LiveOvi · speech-aware video generation2 endpoints

Ovi API — Text-to-Video & Image-to-Video

The Ovi API hub combines prompt-driven text-to-video with image-to-video animation. Describe camera movement, action, dialogue, and ambient sound cues in the prompt, or provide a required image_url to guide the starting frame.

Get an Ovi API Key Try Ovi Text to Video Browse Video Models

Ovi Text to VideoPrompt-driven scenes with speech and sound cues1 models

Text to VideoLiveFeatured

Text to Video

Ovi Text to Video

Generate a video from a prompt with cinematic direction, spoken dialogue markup, and ambient-audio captions.

16:9 or 9:16

$0.20/video

Try Model

Ovi Image to VideoAnimate a required source image1 models

Image to VideoLive

Image to Video

Ovi Image to Video

Animate a required source image with a prompt describing camera motion, dialogue, action, and sound cues.

Source image · video output

$0.20/video

Try Model

What is the Ovi API?

Ovi is a two-endpoint video family on Muapi. Text to Video creates a clip from a prompt, while Image to Video requires image_url and uses the prompt to direct movement and performance from that source frame.

Ovi prompts can include dialogue between <S> and <E> markers and ambient sound descriptions between <AUDCAP> and <ENDAUDCAP>. Text to Video accepts 16:9 or 9:16; Image to Video uses the submitted image as its source. Both endpoints cost $0.20 per video generation.

Ovi API capabilities

Prompt-to-video generation

Create video scenes from a text prompt with direction for action, camera, and composition.

Image-guided animation

Start from a required image_url and describe the desired motion and performance.

Dialogue markup

Use <S> and <E> markers in prompts to structure spoken lines.

Ambient-audio cues

Use <AUDCAP> and <ENDAUDCAP> markers to describe environmental sound.

Ovi workflows

Narrated social clips

Generate a vertical or landscape scene with structured dialogue and ambient sound cues.

Talking-character shots

Use Image to Video to animate a supplied character or portrait with prompt-directed performance.

Cinematic concept tests

Prototype camera moves, action, and atmosphere from a concise text brief.

Quick start — Ovi API code examples

Submit an Ovi text-to-video task with your Muapi key, receive a request ID, and poll the shared predictions endpoint for the completed video URL.

1. Submit an Ovi job

curl -X POST https://api.muapi.ai/api/v1/ovi-text-to-video \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A busy railway station. <S>Attention: the express is now boarding.<E> <AUDCAP>Train whistle and crowd murmur<ENDAUDCAP>","aspect_ratio":"16:9"}'

# Response: {"request_id":"REQUEST_ID"}

The example calls Text to Video with dialogue and ambient-audio markup plus a 16:9 aspect ratio. Switch to ovi-image-to-video and include image_url for image-guided animation.

2. Poll the result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

Poll until the task completes, then read the generated video URL from the result response.

Ovi API FAQ

Which Ovi endpoints are available?

Muapi lists ovi-text-to-video for prompt-driven generation and ovi-image-to-video for animation from a required source image.

What inputs does Ovi Image to Video require?

It requires both prompt and image_url. The prompt describes the motion, camera, dialogue, and sound cues for the generated clip.

Which aspect ratios does Ovi Text to Video support?

Text to Video supports 16:9 and 9:16, with 16:9 as the schema default. Image to Video does not expose an aspect_ratio field.

How do I add speech or ambient sound direction?

Use <S> and <E> around spoken dialogue, and <AUDCAP> and <ENDAUDCAP> around ambient sound descriptions in the prompt.

How is Ovi priced?

Both Ovi endpoints cost $0.20 per video generation.

Compare AI video APIs →See Ovi beside every video-generation family on Muapi.Browse text-to-video models →Compare Ovi Text to Video with other prompt-driven video endpoints.Browse image-to-video models →Compare Ovi Image to Video with other image animation workflows.Explore avatar and lipsync APIs →Compare speech-aware Ovi prompts with dedicated lipsync and avatar endpoints.Read the API docs →Learn Muapi's authentication, submit, and polling flow.

Build with Ovi

Connect prompt-driven and image-guided video generation through one Muapi API key and a shared asynchronous workflow.

Get an API Key Try Ovi