Name: zf-kbot Sonic Talking Photo Video Generator API
Brand: magicapi
SKU: api-magicapi-ai-talking-photo-generator-zf-kbot-sonic
Availability: InStock
Author: API Market

Shashank Agarwal

# 🗣️ Talking Photo Video Generator API (zf-kbot Sonic)

## Overview
Sonic, published by zf-kbot, animates a portrait photo so the person speaks along with an audio track. Its developer describes it as turning photos into lifelike talking animations for creating talking-head videos.

Send a portrait `image` and an `audio` file of the voice. The face is cropped from the image when one is detected, and the model returns the URL of one MP4 video of the person talking to that audio.

## Features
- **Photo plus voice in, talking video out**: both `image` and `audio` are required (audio such as WAV or MP3).
- **Movement intensity**: `dynamic_scale` (0.5 to 2, default 1) increases or decreases head and face movement.
- **Quality and speed**: `inference_steps` (5 to 50, default 25); higher values may improve quality but take longer.
- **Resolution**: `min_resolution` (256 to 1024, default 512) sets the processing resolution after cropping. Set `keep_resolution` to `true` to output the original image resolution instead.

## Use Cases
1. **Talking-head videos**: turn a presenter photo and a voice-over into a short spoken clip.
2. **Avatars for courses and explainers**: give a narrator image a voice for lessons and product walkthroughs.
3. **Localized videos**: pair the same portrait with voice tracks in different languages.
4. **Social posts**: animate a profile or character portrait to speak a message.

## Visual Examples
### Example Input
Image:

![Example input: a portrait photo of a person facing the camera](https://blog.api.market/wp-content/uploads/2026/10/ip-adapter-faceid-input-api-market.png)

Audio: [Listen to the example input audio](https://blog.api.market/wp-content/uploads/2026/10/gpt-4o-mini-transcribe-input-v2-api-market.wav)

Settings: `dynamic_scale` `1`, `min_resolution` `512`, `inference_steps` `25`, `keep_resolution` `false`.

### Example Output
[Watch the example output](https://blog.api.market/wp-content/uploads/2026/11/sonic-output-mz2vhr05-api-market.mp4)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes |  |  | Input portrait image (will be cropped if a face is detected) |
| `audio` | string (URL) | Yes |  |  | Input audio file (WAV, MP3, etc.) for the voice |
| `dynamic_scale` | number | No | `1` | 0.5 to 2 | Controls movement intensity. Increase/decrease for more/less movement |
| `min_resolution` | integer | No | `512` | 256 to 1024 | Minimum image resolution for processing. Lower values use less memory but may reduce quality |
| `inference_steps` | integer | No | `25` | 5 to 50 | Number of diffusion steps. Higher values may improve quality but take longer |
| `keep_resolution` | boolean | No | `false` |  | If true, output video matches the original image resolution. Otherwise uses the min_resolution after cropping |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.355 per API unit.
- **1 API unit = 1 successful request with up to 228 seconds of processing.** A longer job bills one more unit for each started block of 228 seconds (for example, 300 seconds of processing is 2 units, $0.71).
- Longer audio and higher `inference_steps` take longer to process.
- **Example cost**: the example request took 124.66 seconds of processing, which is 1 unit, so $0.355.
- **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/ai-talking-photo-generator-zf-kbot-sonic`

### 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`).

A polling interval of 5 seconds and an overall timeout of 1200 seconds (20 minutes) work well. The example took about 4 minutes from request to result, of which 125 seconds were processing.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/ai-talking-photo-generator-zf-kbot-sonic/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "c6d80220ce71d8df04d5dbf2b189b70b9f4937aea6a030de12cb46951b24d134",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/ip-adapter-faceid-input-api-market.png",
      "audio": "https://blog.api.market/wp-content/uploads/2026/10/gpt-4o-mini-transcribe-input-v2-api-market.wav",
      "dynamic_scale": 1,
      "min_resolution": 512,
      "inference_steps": 25,
      "keep_resolution": false
    }
  }'
```

Response (201 Created):
```json
{
  "id": "mz2vhr05asrn80d1mvr9qgx1yc",
  "version": "c6d80220ce71d8df04d5dbf2b189b70b9f4937aea6a030de12cb46951b24d134",
  "status": "starting",
  "created_at": "2026-11-04T14:21:50.294Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/ai-talking-photo-generator-zf-kbot-sonic/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "mz2vhr05asrn80d1mvr9qgx1yc",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/sonic-output-mz2vhr05-api-market.mp4",
  "error": null,
  "created_at": "2026-11-04T14:21:50.294Z",
  "started_at": "2026-11-04T14:23:53.313Z",
  "completed_at": "2026-11-04T14:25:57.968Z"
}
```

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

### 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 `image` or `audio`, or a `dynamic_scale` outside 0.5 to 2.
- **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
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## 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/ai-talking-photo-generator-zf-kbot-sonic";

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: "c6d80220ce71d8df04d5dbf2b189b70b9f4937aea6a030de12cb46951b24d134", 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 = 1200000;
  const pollInterval = 5000;
  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 20 minutes");
}

createAndWaitForPrediction({
  "image": "https://blog.api.market/wp-content/uploads/2026/10/ip-adapter-faceid-input-api-market.png",
  "audio": "https://blog.api.market/wp-content/uploads/2026/10/gpt-4o-mini-transcribe-input-v2-api-market.wav",
  "dynamic_scale": 1,
  "min_resolution": 512,
  "inference_steps": 25,
  "keep_resolution": false
}).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/ai-talking-photo-generator-zf-kbot-sonic"


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": "c6d80220ce71d8df04d5dbf2b189b70b9f4937aea6a030de12cb46951b24d134", "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 = 1200
    poll_interval = 5
    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 20 minutes")


print(create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/ip-adapter-faceid-input-api-market.png",
    "audio": "https://blog.api.market/wp-content/uploads/2026/10/gpt-4o-mini-transcribe-input-v2-api-market.wav",
    "dynamic_scale": 1,
    "min_resolution": 512,
    "inference_steps": 25,
    "keep_resolution": False
}))
```

## FAQ
- **What kind of photo works best?**
  - A portrait with a visible face. The model crops the image to the face when it detects one.
- **Can I make the head move more or less?**
  - Yes. Raise `dynamic_scale` (up to 2) for more movement or lower it (down to 0.5) for less.
- **How much does one video cost?**
  - $0.355 for each started block of 228 seconds of processing. The example took 124.66 seconds, so it cost 1 unit ($0.355). Very long audio or high `inference_steps` can push a job past 228 seconds and into a second unit.
- **Can the output keep my photo's resolution?**
  - Set `keep_resolution` to `true`. By default the video uses `min_resolution` after cropping.
- **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, reach out to us through the chat on the bottom right of the page.


Animate a portrait photo so the person speaks along with your audio track, with adjustable movement and resolution, using Sonic. $0.355 per request of up to 228 seconds of processing, pay as you go.