Name: Ovi Image-to-Video with Audio API
Brand: magicapi
SKU: api-magicapi-image-to-video-generator-character-ai-ovi-i2v
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎥 Image-to-Video with Audio Generator API (Ovi)

## Overview
Ovi is a model from Character.AI that generates a video with audio from an image and a text prompt. You send the starting `image` and describe the motion, speech and sound in `prompt`. Each request returns the URL of one MP4 video.

Separate negative prompts for the picture (`video_negative_prompt`) and the sound (`audio_negative_prompt`) let you steer away from common artifacts.

## Features
- **Image-to-video with audio**: one call returns a video with a generated soundtrack.
- **Prompt-driven motion and sound**: describe what happens, what is said and what is heard in `prompt`.
- **Video negative prompt**: defaults to `jitter, bad hands, blur, distortion`.
- **Audio negative prompt**: defaults to `robotic, muffled, echo, distorted`.
- **Seed**: set a seed to reproduce a result.

## Use Cases
1. **Talking characters**: animate a portrait or character image that speaks a short line.
2. **Social clips**: short videos with sound from a single still for posts and ads.
3. **Product and brand intros**: bring a mascot or spokesperson image to life with a spoken tagline.
4. **Prototyping scenes**: test a shot with motion and ambient sound before full production.

## Visual Examples
### Example Input
Image (`image`):

![Input image: a woman in a yellow raincoat under a glowing pink neon sign on a rainy night street](https://blog.api.market/wp-content/uploads/2026/10/p-video-avatar-input-api-market.webp)

Prompt: "A woman in a yellow raincoat stands under a glowing pink neon sign on a rainy night street, smiles at the camera and says <S>Every AI model you need, one API key away.<E> She glances up at the sign as rain falls softly around her. <AUDCAP>Clear, warm female voice, gentle rain and a distant city hum.<ENDAUDCAP>"

The prompt marks the spoken line between `<S>` and `<E>` and describes the soundtrack between `<AUDCAP>` and `<ENDAUDCAP>`. All other fields were left at their defaults.

### Example Output
[Watch the example output](https://blog.api.market/wp-content/uploads/2026/10/ovi-i2v-output-api-market.mp4)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Prompt for the generated video |
| `image` | string (URL) | Yes |  |  | Input image to generate the video from |
| `seed` | integer | No | none |  | Random seed. Set for reproducible generation |
| `video_negative_prompt` | string | No | `jitter, bad hands, blur, distortion` |  | Negative prompt for video generation |
| `audio_negative_prompt` | string | No | `robotic, muffled, echo, distorted` |  | Negative prompt for audio generation |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.25 per API unit.
- **1 API unit = 1 output video.** Each request returns one video, so each successful request costs $0.25, including the example above.
- There are no duration or resolution inputs, so every request is billed the same.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/image-to-video-generator-character-ai-ovi-i2v`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

Video generation takes longer than image generation. A polling interval of 2 seconds and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/image-to-video-generator-character-ai-ovi-i2v/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "8a2539bdbc0721aba314c6eed8481ca48ede9f25c37535669526e5e64fddd966",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/p-video-avatar-input-api-market.webp",
      "prompt": "A woman in a yellow raincoat stands under a glowing pink neon sign on a rainy night street, smiles at the camera and says <S>Every AI model you need, one API key away.<E> She glances up at the sign as rain falls softly around her. <AUDCAP>Clear, warm female voice, gentle rain and a distant city hum.<ENDAUDCAP>"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "6sg4y601f9rmw0d17fqs02m3k4",
  "version": "8a2539bdbc0721aba314c6eed8481ca48ede9f25c37535669526e5e64fddd966",
  "status": "starting",
  "created_at": "2026-10-14T19:41:21.777Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/image-to-video-generator-character-ai-ovi-i2v/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "6sg4y601f9rmw0d17fqs02m3k4",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/ovi-i2v-output-api-market.mp4",
  "error": null,
  "created_at": "2026-10-14T19:41:21.777Z",
  "started_at": "2026-10-14T19:41:22.777Z",
  "completed_at": "2026-10-14T19:43:01.777Z"
}
```

`output` is a single URL string pointing to the generated MP4 video with audio.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `prompt` or `image`.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits

All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/image-to-video-generator-character-ai-ovi-i2v";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "8a2539bdbc0721aba314c6eed8481ca48ede9f25c37535669526e5e64fddd966", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 2000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "image": "https://blog.api.market/wp-content/uploads/2026/10/p-video-avatar-input-api-market.webp",
  "prompt": "A woman in a yellow raincoat stands under a glowing pink neon sign on a rainy night street, smiles at the camera and says <S>Every AI model you need, one API key away.<E> She glances up at the sign as rain falls softly around her. <AUDCAP>Clear, warm female voice, gentle rain and a distant city hum.<ENDAUDCAP>"
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/image-to-video-generator-character-ai-ovi-i2v"

def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "8a2539bdbc0721aba314c6eed8481ca48ede9f25c37535669526e5e64fddd966", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])

def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 2
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")

print(create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/p-video-avatar-input-api-market.webp",
    "prompt": "A woman in a yellow raincoat stands under a glowing pink neon sign on a rainy night street, smiles at the camera and says <S>Every AI model you need, one API key away.<E> She glances up at the sign as rain falls softly around her. <AUDCAP>Clear, warm female voice, gentle rain and a distant city hum.<ENDAUDCAP>"
}))
```

## FAQ
- **How do I make the character say something?**
  - Write the line in `prompt` between `<S>` and `<E>`, as in the example. Describe the voice and background sound between `<AUDCAP>` and `<ENDAUDCAP>`.
- **Does the output include sound?**
  - Yes. The model generates a video with audio from your image and prompt.
- **Can I set the video length or resolution?**
  - No. The model has no duration or resolution inputs. Each request returns one video and costs $0.25.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us

If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Generate a video with audio from one image and a text prompt with Ovi from Character.AI, including spoken lines and ambient sound. $0.25 per video.