fal-ai-media
透過 fal.ai MCP 生成圖片、影片與音訊
中文翻譯
---
name: fal-ai-media
description: 透過 fal.ai MCP 統一產生媒體：圖片、影片與音訊。涵蓋文字生圖（Nano Banana）、文字/圖片生影片（Seedance、Kling、Veo 3）、文字轉語音（CSM-1B），以及影片生音訊（ThinkSound）。在使用者想用 AI 產生圖片、影片或音訊時使用。
metadata:
origin: ECC
---
# fal.ai 媒體生成
> **容易過時的 skill。** fal.ai 的 model ID、價格、輸入和 MCP 工具名稱
> 變動很快。在承諾某個模型、參數、輸出格式或費用之前，
> 先搜尋或抓取最新的模型 metadata。
透過 MCP 使用 fal.ai 模型產生圖片、影片和音訊。
## 何時啟用
- 使用者想從文字 prompt 產生圖片
- 從文字或圖片建立影片
- 產生語音、音樂或音效
- 任何媒體生成任務
- 使用者說「generate image」、「create video」、「text to speech」、「make a thumbnail」或類似的話
## MCP 需求
必須設定好 fal.ai MCP server。加到 `~/.claude.json`：
```json
"fal-ai": {
"command": "npx",
"args": ["-y", "fal-ai-mcp-server"],
"env": { "FAL_KEY": "YOUR_FAL_KEY_HERE" }
}
```
到 [fal.ai](https://fal.ai) 取得 API key。
## MCP 工具
fal.ai MCP 提供這些工具：
- `search`：用關鍵字找可用的模型
- `find`：取得模型細節與參數
- `generate`：用參數執行模型
- `result`：檢查非同步生成的狀態
- `status`：檢查 job 狀態
- `cancel`：取消執行中的 job
- `estimate_cost`：估算生成費用
- `models`：列出熱門模型
- `upload`：上傳檔案當作輸入
---
## 圖片生成
### Nano Banana 2（快速）
最適合：快速迭代、草稿、文字生圖、圖片編輯。
```
generate(
app_id: "fal-ai/nano-banana-2",
input_data: {
"prompt": "a futuristic cityscape at sunset, cyberpunk style",
"image_size": "landscape_16_9",
"num_images": 1,
"seed": 42
}
)
```
### Nano Banana Pro（高擬真）
最適合：正式產出的圖片、寫實感、字體排印、細節豐富的 prompt。
```
generate(
app_id: "fal-ai/nano-banana-pro",
input_data: {
"prompt": "professional product photo of wireless headphones on marble surface, studio lighting",
"image_size": "square",
"num_images": 1,
"guidance_scale": 7.5
}
)
```
### 常用圖片參數
| 參數 | 型別 | 選項 | 備註 |
|-------|------|---------|-------|
| `prompt` | string | required | 描述你想要的內容 |
| `image_size` | string | `square`, `portrait_4_3`, `landscape_16_9`, `portrait_16_9`, `landscape_4_3` | 長寬比 |
| `num_images` | number | 1-4 | 要產生幾張 |
| `seed` | number | any integer | 可重現性 |
| `guidance_scale` | number | 1-20 | 要多貼近 prompt（越高越字面） |
### 圖片編輯
用 Nano Banana 2 搭配輸入圖片，做 inpainting、outpainting 或風格轉換：
```
# First upload the source image
upload(file_path: "/path/to/image.png")
# Then generate with image input
generate(
app_id: "fal-ai/nano-banana-2",
input_data: {
"prompt": "same scene but in watercolor style",
"image_url": "<uploaded_url>",
"image_size": "landscape_16_9"
}
)
```
---
## 影片生成
### Seedance 1.0 Pro（ByteDance）
最適合：文字生影片、動態品質高的圖片生影片。
```
generate(
app_id: "fal-ai/seedance-1-0-pro",
input_data: {
"prompt": "a drone flyover of a mountain lake at golden hour, cinematic",
"duration": "5s",
"aspect_ratio": "16:9",
"seed": 42
}
)
```
### Kling Video v3 Pro
最適合：附原生音訊生成的文字/圖片生影片。
```
generate(
app_id: "fal-ai/kling-video/v3/pro",
input_data: {
"prompt": "ocean waves crashing on a rocky coast, dramatic clouds",
"duration": "5s",
"aspect_ratio": "16:9"
}
)
```
### Veo 3（Google DeepMind）
最適合：帶生成音效、視覺品質高的影片。
```
generate(
app_id: "fal-ai/veo-3",
input_data: {
"prompt": "a bustling Tokyo street market at night, neon signs, crowd noise",
"aspect_ratio": "16:9"
}
)
```
### 圖片生影片
從現有的圖片開始：
```
generate(
app_id: "fal-ai/seedance-1-0-pro",
input_data: {
"prompt": "camera slowly zooms out, gentle wind moves the trees",
"image_url": "<uploaded_image_url>",
"duration": "5s"
}
)
```
### 影片參數
| 參數 | 型別 | 選項 | 備註 |
|-------|------|---------|-------|
| `prompt` | string | required | 描述影片 |
| `duration` | string | `"5s"`, `"10s"` | 影片長度 |
| `aspect_ratio` | string | `"16:9"`, `"9:16"`, `"1:1"` | 畫面比例 |
| `seed` | number | any integer | 可重現性 |
| `image_url` | string | URL | 圖片生影片用的來源圖片 |
---
## 音訊生成
### CSM-1B（對話式語音）
自然、有對話感的文字轉語音。
```
generate(
app_id: "fal-ai/csm-1b",
input_data: {
"text": "Hello, welcome to the demo. Let me show you how this works.",
"speaker_id": 0
}
)
```
### ThinkSound（影片生音訊）
從影片內容產生搭配的音訊。
```
generate(
app_id: "fal-ai/thinksound",
input_data: {
"video_url": "<video_url>",
"prompt": "ambient forest sounds with birds chirping"
}
)
```
### ElevenLabs（透過 API，不用 MCP）
要專業的語音合成，直接使用 ElevenLabs：
```python
import os
import requests
resp = requests.post(
"https://api.elevenlabs.io/v1/text-to-speech/<voice_id>",
headers={
"xi-api-key": os.environ["ELEVENLABS_API_KEY"],
"Content-Type": "application/json"
},
json={
"text": "Your text here",
"model_id": "eleven_turbo_v2_5",
"voice_settings": {"stability": 0.5, "similarity_boost": 0.75}
}
)
with open("output.mp3", "wb") as f:
f.write(resp.content)
```
### VideoDB 生成式音訊
如果有設定 VideoDB，就用它的生成式音訊：
```python
# Voice generation
audio = coll.generate_voice(text="Your narration here", voice="alloy")
# Music generation
music = coll.generate_music(prompt="upbeat electronic background music", duration=30)
# Sound effects
sfx = coll.generate_sound_effect(prompt="thunder crack followed by rain")
```
---
## 費用估算
生成之前，先檢查預估費用：
```
estimate_cost(
estimate_type: "unit_price",
endpoints: {
"fal-ai/nano-banana-pro": {
"unit_quantity": 1
}
}
)
```
## 模型探索
為特定任務找模型：
```
search(query: "text to video")
find(endpoint_ids: ["fal-ai/seedance-1-0-pro"])
models()
```
## 小技巧
- 迭代 prompt 時用 `seed` 取得可重現的結果
- prompt 迭代先用較低成本的模型（Nano Banana 2），定稿時再換成 Pro
- 影片的 prompt 要描述清楚但精簡，聚焦在動作與場景
- 圖片生影片比純文字生影片更能控制結果
- 執行昂貴的影片生成之前，先檢查 `estimate_cost`
## 相關 Skill
- `tasteforge-video`：離線的品味萃取與模態規劃。它的
endpoint 候選與 request manifest 只供參考，不是已提交的
job 或已儲存的 Fal 工作流。TasteForge 的交接不代表授權上傳
或生成；請使用另外授權的 provider 工作流，並在執行前驗證
它目前的 endpoint schema。
- `videodb`：影片處理、剪輯與串流
- `video-editing`：AI 驅動的影片剪輯工作流
- `content-engine`：社群平台的內容創作英文原文
---
name: fal-ai-media
description: Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
metadata:
origin: ECC
---
# fal.ai Media Generation
> **Drift-prone skill.** fal.ai model IDs, pricing, inputs, and MCP tool names
> change quickly. Search or fetch the current model metadata before promising a
> specific model, parameter, output format, or cost.
Generate images, videos, and audio using fal.ai models via MCP.
## When to Activate
- User wants to generate images from text prompts
- Creating videos from text or images
- Generating speech, music, or sound effects
- Any media generation task
- User says "generate image", "create video", "text to speech", "make a thumbnail", or similar
## MCP Requirement
fal.ai MCP server must be configured. Add to `~/.claude.json`:
```json
"fal-ai": {
"command": "npx",
"args": ["-y", "fal-ai-mcp-server"],
"env": { "FAL_KEY": "YOUR_FAL_KEY_HERE" }
}
```
Get an API key at [fal.ai](https://fal.ai).
## MCP Tools
The fal.ai MCP provides these tools:
- `search` — Find available models by keyword
- `find` — Get model details and parameters
- `generate` — Run a model with parameters
- `result` — Check async generation status
- `status` — Check job status
- `cancel` — Cancel a running job
- `estimate_cost` — Estimate generation cost
- `models` — List popular models
- `upload` — Upload files for use as inputs
---
## Image Generation
### Nano Banana 2 (Fast)
Best for: quick iterations, drafts, text-to-image, image editing.
```
generate(
app_id: "fal-ai/nano-banana-2",
input_data: {
"prompt": "a futuristic cityscape at sunset, cyberpunk style",
"image_size": "landscape_16_9",
"num_images": 1,
"seed": 42
}
)
```
### Nano Banana Pro (High Fidelity)
Best for: production images, realism, typography, detailed prompts.
```
generate(
app_id: "fal-ai/nano-banana-pro",
input_data: {
"prompt": "professional product photo of wireless headphones on marble surface, studio lighting",
"image_size": "square",
"num_images": 1,
"guidance_scale": 7.5
}
)
```
### Common Image Parameters
| Param | Type | Options | Notes |
|-------|------|---------|-------|
| `prompt` | string | required | Describe what you want |
| `image_size` | string | `square`, `portrait_4_3`, `landscape_16_9`, `portrait_16_9`, `landscape_4_3` | Aspect ratio |
| `num_images` | number | 1-4 | How many to generate |
| `seed` | number | any integer | Reproducibility |
| `guidance_scale` | number | 1-20 | How closely to follow the prompt (higher = more literal) |
### Image Editing
Use Nano Banana 2 with an input image for inpainting, outpainting, or style transfer:
```
# First upload the source image
upload(file_path: "/path/to/image.png")
# Then generate with image input
generate(
app_id: "fal-ai/nano-banana-2",
input_data: {
"prompt": "same scene but in watercolor style",
"image_url": "<uploaded_url>",
"image_size": "landscape_16_9"
}
)
```
---
## Video Generation
### Seedance 1.0 Pro (ByteDance)
Best for: text-to-video, image-to-video with high motion quality.
```
generate(
app_id: "fal-ai/seedance-1-0-pro",
input_data: {
"prompt": "a drone flyover of a mountain lake at golden hour, cinematic",
"duration": "5s",
"aspect_ratio": "16:9",
"seed": 42
}
)
```
### Kling Video v3 Pro
Best for: text/image-to-video with native audio generation.
```
generate(
app_id: "fal-ai/kling-video/v3/pro",
input_data: {
"prompt": "ocean waves crashing on a rocky coast, dramatic clouds",
"duration": "5s",
"aspect_ratio": "16:9"
}
)
```
### Veo 3 (Google DeepMind)
Best for: video with generated sound, high visual quality.
```
generate(
app_id: "fal-ai/veo-3",
input_data: {
"prompt": "a bustling Tokyo street market at night, neon signs, crowd noise",
"aspect_ratio": "16:9"
}
)
```
### Image-to-Video
Start from an existing image:
```
generate(
app_id: "fal-ai/seedance-1-0-pro",
input_data: {
"prompt": "camera slowly zooms out, gentle wind moves the trees",
"image_url": "<uploaded_image_url>",
"duration": "5s"
}
)
```
### Video Parameters
| Param | Type | Options | Notes |
|-------|------|---------|-------|
| `prompt` | string | required | Describe the video |
| `duration` | string | `"5s"`, `"10s"` | Video length |
| `aspect_ratio` | string | `"16:9"`, `"9:16"`, `"1:1"` | Frame ratio |
| `seed` | number | any integer | Reproducibility |
| `image_url` | string | URL | Source image for image-to-video |
---
## Audio Generation
### CSM-1B (Conversational Speech)
Text-to-speech with natural, conversational quality.
```
generate(
app_id: "fal-ai/csm-1b",
input_data: {
"text": "Hello, welcome to the demo. Let me show you how this works.",
"speaker_id": 0
}
)
```
### ThinkSound (Video-to-Audio)
Generate matching audio from video content.
```
generate(
app_id: "fal-ai/thinksound",
input_data: {
"video_url": "<video_url>",
"prompt": "ambient forest sounds with birds chirping"
}
)
```
### ElevenLabs (via API, no MCP)
For professional voice synthesis, use ElevenLabs directly:
```python
import os
import requests
resp = requests.post(
"https://api.elevenlabs.io/v1/text-to-speech/<voice_id>",
headers={
"xi-api-key": os.environ["ELEVENLABS_API_KEY"],
"Content-Type": "application/json"
},
json={
"text": "Your text here",
"model_id": "eleven_turbo_v2_5",
"voice_settings": {"stability": 0.5, "similarity_boost": 0.75}
}
)
with open("output.mp3", "wb") as f:
f.write(resp.content)
```
### VideoDB Generative Audio
If VideoDB is configured, use its generative audio:
```python
# Voice generation
audio = coll.generate_voice(text="Your narration here", voice="alloy")
# Music generation
music = coll.generate_music(prompt="upbeat electronic background music", duration=30)
# Sound effects
sfx = coll.generate_sound_effect(prompt="thunder crack followed by rain")
```
---
## Cost Estimation
Before generating, check estimated cost:
```
estimate_cost(
estimate_type: "unit_price",
endpoints: {
"fal-ai/nano-banana-pro": {
"unit_quantity": 1
}
}
)
```
## Model Discovery
Find models for specific tasks:
```
search(query: "text to video")
find(endpoint_ids: ["fal-ai/seedance-1-0-pro"])
models()
```
## Tips
- Use `seed` for reproducible results when iterating on prompts
- Start with lower-cost models (Nano Banana 2) for prompt iteration, then switch to Pro for finals
- For video, keep prompts descriptive but concise — focus on motion and scene
- Image-to-video produces more controlled results than pure text-to-video
- Check `estimate_cost` before running expensive video generations
## Related Skills
- `tasteforge-video` — Offline taste distillation and modality planning. Its
endpoint candidates and request manifests are reference-only, not submitted
jobs or saved Fal workflows. A TasteForge handoff does not authorize upload
or generation; use a separately authorized provider workflow and verify its
current endpoint schema before executing.
- `videodb` — Video processing, editing, and streaming
- `video-editing` — AI-powered video editing workflows
- `content-engine` — Content creation for social platforms