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.
Scored across 22 tools
Most tools map to a clearly distinct action+resource (ad generation, face swap, inpainting, background removal, transcription, uploads), and the descriptions add useful guidance such as calling fattly_list_ad_presets before fattly_generate_ad. The main overlaps are fattly_generate_audio (mode=speech) versus fattly_clone_voice, which both produce spoken text, and the cluster of video producers (generate_video, animate_photo, trend_video, actor_swap) that an agent must distinguish by input type rather than name. fattly_video_status is also described as only following fattly_generate_video even though other tools return ids to check with it.
All 22 tools share the fattly_ prefix and snake_case, which makes the set easy to scan. The only deviation is word order: two tools use noun_verb (fattly_actor_swap, fattly_face_swap) and one is noun_noun (fattly_video_status) while the rest follow verb_noun (generate_image, upload_media, list_models, remove_background). Minor and readable, but not a fully predictable pattern.
22 tools is on the heavy side, but the server spans several genuinely separate domains (image, video, audio/voice, ad studio, uploads, account) so most tools earn their place as a distinct generation mode. There is mild redundancy from parallel ad-image/ad-video and speech/voice-clone paths, but nothing looks like filler.
Coverage of a media-generation platform is strong: text-to-image, image editing (inpaint, upscale, background removal), face/actor swap, video generation plus status polling, audio generation, voice cloning, transcription, ad studio, uploads, model listing and credit balance. Remaining gaps are modest: no status/retry path for image or audio jobs, no asset listing or deletion of previously generated media, and no combine/extend operation for clips.
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.
Inputs: consent (required), videoUrl (required), actorId, actorUrl.
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.
Inputs: consent (required), imageUrl (required), prompt, modelId.
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.
Inputs: text (required), consent (required), voiceId, saveName, +1 more.
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.
Inputs: description (required).
Shows the current credit balance on the FATTLY account.
Inputs: no named 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. Upload the source video with fattly_upload_media and the mask with fattly_upload_image (other links are rejected). Takes a few minutes; returns the mp4 link, or a generation id to check with fattly_video_status.
Inputs: prompt (required), consent (required), maskUrl (required), videoUrl (required), +2 more.
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.
Inputs: consent (required), baseImageUrl (required), swapImageUrl (required).
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.
Inputs: mode (required), prompt, actorId, consent, +7 more.
Ad Studio VIDEO ad (premium, from 150 credits; longer Polish ads cost more per second): a real-looking creator presents your product on camera with a real voice — the full site flow. Takes a few minutes; the tool waits ~2 min and then returns an id to check with fattly_video_status.
Inputs: mode (required), locale, prompt, script, +10 more.
Generates AI audio: a voiceover (mode=speech) from text, or music (mode=music) from a description. Returns a link to the mp3 file.
Inputs: mode (required), text (required), voice, seconds.
Generates an AI image from a prompt. Returns a link to the finished image. Credits are deducted from the user's account.
Inputs: prompt (required), model, numImages, aspectRatio, +2 more.
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.
Inputs: prompt (required), model, consent, duration, +3 more.
Edits part of an image: repaints the masked area to match a prompt. Returns a link to the result.
Inputs: prompt (required), maskUrl (required), imageUrl (required).
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.
Inputs: mode.
Returns available models and their cost in credits (images, video, audio). Use before generating to pick the right model.
Inputs: category.
Removes the background from an image, leaving a clean cutout. Returns a link to the result.
Inputs: imageUrl (required).
Transcribes an audio file to text with timed segments. Returns the transcript as JSON.
Inputs: audioUrl (required), task, language.
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.
Inputs: consent (required), imageUrl (required), presetId (required).
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.
Inputs: imageUrl, imageBase64.
Uploads a VIDEO or AUDIO file (public URL or base64 data) to FATTLY and returns a fal URL. Every videoUrl / audioUrl / sampleUrl you pass to other tools (fattly_edit_video, fattly_actor_swap, fattly_transcribe, fattly_clone_voice) must come from this upload — links uploaded elsewhere (even other fal.media links) are rejected. Video: MP4/MOV/WEBM up to 50 MB, checked for safety; audio: MP3/WAV/OGG/M4A/AAC up to 20 MB. Prefer url for larger files. No credits are charged for the upload.
Inputs: kind (required), url, base64.
Upscales an image to higher resolution. Returns a link to the upscaled image.
Inputs: imageUrl (required), factor.
Checks a video generation started by fattly_generate_video. Returns the mp4 link when it is ready, or the current status.
Inputs: id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Make AI videos, images, voiceovers and full AI Video Story episodes on Veo, Kling and Seedance, then post them to TikTok, YouTube and Instagram. 61 tools, OAuth sign-in, every generation priced before it spends.
Generate and edit images, video and audio: 300+ AI models, video tools, voice cloning, transcripts.
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
Your AI assistant's creative studio. Make images, video, music and speech with Kling 4.0, Seedance 2.5, Nano Banana Pro, GPT Image 2.5 and more, billed at real model cost. A second brain learns from every generation and 100+ tested workflows, so results get better the more you make
Add one secure layer between your agents and this server.
