L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

veo-3-fast

veo-3-fast

Google Veo 3 | Fast. Generate videos with audio from text prompts using Google Veo 3 Fast. Fast AI video generation with built-in audio. Triggers: veo 3 fast, google video fast, fast text to video, veo fast, google veo 3, video generation fast, veo text to video

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: veo-3-fast description: "Google Veo 3 | Fast. Generate videos with audio from text prompts using Google Veo 3 Fast. Fast AI video generation with built-in audio. Triggers: veo 3 fast, google video fast, fast text to video, veo fast, google veo 3, video generation fast, veo text to video" allowed-tools: Bash(curl *), WebFetch

Google Veo 3 | Fast

Generate videos with optional audio from text prompts using Google Veo 3 Fast. A speed-optimized variant of Veo 3 that produces high-quality videos with built-in audio generation, prompt enhancement, and multiple duration options.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo-3-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "A chef preparing sushi in a traditional Japanese restaurant, close-up of hands slicing fish, ambient restaurant sounds",
      "aspect_ratio": "16:9",
      "duration": "8s",
      "generate_audio": true
    }
  }'

Parameters

ParameterTypeDefaultDescription
aspect_ratiostring16:9Aspect ratio. Options: 16:9, 9:16
auto_fixbooleanfalseAutomatically attempt to fix prompts that fail content policy
durationstring8sVideo duration. Options: 4s, 6s, 8s
enhance_promptbooleantrueWhether to enhance the prompt for better results
generate_audiobooleantrueWhether to generate audio with the video
negative_promptstring-Text describing what to avoid
promptstring-Text prompt for video generation
resolutionstring720pVideo resolution. Options: 720p, 1080p
seedinteger-Random seed for reproducible results

Examples

Cinematic scene with audio:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo-3-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "A thunderstorm rolling over a countryside farm, lightning flashing, rain pouring down on the barn roof",
      "duration": "8s",
      "aspect_ratio": "16:9",
      "resolution": "1080p",
      "generate_audio": true
    }
  }'

Short vertical clip for social media:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo-3-fast",
    "version": "0.0.1",
    "input": {
      "prompt": "A barista pouring latte art into a coffee cup, smooth milk swirl, cafe ambiance",
      "duration": "4s",
      "aspect_ratio": "9:16",
      "negative_prompt": "blurry, low quality, distorted",
      "seed": 5678
    }
  }'

Related Models

Documentation

Skills enregistrées