For the complete documentation index, see llms.txt. This page is also available as Markdown.

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

voiceName

enum

No

Brian (American, deep)

ElevenLabs voice. See voice options below

aiImageModel

enum

No

fal-ai/imagen4/preview/fast

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

fal-ai/nano-banana

Nano Banana

15

fal-ai/nano-banana/edit

Nano Banana Edit

15

fal-ai/nano-banana-pro

Nano Banana Pro

50

fal-ai/nano-banana-pro/edit

Nano Banana Pro Edit

50

fal-ai/imagen4/preview/fast

Imagen 4 Fast (default)

7

fal-ai/bytedance/seedream/v4.5/text-to-image

Seedream v4.5

15

fal-ai/bytedance/seedream/v4.5/edit

Seedream v4.5 Edit

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

Example 2: Manual Inputs

Example 3: Hybrid with Custom Voice

Example 4: Mixed Media Sources

See Also

Last updated