VPick AI Video Creator

VPick Video Creator

All-in-one AI video production studio — from image generation to video creation, voiceover, music, lip-sync, and final export — all on a visual canvas. Powered by VPick.

Security & Data Handling

Prerequisites

1. Sign up at vpick.10xboost.org (Google OAuth — new users get $1 free credit) 2. Get your MCP link: Go to Settings → copy your MCP Server URL (contains your auth token) 3. Add to Claude: Paste the MCP link into Claude settings as a Connector — no install, no API keys needed 4. Top up credits if needed — generation costs are deducted from your VPick balance

Supported Models

Video Generation Models

| Model | Duration | Sound | Cost | MultiShot | Best For | |-------|----------|-------|------|-----------|----------| | Kling 3.0 Standard | 3-10s | Yes | ~$0.30/sec | Yes | MultiShot scenes, character consistency | | Kling 3.0 Professional | 3-10s | Yes | ~$0.405/sec | Yes | Higher quality MultiShot | | Veo 3.1 Fast | 8s fixed | Yes | $0.90/video | No | Quick high-quality clips | | Sora 2 | 10-15s | Yes | $0.525-$0.60 | No | Creative, artistic videos | | Runway 720p/1080p | 5-10s | No | $0.18-$0.45 | No | Fast iteration | | Grok Imagine | 6-15s | Yes | $0.15-$0.60 | No | Budget-friendly with audio | | Midjourney Video | 5s | No | $0.90 | No | Stylized, artistic clips |

Image Generation Models (for references, storyboards, thumbnails)

| Model | Cost | Output | Best For | |-------|------|--------|----------| | nano-banana-2 | $0.16/image | 1 image | Default, fast, multi-reference | | Midjourney (relaxed/fast/turbo) | $0.045-$0.24/grid | 4 images | Artistic, stylized | | Grok Imagine | $0.06/call | 6 images | Bulk, budget | | Seedream 5.0 (Lite/HD) | $0.0825/image | 1 image (2K-3K) | High resolution |

Audio & Voice Models

| Model | Type | Cost | Features | |-------|------|------|----------| | ElevenLabs V3 | Text-to-Speech | $0.21/1000 chars | 29+ voices, multi-language, stability control | | Suno V4.5 | Music Generation | $0.10/song | Custom style, instrumental toggle, vocal gender | | Kling AI Avatar | Lip Sync | $0.12/sec | Face animation from image + audio | | Demucs | Vocal Separation | $0.30/call | Isolate vocals/accompaniment from audio | | ElevenLabs STS v2 | Voice Changer | Free (user API key) | Speech-to-speech, noise removal |

Production Pipeline Overview

VPick covers the entire video production workflow in one place:

Image Gen → Video Gen → Voiceover/Music → Lip Sync → Vocal/Voice Edit → Combine & Export

1. Pre-production: Generate character designs, environments, storyboard frames 2. Video generation: Single shot or MultiShot with character consistency 3. Audio production: Voiceover (ElevenLabs TTS), music (Suno), vocal separation (Demucs), voice changing 4. Lip sync: Animate a face image to speak with generated audio (Kling AI Avatar) 5. Post-production: Combine video clips, mix audio tracks, export final video

Core Workflow

Step 1: Set Up the Canvas

Start by understanding the user's project:

Step 2: Prepare Assets

Create input nodes on the canvas:

Text prompts:

add_node(type: "text", name: "Scene 1 Prompt", data: { content: "A samurai walking through rain, cinematic lighting" })

Reference images (for start/end frames or character consistency):

upload_image(url: "https://example.com/character.jpg")

Generate images first if needed:

run_image_generator(nodeId: "", prompt: "samurai portrait, white background", model: "nano-banana-2")

Step 3: Generate Video

#### Simple Video (Single Shot)

add_node(type: "video-generator", name: "Scene 1")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "text-out", targetHandle: "prompt-in")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "image-out", targetHandle: "start-image-in")
run_video_generator(nodeId: "", model: "kling-3.0", duration: 5, sound: true)

#### MultiShot Video (Multiple Connected Shots — Kling 3.0 Only)

MultiShot generates 3-15 seconds of video with multiple camera angles and character consistency in a single API call.

run_video_generator(
  nodeId: "",
  model: "kling-3.0",
  multiShot: true,
  multiPrompt: [
    { "prompt": "@character walks into frame, wide shot", "duration": 4 },
    { "prompt": "@character looks at camera, medium close-up", "duration": 3 },
    { "prompt": "@character turns away, slow dolly out", "duration": 3 }
  ],
  elements: [
    {
      "name": "character",
      "description": "Main protagonist, male samurai",
      "imageUrls": ["https://.../char-front.jpg", "https://.../char-side.jpg"]
    }
  ],
  sound: true
)

MultiShot Rules:

Step 4: Audio Production

Audio is a core part of video production. VPick supports 5 audio tools:

#### 4a. Voiceover — ElevenLabs Text-to-Speech

Generate natural narration or dialogue from text. 29+ built-in voices, multi-language support.

add_node(type: "audio-generator", name: "Narration")
run_audio_generator(
  nodeId: "",
  prompt: "The samurai stood alone in the rain, waiting for dawn.",
  model: "elevenlabs",
  voiceId: "",
  stability: 0.5
)

You can connect a Text node as input:

connect_nodes(sourceId: "", targetId: "", sourceHandle: "text-out", targetHandle: "text-in")

#### 4b. Music Generation — Suno

Create original background music, theme songs, or jingles.

add_node(type: "music-generator", name: "BGM")
run_music_generator(
  nodeId: "",
  prompt: "epic cinematic orchestral, tension building, dark atmosphere",
  model: "suno",
  instrumental: true,
  style: "cinematic orchestral"
)

Set instrumental: false to include AI-generated vocals with lyrics from the prompt.

#### 4c. Lip Sync — Kling AI Avatar

Animate a character's face to speak with any audio. Turns a still image into a talking head video.

add_node(type: "lipsync-generator", name: "Talking Character")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "image-out", targetHandle: "image-in")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "audio-out", targetHandle: "audio-in")
run_lipsync_generator(nodeId: "")

Cost: ~$0.12/sec. Great for dialogue scenes, explainer videos, or virtual presenters.

#### 4d. Vocal Separation — Demucs

Isolate vocals from background music in any audio/video file. Outputs: vocals track, accompaniment track, and original.

add_node(type: "vocal-separator", name: "Separate Audio")
connect_nodes(sourceId: "", targetId: "", ...)
run_vocal_separator(nodeId: "")

Use cases: Extract dialogue from a scene, remove background music, remix audio.

#### 4e. Voice Changer — ElevenLabs Speech-to-Speech

Transform any voice recording into a different voice while preserving speech patterns and emotion.

add_node(type: "voice-changer", name: "New Voice")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "audio-out", targetHandle: "audio-in")
run_voice_changer(nodeId: "", voiceId: "", removeBackgroundNoise: true)

Requires user's own ElevenLabs API key (free, no credit charge).

#### 4f. Audio Mixing

Combine multiple audio tracks (e.g., voiceover + BGM) into one:

add_node(type: "audio-combine", name: "Mixed Audio")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "audio-out", targetHandle: "audio-in")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "audio-out", targetHandle: "audio-in")
run_audio_combine(nodeId: "")

Supports up to 10 audio inputs.

Step 5: Combine & Export

Combine multiple video clips:

add_node(type: "combine", name: "Final Video")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "video-out", targetHandle: "videos-in")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "video-out", targetHandle: "videos-in")
connect_nodes(sourceId: "", targetId: "", sourceHandle: "audio-out", targetHandle: "audio-in")
run_combine(nodeId: "")

Mix audio tracks:

run_audio_combine(nodeId: "")

Step 6: Organize Canvas

Keep the canvas clean:

auto_layout(nodeIds: ["", "", ...], direction: "horizontal", spacing: 200)
create_group(nodeIds: ["", "", ...], overrides: { label: "Scene 1", color: "#4A90D9" })

Workflows (Automated Pipelines)

For repeatable processes, create workflows:

create_workflow(nodes: [...], edges: [...])
run_workflow(workflowId: "")

Checking Results

Tips

Error Handling

| Error | Solution | |-------|----------| | Generation timeout | Auto-retries up to 2 times; check node status with get_node | | Insufficient credits | Prompt user to top up at vpick.10xboost.org | | Element name mismatch | Verify @name in prompts matches element name exactly | | Invalid media format | Videos: MP4 recommended; Images: JPG/PNG | | Node not found | Use list_nodes to get current node IDs |

Documentation

1. Sign up at vpick.10xboost.org (Google OAuth — new users get $1 free credit) 2. Get your MCP link: Go to Settings → copy your MCP Server URL (contains your auth token) 3. Add to Claude: Paste the MCP link into Claude settings as a Connector — no install, no API keys needed 4. Top up credits if needed — generation costs are deducted from your VPick balance