# Alibaba Wan 2.2 Speech to Video API

> Wan 2.2 Speech to Video turns a portrait image and a speech audio into a talking video guided by a prompt.

Source: https://www.sandbase.ai/models/alibaba/wan/2.2/speech-to-video
API reference: https://www.sandbase.ai/models/alibaba/wan/2.2/speech-to-video/docs

## Facts

- Provider: Alibaba
- Type: Video model
- Model ID: `alibaba/wan/2.2/speech-to-video`
- Price: From $1 per run
- Capabilities: audio to video
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Unified Run API: `POST https://api.sandbase.ai/v1/run`

```bash
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/wan/2.2/speech-to-video",
  "audio": "https://static.sandbase.ai/examples/alibaba/wan/2.2/speech-to-video/input_audio_1.wav",
  "image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/speech-to-video/input_image_0.png",
  "prompt": "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard.",
  "num_frames": 80,
  "resolution": "720p"
}'
```

The response returns a run id; poll `GET https://api.sandbase.ai/v1/run/{id}` until the status is `completed` or `failed`.

## FAQ

### How do I call Alibaba Wan 2.2 Speech to Video through SandBase?

Create a SandBase API key, then send requests with the model ID "alibaba/wan/2.2/speech-to-video" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### Do I need a separate Alibaba account?

No. One SandBase API key and balance gives you access to Alibaba Wan 2.2 Speech to Video and the other models in the catalog; you do not need to sign up with Alibaba separately.

## README

### Wan 2.2 Speech to Video

Turn a portrait and a speech track into a talking video. Wan 2.2 lip-syncs the face in `image` to `audio` and animates head and body movement; the prompt sets the scene and gestures.

#### Fields

| Field | Type | Default | Notes |
|---|---|---|---|
| `prompt` | string, required | — | Text instruction. |
| `image` | image URL, required | — | Portrait to animate. JPEG, PNG, or WebP URL. |
| `audio` | audio URL, required | — | Speech track (WAV/MP3) that drives the lips. |
| `num_frames` | integer 40–120 | 80 | Frames to generate (40–120, 16 frames per second of video). |
| `resolution` | `480p` / `580p` / `720p` | `720p` | Sets the rate. |
| `negative_prompt` | string | — | What to avoid. |
| `seed` | integer 0–2147483647 | random | Fix it to compare prompt changes. |

#### Billing

Billed per output second at the upstream rate: $0.10 at 480p, $0.15 at 580p, $0.20 at 720p. The default 80 frames is 5 seconds.

| Output | 480p | 580p | 720p |
|---|---|---|---|
| 80 frames (5s, default) | $0.50 | $0.75 | $1.00 |
| 120 frames (7.5s) | $0.75 | $1.125 | $1.50 |

Failed runs are not charged.

#### Prompting

- Describe gestures and setting; the lips follow the audio automatically.
- Use a front-facing portrait with the mouth clearly visible.

#### Limits

- Up to 120 frames (7.5 seconds) per request.

#### Also on SandBase

Other Wan 2.2 endpoints: `alibaba/wan/2.2/animate/move`, `alibaba/wan/2.2/animate/replace`.