### Install Sonilo Client

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Install the core library via pip.

```bash
pip install sonilo
```

--------------------------------

### Install and Use Sonilo CLI

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Install the command-line interface wrapper for music and SFX generation.

```bash
pip install sonilo-cli
sonilo text-to-music --prompt "warm lo-fi piano, rain" --duration 30
```

--------------------------------

### Compose with segments

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Defines a composition using contiguous segments with specific start times and prompts.

```python
client.text_to_music.generate(
    prompt="epic trailer",
    duration=60,
    segments=[
        {"start": 0, "prompt": "soft intro", "label": "intro"},
        {"start": 20, "prompt": "building tension", "label": "verse"},
        {"start": 40, "prompt": "full orchestra", "label": "chorus"},
    ],
)
```

--------------------------------

### Configure Ducking and Output Format

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Customize async video-to-music generation with ducking and specific output formats like WAV.

```python
result = client.video_to_music.generate_async(
    video="my_video.mp4",
    preserve_speech=True,
    output_format="wav",
    # ducking defaults on in async — pass ducking=False to disable
)
result.save("track.wav")
if result.ducked:
    result.save("ducked.wav", which="ducked")
```

--------------------------------

### Generate Music from Text

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Initialize the client and generate a music track from a text prompt.

```python
from sonilo import Sonilo

client = Sonilo()  # reads SONILO_API_KEY

track = client.text_to_music.generate(
    prompt="cinematic orchestral score",
    duration=60,
)
track.save("output.mp3")
print(track.title)
```

--------------------------------

### Configure Authentication

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Set the API key via environment variable or pass it directly to the client constructor.

```bash
export SONILO_API_KEY=sk_...
```

```python
client = Sonilo()                  # reads SONILO_API_KEY
client = Sonilo(api_key="sk_...")  # or pass it directly
```

--------------------------------

### client.account.services()

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Retrieves a list of available services for the account.

```APIDOC
## client.account.services()

### Description
Retrieves the list of services available to the current account.

### Method
SDK Method

### Parameters
None
```

--------------------------------

### Generate and stream asynchronously

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Demonstrates asynchronous client usage for both generation and streaming operations.

```python
from sonilo import AsyncSonilo

async with AsyncSonilo() as client:
    track = await client.text_to_music.generate(prompt="lofi", duration=30)
    async for event in client.text_to_music.stream(prompt="lofi", duration=30):
        ...
```

--------------------------------

### client.video_to_sound.generate

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Generates a mixed music bed and sound effects for a video clip, returning the mixed audio.

```APIDOC
## client.video_to_sound.generate

### Description
Generates a mixed music bed and sound effects for a video clip, returning the mixed audio.

### Parameters
- **video_url** (str) - Required - URL of the video.
- **music_prompt** (str) - Required - Description of the music.
- **sfx_prompt** (str) - Required - Description of the sound effects.
- **ducking** (bool) - Optional - Whether to dip music under speech (default: True).
```

--------------------------------

### client.video_to_video_music.generate

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Generates music for a video and returns a re-hosted video with the audio muxed in.

```APIDOC
## client.video_to_video_music.generate

### Description
Generates music for a video and returns a re-hosted video with the audio muxed in.

### Parameters
- **video** (str/bytes/file) - Required - Path, bytes, or open file object of the video.
- **video_url** (str) - Optional - URL of the video.
- **prompt** (str) - Required - Description of the music to generate.
- **preserve_speech** (bool) - Optional - Whether to preserve speech from the source video.
```

--------------------------------

### client.video_to_video_sfx.generate

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Generates sound effects for specific segments of a video and returns a re-hosted video with the audio muxed in.

```APIDOC
## client.video_to_video_sfx.generate

### Description
Generates sound effects for specific segments of a video and returns a re-hosted video with the audio muxed in.

### Parameters
- **video** (str/bytes/file) - Required - Path, bytes, or open file object of the video.
- **segments** (list) - Required - List of dictionaries containing 'start', 'end', and 'prompt' for sound effects.
```

--------------------------------

### Manage manual sound effect tasks

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Manually submits a video-to-sfx task and polls for completion with custom intervals.

```python
task = client.video_to_sfx.submit(
    video="clip.mp4",
    segments=[{"start": 0, "end": 2.5, "prompt": "footsteps on gravel"}],
    audio_format="wav",
)
result = client.tasks.wait(task.task_id, poll_interval=2.0, timeout=600.0)
result.save("audio.wav")  # video-to-sfx returns the generated audio only
```

--------------------------------

### video_to_sfx.submit

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Submits a video-to-sfx generation task.

```APIDOC
## client.video_to_sfx.submit

### Description
Submits a video file for sound effect generation based on segments.

### Parameters
- **video** (str) - Required - Path or identifier for the video file.
- **segments** (list) - Required - List of segments with 'start', 'end', and 'prompt'.
- **audio_format** (str) - Optional - The desired output format (e.g., 'wav').
```

--------------------------------

### Retrieve account services and usage

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Use these methods to check available services and monitor API usage over a specified period.

```python
client.account.services()
client.account.usage(days=7)
```

--------------------------------

### Generate video-to-video music and sound effects

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Use the video_to_video_music and video_to_video_sfx endpoints to generate and mux audio into video files.

```python
music = client.video_to_video_music.generate(
    video="my_video.mp4",  # path, bytes, open file, or use video_url=
    prompt="cinematic orchestral swell",
    preserve_speech=True,
)
music.save("scored.mp4")

sfx = client.video_to_video_sfx.generate(
    video="my_video.mp4",
    segments=[{"start": 0, "end": 2, "prompt": "footsteps on gravel"}],
)
sfx.save("with_sfx.mp4")
```

--------------------------------

### Preserve Speech in Async Video-to-Music

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Use async generation to preserve speech and retrieve separate audio stems.

```python
result = client.video_to_music.generate_async(
    video="my_video.mp4",
    prompt="upbeat",
    preserve_speech=True,  # implies mode="async"; omit mode to let it auto-select
)
result.save("mix.m4a")           # result.audio[0] — the full mix
result.save("vocals.m4a", which="vocals")
result.save("video.mp4", which="mux")  # generated music muxed with the preserved speech
print(result.title.title if result.title else None)
```

--------------------------------

### text_to_sfx.generate

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Generates sound effects synchronously by wrapping submission and polling.

```APIDOC
## client.text_to_sfx.generate

### Description
Submits a sound effect generation request and polls until completion.

### Parameters
- **prompt** (str) - Required - Description of the sound effect.
- **duration** (int) - Required - Duration in seconds.
```

--------------------------------

### client.account.usage(days=7)

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Retrieves the usage statistics for the account over a specified number of days.

```APIDOC
## client.account.usage(days=7)

### Description
Fetches usage data for the account for the specified number of days.

### Method
SDK Method

### Parameters
#### Arguments
- **days** (int) - Optional - The number of days to retrieve usage for. Defaults to 7.
```

--------------------------------

### Generate Music from Video

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Generate music based on a video file or URL.

```python
track = client.video_to_music.generate(video="my_video.mp4", prompt="upbeat")
# or bytes / an open binary file, or a hosted URL:
track = client.video_to_music.generate(video_url="https://example.com/clip.mp4")
```

--------------------------------

### text_to_music.generate

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Generates music based on a prompt, supporting optional segment-based composition.

```APIDOC
## client.text_to_music.generate

### Description
Generates a music track based on the provided prompt and duration. Supports complex compositions using segments.

### Parameters
- **prompt** (str) - Required - The description of the music to generate.
- **duration** (int) - Required - The length of the track in seconds.
- **segments** (list) - Optional - A list of dictionaries defining composition segments with 'start', 'prompt', and 'label'.
```

--------------------------------

### Generate mixed video-to-sound output

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Generate a combined music and sound effect track for a video clip using a single request.

```python
from sonilo import Sonilo

client = Sonilo()

result = client.video_to_sound.generate(
    video_url="https://example.com/clip.mp4",
    music_prompt="uplifting orchestral score",
    sfx_prompt="match the on-screen action",
)
result.save("soundtrack.wav")
```

--------------------------------

### text_to_music.stream

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Streams audio chunks as they are generated.

```APIDOC
## client.text_to_music.stream

### Description
Streams audio generation events. Returns an iterator yielding events with 'type' and 'data' fields.

### Parameters
- **prompt** (str) - Required - The description of the music to generate.
- **duration** (int) - Required - The length of the track in seconds.
```

--------------------------------

### Stream audio chunks

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Processes audio data as it arrives from the server using a synchronous generator.

```python
for event in client.text_to_music.stream(prompt="lofi", duration=30):
    if event["type"] == "audio_chunk":
        handle(event["data"])  # bytes, as they arrive
```

--------------------------------

### Save individual audio stems

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Extract and save individual music or sound effect stems from a generated result.

```python
result.save_stem("music.m4a", which="music")
result.save_stem("sfx.wav", which="sfx")
```

--------------------------------

### Manual Async Task Polling

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Manually submit a task and poll for completion using the task parser.

```python
from sonilo.resources.tasks import parse_music_result

task = client.video_to_music.submit(video_url="https://example.com/clip.mp4", preserve_speech=True)
result = client.tasks.wait(
    task.task_id,
    parser=parse_music_result,  # required: tasks.wait()/get() default to the SFX parser
)
```

--------------------------------

### tasks.wait

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Polls for the completion of an asynchronous task.

```APIDOC
## client.tasks.wait

### Description
Polls a task until it completes, fails, or times out.

### Parameters
- **task_id** (str) - Required - The ID of the task to poll.
- **poll_interval** (float) - Optional - Time in seconds between polls.
- **timeout** (float) - Optional - Maximum time to wait in seconds.
```

--------------------------------

### Generate sound effects

Source: https://github.com/sonilo-ai/sonilo-python/blob/main/README.md

Uses the generate method to submit and poll for sound effect results automatically.

```python
from sonilo import Sonilo

with Sonilo() as client:
    result = client.text_to_sfx.generate(prompt="glass shattering", duration=5)
    result.save("sfx.m4a")
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.