AI media generation via fal.ai (image, video, audio)
Generate images, videos and audio through fal.ai MCP models β Nano Banana, Seedance, Kling, Veo 3, CSM-1B β with cost estimation first
- What
- Generate images, videos and audio through fal.ai MCP models β Nano Banana, Seedance, Kling, Veo 3, CSM-1B β with cost estimation first
- Cost
- Free
- Needs
- a fal.ai account and API key (FAL_KEY) β generations are billed per run, no usable free tier; the fal.ai MCP server (fal-ai-mcp-server) installable via npx
- Install
- Copy the installer prompt below into your Muse β your agent does the rest.
Curated by Skill Harbor β π³ **Paid API required / API payante requise** β fal.ai generations are billed per run through your FAL API key; there is no ongoing usable free tier. @affaan-m's unified media-generation skill routes through the fal.ai MCP server: text-to-image and editing with Nano Banana 2 (fast) and Nano Banana Pro (high fidelity), text/image-to-video with Seedance 1.0 Pro, Kling Video v3 Pro and Veo 3, text-to-speech with CSM-1B, video-to-audio with ThinkSound, plus an ElevenLabs REST fallback for professional voice synthesis β with a `search`/`find`/`estimate_cost` discovery flow and a strict discipline of checking cost before generating, using seeds for reproducibility, and iterating on cheap models before final renders. Honest caveats: requires the fal.ai MCP configured with your own `FAL_KEY` (keep it in the vault); video jobs are async β poll status; third-party models are subject to fal.ai's own terms. MIT-licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a fal.ai account and API key (FAL_KEY) β generations are billed per run, no usable free tier; the fal.ai MCP server (fal-ai-mcp-server) installable via npx Install "AI media generation via fal.ai (image, video, audio)" for me. It gives the agent @affaan-m's playbook for generating media through the fal.ai MCP: text-to-image/editing (Nano Banana 2/Pro), text/image-to-video (Seedance 1.0 Pro, Kling Video v3 Pro, Veo 3), text-to-speech (CSM-1B), video-to-audio (ThinkSound), plus an ElevenLabs fallback β with model discovery (search/find), mandatory cost estimation before generating, seeds for reproducibility, and async job handling. MIT-licensed. Repository: https://github.com/affaan-m/ecc/blob/main/.agents/skills/fal-ai-media/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "fal-ai-media". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. get a FAL API key and save it in the vault, add the fal.ai MCP server to my agent config). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you β no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the sellerβs own page, usually Stripe.
What does the β next to a creatorβs name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself β always check a build before installing it.