;
## Overview
Generate royalty-free sound effects or music from natural language descriptions. Describe what you want to hear and get audio output.
### Listen to Examples
### Prerequisites
Sign up at [CAMB.AI Studio](https://studio.camb.ai) if you haven't already.
Go to **Settings → API Keys** in Studio and copy your key. See [Authentication](/getting-started/authentication) for details.
```bash Python theme={null}
pip install camb-sdk
```
```bash TypeScript theme={null}
npm install @camb-ai/sdk
```
Skip this step if you're using the [direct API](/tutorials/direct-api).
```bash theme={null}
export CAMB_API_KEY="your_api_key_here"
```
***
## Code
```python Python theme={null}
import os
import time
from camb.client import CambAI, save_stream_to_file
client = CambAI(api_key=os.getenv("CAMB_API_KEY"))
def generate_sound():
# Create sound effect from text prompt
# audio_type: "sound" for effects, "music" for music
response = client.text_to_audio.create_text_to_audio(
prompt="Sword clashing against a metal shield in a medieval battle",
duration=3.0,
audio_type="sound"
)
task_id = response.task_id
print(f"Task created: {task_id}")
# Poll for completion
while True:
status = client.text_to_audio.get_text_to_audio_status(task_id=task_id)
print(f"Status: {status.status}")
if status.status == "SUCCESS":
result = client.text_to_audio.get_text_to_audio_result(status.run_id)
save_stream_to_file(result, "sound_effect.wav")
print("Saved to sound_effect.wav")
break
elif status.status == "FAILED":
print("Task failed!")
break
time.sleep(2)
generate_sound()
```
```javascript TypeScript theme={null}
import { CambClient, saveStreamToFile } from '@camb-ai/sdk';
const client = new CambClient({
apiKey: process.env.CAMB_API_KEY
});
async function generateSound() {
// Create sound effect from text prompt
// audio_type: "sound" for effects, "music" for music
console.log('Creating sound effect...');
const response = await client.textToAudio.createTextToAudio({
prompt: 'Sword clashing against a metal shield in a medieval battle',
duration: 3.0,
audio_type: 'sound'
});
const taskId = response.task_id;
console.log(`Task created: ${taskId}`);
// Poll for completion
while (true) {
const status = await client.textToAudio.getTextToAudioStatus({
task_id: taskId
});
console.log(`Status: ${status.status}`);
if (status.status === 'SUCCESS') {
const result = await client.textToAudio.getTextToAudioResult({
run_id: status.run_id
});
await saveStreamToFile(result, 'sound_effect.wav');
console.log('Saved to sound_effect.wav');
break;
} else if (status.status === 'FAILED') {
console.log('Task failed!');
break;
}
await new Promise(r => setTimeout(r, 2000));
}
}
generateSound();
```
***
## Parameters
| Parameter | Description | Values |
| ------------ | --------------------------------------------- | ---------------------- |
| `prompt` | Natural language description of desired audio | Any text |
| `duration` | Length of audio in seconds | `1.0` - `30.0` |
| `audio_type` | Type of audio to generate | `"sound"` or `"music"` |
***
## Use Cases
***
## Next Steps
Generate speech from text using the SDK.
Speak in 140+ language accents with the same voice.
Clone a voice from reference audio.
Full Text-to-Sound API specification.