Generate AI images, video, voiceovers and music from Claude, ChatGPT or Cursor through 50+ models (Veo 3.1, Kling 3, Seedance, Nano Banana, GPT Image, ElevenLabs). Also image editing, upscaling, background removal, face swap, transcription, voice cloning and UGC-style video ads. Sign in with OAuth — no API key to paste. Tools are annotated (read-only vs. credit-spending); failed generations are refunded.
Score is being calculated.
Replaces the creator in an existing video with another actor. Takes a few minutes. By using this you confirm you have the right to the video and the actor's likeness.
| Name | Required | Description | Default |
|---|---|---|---|
| actorId | No | Avatar you generated (fattly_create_avatar). | |
| consent | Yes | Must be true — confirms you have the right to the video and the actor's likeness. | |
| actorUrl | No | Your own actor photo as a fal URL. | |
| videoUrl | Yes | Source video — a fal URL from fattly_upload_image. |
Cinema Studio: brings a still photo to life as a video (adds motion). Takes a few minutes. By using this you confirm you have the right to animate the people/content shown.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | Optional motion/look direction. | |
| consent | Yes | Must be true — confirms you have the right to animate the people/content shown. | |
| modelId | No | Video model id (default: Cinema model). List: fattly_list_models. | |
| imageUrl | Yes | Photo to animate — a fal URL from fattly_upload_image. |
Voice: either clone a NEW voice from a sample and speak text with it, or REUSE a saved voice (cheaper). Use only voices you have the right to use.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | What the voice should say. | |
| voiceId | No | Id of a voice you saved earlier — reuse it instead of cloning (cheaper). | |
| saveName | No | If set when cloning, saves the voice under this name for reuse. | |
| sampleUrl | No | Voice sample to clone — a fal URL. Required when cloning a new voice. |
Ad Studio: generates your own creator avatar from a description (20 credits). Returns the actorId — pass it to fattly_generate_ad / fattly_generate_ad_video so the SAME creator presents your product. Adults only, enforced server-side.
| Name | Required | Description | Default |
|---|---|---|---|
| description | Yes | What the creator looks like, e.g. 'a woman with curly red hair and freckles, casual denim jacket'. Any language — translated server-side. |
Shows the current credit balance on the FATTLY account.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Draw-to-Edit: edits a REGION of a video using a mask + a text instruction (e.g. "make the car burn", "remove the person", "replace with a red car"). The masked area (WHITE on the mask, BLACK elsewhere) is regenerated across the whole clip, the rest is kept. Source video AND mask image must both be fal URLs (get them with fattly_upload_image). Takes a few minutes; returns the mp4 link, or a generation id to check with fattly_video_status.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | What should happen to the masked area. | |
| maskUrl | Yes | Mask image, fal URL. WHITE = area to edit, BLACK = keep unchanged. | |
| videoUrl | Yes | Source video, fal URL (from fattly_upload_image). | |
| resolution | No | Output resolution (default 720p). | |
| durationSeconds | No | Clip length in seconds, 2-12 (default 5). |
Swaps the face from one image onto another. SFW-only and the result is scanned — use only faces you have the right to use; do not create misleading or explicit imagery.
| Name | Required | Description | Default |
|---|---|---|---|
| baseImageUrl | Yes | Scene image (the body/photo to keep) — fal URL. | |
| swapImageUrl | Yes | Face image to place into the scene — fal URL. |
Ad Studio: turns a product photo into a finished ad (20 credits). graphic = product alone in a styled scene; product = a creator holding it; service = a creator with no product. Pick templateId with fattly_list_ad_presets. Upload the product photo with fattly_upload_image first.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | graphic = product only (needs productImageUrl). product = creator + product (needs productImageUrl AND a creator). service = creator only (needs prompt AND a creator). | |
| prompt | No | What the ad is about — REQUIRED for service mode. Any language; it is translated to English server-side. | |
| actorId | No | Id of an avatar you generated earlier on this account („My actors”). | |
| setting | No | Scene id from fattly_list_ad_presets (scenes). | |
| avatarId | No | Creator from the built-in roster (product/service modes). See fattly_list_ad_presets. | |
| avatarUrl | No | Your own creator photo as a fal URL (alternative to avatarId). | |
| unbranded | No | Keep the product free of invented logos/branding. | |
| templateId | No | Ad preset id from fattly_list_ad_presets. Must match the mode (graphic presets only in graphic mode, and vice versa). | |
| aspectRatio | No | Graphic mode only: 1:1, 2:3, 9:16 or 16:9 (default 1:1). Ignored in product/service modes, which are always 9:16. | |
| productImageUrl | No | Product photo as a fal URL — REQUIRED for graphic and product modes. Get one with fattly_upload_image. |
Ad Studio VIDEO ad (premium, ~150 credits): your creator holds your product and SPEAKS your script, with a real voice. This is the full site flow — product + creator + what the creator says. Takes a few minutes; the tool waits ~2 min and then returns an id to check with fattly_video_status.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | product = creator holds your product (needs productImageUrl). service = creator talks to camera, no product in frame. | |
| voice | No | Voice name for non-EN locales. | |
| locale | No | Spoken language (default en). EN uses native Kling audio; others use TTS + avatar. | |
| script | Yes | What the creator SAYS on camera. Keep it short — a few seconds of speech. | |
| actorId | No | Avatar you generated with fattly_create_avatar — the SAME creator presents the product. | |
| setting | No | Scene id from fattly_list_ad_presets. | |
| avatarId | No | Creator from the built-in roster (see fattly_list_ad_presets). | |
| avatarUrl | No | Your own creator photo as a fal URL. | |
| unbranded | No | Keep the product free of invented branding. | |
| templateId | No | Ad preset id — must be a non-graphic preset (see fattly_list_ad_presets). | |
| productImageUrl | No | Product photo as a fal URL — REQUIRED for product mode. Use fattly_upload_image. |
Generates AI audio: a voiceover (mode=speech) from text, or music (mode=music) from a description. Returns a link to the mp3 file.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | speech = voiceover, music = music. | |
| text | Yes | Text to read (speech) or a music description (music). | |
| voice | No | Voiceover voice, e.g. Rachel, Aria, George (speech only). | |
| seconds | No | Music length: 15, 30 or 60 (music only). |
Generates an AI image from a prompt. Returns a link to the finished image. Credits are deducted from the user's account.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model id (default nano-banana-2). List: fattly_list_models. | |
| prompt | Yes | Description of the image to generate. | |
| numImages | No | Number of images 1–4 (default 1). | |
| aspectRatio | No | Aspect ratio, e.g. 1:1, 16:9, 9:16 (default 1:1). | |
| inputImageUrl | No | Optional single input image for editing / face-swap models — must be a fal URL. Get one with fattly_upload_image. | |
| inputImageUrls | No | Optional MULTIPLE input images (fal URLs) for multi-image edit models like nano-banana-2-edit / nano-banana-pro-edit. Typical swap use: image #1 = the scene/frame to keep (background, framing, lighting), image #2 = the subject/face to place into that scene. Get each URL from fattly_upload_image. |
Generates an AI video from a prompt (or from an image). Takes a few minutes — the tool waits up to ~2 minutes and returns a link to the mp4 file; if it is still rendering, it returns a generation id to check with fattly_video_status.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | kling-3-standard | veo-3-1 | seedance-2-5 (default kling-3-standard). | |
| prompt | Yes | Description of the video scene. | |
| duration | No | Clip length in seconds (model dependent). | |
| aspectRatio | No | Aspect ratio, e.g. 16:9, 9:16, 1:1 (default 16:9). | |
| inputImageUrl | No | Optional start image for image-to-video — must be a fal URL. Get one with fattly_upload_image. | |
| referenceImageUrls | No | Optional MULTIPLE reference images (fal URLs, 2-50) for reference-to-video models like seedance-2-5 — the model blends them into one video. With a single URL the video starts from that image (image-to-video). Get each URL with fattly_upload_image. |
Edits part of an image: repaints the masked area to match a prompt. Returns a link to the result.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | What to paint into the masked area. | |
| maskUrl | Yes | Mask (white = area to repaint) — a fal URL from fattly_upload_image. | |
| imageUrl | Yes | Image to edit — a fal URL from fattly_upload_image. |
Lists what Ad Studio offers: ad presets (templateId), scenes and creator avatars. Call this BEFORE fattly_generate_ad — preset ids are validated server-side and a preset only works in its matching mode.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Filter presets by mode. graphic = product only, no person in frame. product = creator holding/using your product. service = creator only, no product. Omit to list every preset. |
Returns available models and their cost in credits (images, video, audio). Use before generating to pick the right model.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | Optional category filter. |
Removes the background from an image, leaving a clean cutout. Returns a link to the result.
| Name | Required | Description | Default |
|---|---|---|---|
| imageUrl | Yes | Image to cut out — a fal URL from fattly_upload_image. |
Transcribes an audio file to text with timed segments. Returns the transcript as JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | transcribe (default) or translate to English. | |
| audioUrl | Yes | Audio to transcribe — a fal URL from fattly_upload_image (kind audio). | |
| language | No | Language hint, e.g. en, pl (auto-detect if omitted). |
Turns a photo into a trend-style video from a preset. Takes a few minutes. By using this you confirm you have the right to animate the people/content shown.
| Name | Required | Description | Default |
|---|---|---|---|
| consent | Yes | Must be true — confirms you have the right to animate the people/content shown. | |
| imageUrl | Yes | Photo — a fal URL from fattly_upload_image. | |
| presetId | Yes | Trend preset id. |
Uploads an image (public URL or base64 data) to FATTLY and returns a fal URL. Use this to turn a picture into an inputImageUrl for editing / face-swap / image-to-video models: pass the returned URL as inputImageUrl to fattly_generate_image or fattly_generate_video. No credits are charged for the upload.
| Name | Required | Description | Default |
|---|---|---|---|
| imageUrl | No | Public http(s) URL of a JPG, PNG or WEBP image, max 10 MB. | |
| imageBase64 | No | Alternatively: base64-encoded image data (raw or data-URI), max 10 MB. |
Upscales an image to higher resolution. Returns a link to the upscaled image.
| Name | Required | Description | Default |
|---|---|---|---|
| factor | No | Scale factor 2–4 (default 2). | |
| imageUrl | Yes | Image to upscale — a fal URL from fattly_upload_image. |
Checks a video generation started by fattly_generate_video. Returns the mp4 link when it is ready, or the current status.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Generation id returned by fattly_generate_video. |
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
Best Image and video generation: 20+ models (Kling, Seedance, Veo, NB, FLUX.2), OAuth, pay-per-use.
Generate text, images, speech, music, and video with any AI model, from one credit balance.
Generate and edit images, videos, and audio with 150+ models from 20+ vendors.
Add one secure layer between your agents and this server.
