# Hedra Character-3 · Talking Avatar Video

Make a talking video from a photo and audio with Hedra Character-3 · Talking Avatar Video through one Spiral API key. Animates the face in a still image to speak along with an audio track, making a talking video of up to 10 minutes at up to 1080p. It runs in the background and returns video. Pay as you go, with no subscription.

- Provider: Hedra
- Category: Video
- Runs: In the background
- Returns: video
- Released: 2025-03-06
- Tool id: `hedra` / `hedra-character-3`
- Page: https://spiral.ai/tools/hedra/hedra-character-3

## Pricing

$0.065 per second at 720p ($0.0325 at 540p, $0.0813 at 1080p), for the audio's length.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 1 hour
- Longest run, end to end: 310 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `audio` (required) | JSON |  | — | Driving audio, a single speaker: `{"source": "url", "url": "https://…"}`, 0.5 s to 600 s and at most 104.8 MB. The video runs as long as the audio. |
| `prompt` (required) | text |  | Generate a realistic talking avatar video with lip sync | Generation prompt. |
| `resolution` (required) | one of | 540p, 720p, 1080p | 720p | Output resolution. |
| `start_image` (required) | JSON |  | — | Start frame (the face to animate): `{"source": "url", "url": "https://…"}`. At most 10.4 MB. |
| `aspect_ratio` (required) | one of | 1:1, 4:3, 3:4, 16:9, 9:16, 9:21, 21:9 | 9:16 | Output aspect ratio. |
| `duration_ms` | number (whole) | … to 600000 | — | Duration in ms. At most 600000. |
| `bounding_box_target` | JSON |  | — | Speaker position in the start frame, as normalized [x, y] image coordinates (0-1 from the top-left); selects who speaks in a frame with several people. |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "hedra",
    "model": "hedra-character-3",
    "input": {
      "audio": {
        "url": "<url>",
        "source": "url"
      },
      "prompt": "Generate a realistic talking avatar video with lip sync",
      "resolution": "720p",
      "start_image": {
        "url": "<url>",
        "source": "url"
      },
      "aspect_ratio": "9:16"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=hedra&model=hedra-character-3

## Common questions

### Hedra Character-3 · Talking Avatar Video

**How much does Hedra Character-3 · Talking Avatar Video cost?**

$0.065 per second at 720p ($0.0325 at 540p, $0.0813 at 1080p), for the audio's length. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Hedra Character-3 · Talking Avatar Video through an API?**

Send `POST /v1/runs` with `"provider": "hedra"`, `"model": "hedra-character-3"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with Hedra to use Hedra Character-3 · Talking Avatar Video?**

No. Spiral runs it on its own Hedra account and charges your Spiral balance.

**Can my AI agent use Hedra Character-3 · Talking Avatar Video?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

