## Getting started

### What is a Task?

A Task is a processing job. You provide a media source and one or more model targets — AudioShake processes them asynchronously and returns results for each target. See [Create Task](https://developer.audioshake.ai/api-reference/tasks/create).

### What is a target?

A target specifies which model to run and what output format to produce. You can include up to 20 targets in one Task to generate several outputs from the same file:

```
{
  "assetId": "your_asset_id",
  "targets": [
    { "model": "vocals", "formats": ["wav"] },
    { "model": "instrumental", "formats": ["wav"] },
    { "model": "transcription", "formats": ["json"] }
  ]
}
```

### Should I use a URL or upload a file?

- Use `url` when your media is publicly accessible over HTTPS
- Use `assetId` when your media is local — [upload it first](https://developer.audioshake.ai/api-reference/assets/upload), then reference the returned ID

We recommend uploading files when possible for the most reliable processing.

### What models are available?

AudioShake offers models for instrument stem separation, speech processing, post-production, copyright compliance, and lyric transcription. See the [Models](https://developer.audioshake.ai/models) page for the full list with descriptions and pricing.

### I already have a lyrics transcript. Can I just align it?

Yes. Use the `alignment` model and provide your existing transcript via `transcriptUrl` or `transcriptAssetId`. If no transcript is provided, the model will transcribe automatically.

```
{
  "assetId": "your_asset_id",
  "targets": [
    {
      "model": "alignment",
      "formats": ["json"],
      "transcriptUrl": "https://example.com/lyrics.txt"
    }
  ]
}
```

## Processing

### How do I know when a Task is complete?

Two options:

- **Poll** — call [Get Task by ID](https://developer.audioshake.ai/api-reference/tasks/get) until each target’s `status` is `completed` or `error`. See [Check Task Status](https://developer.audioshake.ai/check-task-status).
- **Webhooks** — receive a POST request each time a target completes. See [Webhooks](https://developer.audioshake.ai/api-reference/tasks/webhooks).

### How long does processing take?

Processing time depends on the media length, number of targets, and current queue load. Most tasks complete within seconds to a few minutes.

### Can I process video files?

Yes. AudioShake accepts MP4 and MOV video files. Only the audio stream is processed — video content is ignored. See [Formats](https://developer.audioshake.ai/api-reference/formats) for all supported input types.

### What happens if a target fails?

Individual targets can fail independently. Check the `status` and `error` fields on each target in the Task response. Other targets in the same Task are not affected.

## Files and formats

### What formats can I upload?

Audio: WAV, AIFF, FLAC, MP3, AAC. Video: MP4, MOV. Maximum file size is 2GB. See [Formats](https://developer.audioshake.ai/api-reference/formats) for the full list.

### What output formats are available?

Audio: `wav`, `mp3`, `flac`, `aiff`. Video: `mp4`. Text: `json`, `srt`, `txt`. See [Formats](https://developer.audioshake.ai/api-reference/formats) for which formats apply to which models.

### How long do uploaded Assets and output files last?

Uploaded Assets expire after 72 hours. Output download links expire after one hour — re-fetch the Task to get fresh links.

## Billing

### How are credits calculated?

Credits are charged per minute of source audio, per target model. Duration is rounded up to the nearest minute. See [Billing & Credits](https://developer.audioshake.ai/billing) for examples and [Models](https://developer.audioshake.ai/models) for per-model rates.

### Do failed Tasks consume credits?

Tasks that fail before processing begins are not charged. If a Task fails mid-processing, contact [support@audioshake.ai](mailto:support@audioshake.ai) with the Task ID.

### Are bulk discounts available?

Yes. Contact [info@audioshake.ai](mailto:info@audioshake.ai) for volume pricing, custom SLAs, and enterprise plans.

## Support

### How do I contact support?

Email [support@audioshake.ai](mailto:support@audioshake.ai). Include your Task ID and the full error message for the fastest resolution.

### Is there a rate limit?

Yes — 60 requests per second. See [Rate Limits](https://developer.audioshake.ai/api-reference/rate-limits).