# Audio Understanding

> A audio understanding model to analyze audio content and answer questions about what's happening in the audio based on user prompts.


## Overview

- **Endpoint**: `https://fal.run/fal-ai/audio-understanding`
- **Model ID**: `fal-ai/audio-understanding`
- **Category**: audio-to-audio
- **Kind**: inference
**Tags**: utility, audio



## Pricing

- **Price**: $0.01 per 5 seconds

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`audio_url`** (`string`, _required_):
  URL of the audio file to analyze
  - Examples: "https://storage.googleapis.com/falserverless/model_tests/audio-understanding/Title_%20Running%20on%20Fal.mp3"

- **`prompt`** (`string`, _required_):
  The question or prompt about the audio content.
  - Examples: "What is being discussed in this audio?", "What emotions are expressed in this audio?", "What is the main topic of this conversation?"

- **`detailed_analysis`** (`boolean`, _optional_):
  Whether to request a more detailed analysis of the audio
  - Default: `false`



**Required Parameters Example**:

```json
{
  "audio_url": "https://storage.googleapis.com/falserverless/model_tests/audio-understanding/Title_%20Running%20on%20Fal.mp3",
  "prompt": "What is being discussed in this audio?"
}
```


### Output Schema

The API returns the following output format:

- **`output`** (`string`, _required_):
  The analysis of the audio content based on the prompt
  - Examples: "Based on the audio, this appears to be a business meeting discussing quarterly sales results. The speakers are analyzing performance metrics and discussing strategies for the upcoming quarter. The tone is professional and collaborative, with multiple participants contributing to the discussion."



**Example Response**:

```json
{
  "output": "Based on the audio, this appears to be a business meeting discussing quarterly sales results. The speakers are analyzing performance metrics and discussing strategies for the upcoming quarter. The tone is professional and collaborative, with multiple participants contributing to the discussion."
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/fal-ai/audio-understanding \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "audio_url": "https://storage.googleapis.com/falserverless/model_tests/audio-understanding/Title_%20Running%20on%20Fal.mp3",
     "prompt": "What is being discussed in this audio?"
   }'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/audio-understanding",
    arguments={
        "audio_url": "https://storage.googleapis.com/falserverless/model_tests/audio-understanding/Title_%20Running%20on%20Fal.mp3",
        "prompt": "What is being discussed in this audio?"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/audio-understanding", {
  input: {
    audio_url: "https://storage.googleapis.com/falserverless/model_tests/audio-understanding/Title_%20Running%20on%20Fal.mp3",
    prompt: "What is being discussed in this audio?"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/fal-ai/audio-understanding)
- [API Documentation](https://fal.ai/models/fal-ai/audio-understanding/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/audio-understanding)

### fal.ai Platform

- [Platform Documentation](https://docs.fal.ai)
- [Python Client](https://docs.fal.ai/clients/python)
- [JavaScript Client](https://docs.fal.ai/clients/javascript)