemple d'appel
```
{"name": "video_projects_delete", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
video_projects_retrieve_details≈ 1308 tokens
MCP guidance: - Use this after a create tool to poll job status. When status is `complete`, surface the `downloads` URLs to the user; if status is `error`, surface the error message. - Each `downloads[n].url` is already the full signed download URL. Use it exactly as returned. Do not shorten it, strip query parameters, or append `expires_at` onto the URL string. Check the progress of a video project. The `downloads` field is populated after a successful render. **Statuses** - `queued` — waiting to start - `rendering` — in progress - `complete` — ready; see `downloads` - `error` — a failure occurred (see `error`) - `canceled` — user canceled - `draft` — not used
Paramètres, retour & exemple (1)
Paramètres
- id · string · requis
  Unique ID of the video project. This value is returned by all of the POST APIs that create a video.
Exemple d'appel
```
{"name": "video_projects_retrieve_details", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "fps": 1, "name": "texte", "type": "texte", "error": {}, "width": 1, "height": 1, "status": "draft", "enabled": true, "downloads": [], "created_at": "texte", "end_seconds": 1}}
```
video_to_video_create_video≈ 1949 tokens
MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Video To Video you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding video to video into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a video to video job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/video-to-video).
Paramètres, retour & exemple (6)
Paramètres
- name · string · optionnel
  Give your video a custom name for easy identification.
- style · object · requis
- assets · object · requis
  Provide the assets for video-to-video. For video, The `video_source` field determines whether `video_file_path` or `youtube_url` field is used
- end_seconds · number · requis
  End time of your clip (seconds). Must be greater than start_seconds.
- start_seconds · number · requis
  Start time of your clip (seconds). Must be ≥ 0.
- fps_resolution · string · optionnel · FULL | HALF
  Determines whether the resulting video will have the same frame per second as the original video, or half. * `FULL` - the result video will have the same FPS as the input video * `HALF` - the result video will have half the FPS as the input video
Exemple d'appel
```
{"name": "video_to_video_create_video", "arguments": {"style": {}, "assets": {}, "end_seconds": 1, "start_seconds": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "credits_charged": 1}}
```
wait_for_audio_project≈ 295 tokens
Poll an audio project until it completes, errors, is canceled, or times out. After a timeout, resume with the same id; do not create another generation. Returns the final project JSON and, when complete, attempts to inline audio downloads for Inspector or compatible clients. Returns sanitized download fields. Use `exact_download_urls[n]` or `downloads[n].url` exactly as returned; do not shorten it, remove query parameters, or append expiration metadata. Inline previews share an 8 MiB limit; all download URLs remain available.
Paramètres, retour & exemple (6)
Paramètres
- id · string · requis
- timeout_seconds · number · optionnel
- max_inline_downloads · integer · optionnel
- poll_interval_seconds · number · optionnel
- max_bytes_per_download · integer · optionnel
- include_inline_downloads · boolean · optionnel
Exemple d'appel
```
{"name": "wait_for_audio_project", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
wait_for_image_project≈ 295 tokens
Poll an image project until it completes, errors, is canceled, or times out. After a timeout, resume with the same id; do not create another generation. Returns the final project JSON and, when complete, attempts to inline image downloads for Inspector or compatible clients. Returns sanitized download fields. Use `exact_download_urls[n]` or `downloads[n].url` exactly as returned; do not shorten it, remove query parameters, or append expiration metadata. Inline previews share an 8 MiB limit; all download URLs remain available.
Paramètres, retour & exemple (6)
Paramètres
- id · string · requis
- timeout_seconds · number · optionnel
- max_inline_downloads · integer · optionnel
- poll_interval_seconds · number · optionnel
- max_bytes_per_download · integer · optionnel
- include_inline_downloads · boolean · optionnel
Exemple d'appel
```
{"name": "wait_for_image_project", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
wait_for_video_project≈ 248 tokens
Poll a video project until it completes, errors, is canceled, or times out. After a timeout, resume with the same id; do not create another generation. Returns sanitized download fields. Use `exact_download_urls[n]` or `downloads[n].url` exactly as returned; do not shorten it, remove query parameters, or append expiration metadata. Inline previews share an 8 MiB limit; all download URLs remain available.
Paramètres, retour & exemple (5)
Paramètres
- id · string · requis
- timeout_seconds · number · optionnel
- max_inline_downloads · integer · optionnel
- poll_interval_seconds · number · optionnel
- include_inline_downloads · boolean · optionnel
Exemple d'appel
```
{"name": "wait_for_video_project", "arguments": {"id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
workflow_guide_retrieve≈ 216 tokens
Read Magic Hour workflow guidance for face swap, image editing, image-to-video, video generation, lip sync, UGC ads, talking photos or API integration. Returns product and documentation URLs, exact tool names, ordered steps, example requests, follow-up edits and review criteria; does not generate media, spend credits or check account access.
Paramètres, retour & exemple (1)
Paramètres
- workflow · string · requis · video-face-swap | image-editor | image-to-video | video-generator | lip-sync | ugc-ads | talking-photo | media-apis
Exemple d'appel
```
{"name": "workflow_guide_retrieve", "arguments": {"workflow": "video-face-swap"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.magichour.ai/