AI Video with AI Voice

Create AI-narrated videos with generated or uploaded media. 8.9M views, trending template.

When to Use This Template

• You have a script or topic and want Blotato to generate a full video with AI images, voiceover, and captions

• You want to create faceless story videos, educational explainers, or narrated content without filming yourself

• You are making content for TikTok, Instagram Reels, or YouTube Shorts and need AI to handle image generation and voiceover

• You want to upload your own media for some scenes and use AI-generated images for others (hybrid approach)

• Use advanced options to control the exact image prompt and voiceover script per scene

Template Information

Property	Value
Template ID	/base/v2/ai-story-video/5903fe43-514d-40ee-a060-0d6628c5f8fd/v1
Output Type	Video
Category	AI Videos

Parameters

Parameter	Type	Required	Default	Description
scenes	array	Yes	-	Scene objects. Min: 1, Max: 20
scenes[].mediaSource	union	Yes	-	Upload video URL or AI prompt for image generation
scenes[].script	string	Yes	-	Voiceover text for this scene
enableVoiceover	boolean	No	true	Generate voiceover audio
voiceName	enum	No	Brian (American, deep)	ElevenLabs voice. See voice options below
aiImageModel	enum	No	fal-ai/nano-banana	AI model for image generation. See values below
animateAiImages	boolean	No	false	Convert AI images to animated videos
captionPosition	enum	No	center	Values: top, center, bottom
highlightColor	color	No	#FFFF00	Highlighted word color in captions
transition	enum	No	none	Values: none, fade, slide, zoom
aspectRatio	enum	No	9:16	Values: 16:9, 1:1, 4:5, 9:16
trimToVoiceover	boolean	No	true	Trim video to match voiceover duration

Available AI Image Models

Pass one of these values as aiImageModel to control which AI model generates your images. Each model has a different credit cost. See AI Video Credits for pricing.

Value	Label	Credits/Image
replicate/black-forest-labs/flux-schnell	Cheapest	1
replicate/black-forest-labs/flux-dev	Good	10
replicate/black-forest-labs/flux-1.1-pro	Great	15
replicate/black-forest-labs/flux-1.1-pro-ultra	Best for Images	20
replicate/recraft-ai/recraft-v3	Best for Realistic Image	15
replicate/ideogram-ai/ideogram-v2	Best for Text	30
replicate/luma/photon	Good	10
openai/gpt-image-1	OpenAI GPT Image	25
openai/gpt-image-2	OpenAI GPT Image 2	25
fal-ai/nano-banana	Nano Banana (default)	15
fal-ai/nano-banana-pro	Nano Banana Pro	50
fal-ai/nano-banana-2	Nano Banana 2	30
fal-ai/bytedance/seedream/v4.5/text-to-image	Seedream v4.5	15

Available Voices

Alice (British, confident), Aria (American, expressive), Bill (American, trustworthy), Brian (American, deep), Callum (Transatlantic, intense), Charlie (Australian, natural), Charlotte (Swedish, seductive), Chris (American, casual), Daniel (British, authoritative), Eric (American, friendly), George (British, warm), Jessica (American, expressive), Laura (American, upbeat), Liam (American, articulate), Lily (British, warm), Matilda (American, friendly), River (American, confident), Roger (American, confident), Sarah (American, soft), Will (American, friendly)

Example 1: AI-Powered with Prompt

POST https://backend.blotato.com/v2/videos/from-templates
Content-Type: application/json
blotato-api-key: YOUR_API_KEY

{
  "templateId": "/base/v2/ai-story-video/5903fe43-514d-40ee-a060-0d6628c5f8fd/v1",
  "inputs": {},
  "prompt": "Create a 3-scene video about the history of coffee, from ancient Ethiopia to modern cafes",
  "render": true
}

Example 2: Manual Inputs

POST https://backend.blotato.com/v2/videos/from-templates
Content-Type: application/json
blotato-api-key: YOUR_API_KEY

{
  "templateId": "/base/v2/ai-story-video/5903fe43-514d-40ee-a060-0d6628c5f8fd/v1",
  "inputs": {
    "scenes": [
      {
        "mediaSource": "A serene winter landscape with snow-covered mountains and a frozen lake",
        "script": "Welcome to this amazing journey. Let me show you something incredible."
      },
      {
        "mediaSource": "A golden retriever playing happily in a sunny meadow",
        "script": "Every moment is an opportunity to create something beautiful."
      },
      {
        "mediaSource": "A cozy coffee shop interior with warm lighting and books",
        "script": "And remember, the best stories are yet to be told."
      }
    ],
    "voiceName": "Brian (American, deep)",
    "captionPosition": "center",
    "highlightColor": "#FFFF00",
    "transition": "fade",
    "aspectRatio": "9:16"
  },
  "render": true
}

Example 3: Hybrid with Custom Voice

POST https://backend.blotato.com/v2/videos/from-templates
Content-Type: application/json
blotato-api-key: YOUR_API_KEY

{
  "templateId": "/base/v2/ai-story-video/5903fe43-514d-40ee-a060-0d6628c5f8fd/v1",
  "inputs": {
    "voiceName": "Alice (British, confident)",
    "captionPosition": "bottom",
    "highlightColor": "#00FF00",
    "animateAiImages": true,
    "aspectRatio": "1:1"
  },
  "prompt": "Create a 4-scene video about the benefits of meditation for busy professionals",
  "render": true
}

Example 4: Mixed Media Sources

POST https://backend.blotato.com/v2/videos/from-templates
Content-Type: application/json
blotato-api-key: YOUR_API_KEY

{
  "templateId": "/base/v2/ai-story-video/5903fe43-514d-40ee-a060-0d6628c5f8fd/v1",
  "inputs": {
    "scenes": [
      {
        "mediaSource": "https://example.com/my-uploaded-video.mp4",
        "script": "Here is my introduction using uploaded footage."
      },
      {
        "mediaSource": "A futuristic cityscape with flying cars and neon lights",
        "script": "Now imagine what the future could look like."
      }
    ],
    "voiceName": "Daniel (British, authoritative)",
    "aspectRatio": "16:9"
  },
  "render": true
}

Related Templates

• AI Selfie Talking Video

• AI Avatar with AI Generated B-roll

• Combine Clips and Apply Basic Edits

See Also

• Create Visual API Reference

• Voice IDs Reference

• All Visual Templates