EmpirioLabs AI Music
Generate music and sound effects with EmpirioLabs AI from a text description, with optional lyrics on models that sing, wait for the result, and save the audio file. Use when the user asks to compose a song, a backing track, a jingle, or a film score, to create a sound effect or ambience, or to check on an audio job that is still running. Runs a bundled Python script that picks a model from the live catalog (or the one you name) and saves the file to the path you choose.
EmpirioLabs AI music and sound generation
Make music and sound effects from a description with the EmpirioLabs AI audio generation API. The bundled script submits the request, waits until the audio is ready, and saves the file. To read text aloud, use the empiriolabs-speech skill instead.
Setup
- Create an API key at https://platform.empiriolabs.ai/dashboard/api-keys. Keys start with
sk-empiriolabs-. - Make the key available as
EMPIRIOLABS_API_KEYin the environment where commands run. Never paste the key into a prompt or a file in the project. - Python 3.8 or later. There is nothing to install.
Script paths below are relative to this skill's folder. On Windows, use python instead of python3.
Make a track
python3 scripts/music.py "an upbeat synthwave track with a driving bassline" --duration 30 --out ./audio/track.mp3
The file extension in --out selects the audio format when the model offers it (.mp3, .wav, .flac, .ogg). The script prints progress to stderr, then a JSON summary:
{
"model": "MODEL_ID",
"job_id": "...",
"files": ["/home/me/project/audio/track.mp3"],
"urls": ["https://media.empiriolabs.ai/..."]
}
Sing lyrics
On models that take lyrics, pass them as text or from a file:
python3 scripts/music.py "a gentle folk song with acoustic guitar" --lyrics-file ./lyrics.txt --out ./audio/song.mp3
Make a sound effect
Choose a sound effect model with --list-models, then describe the sound:
python3 scripts/music.py "footsteps on gravel, then a door closing" --model MODEL_ID --duration 5 --out ./audio/steps.wav
Long jobs
python3 scripts/music.py "a film score that swells slowly" --no-wait # prints the job id
python3 scripts/music.py --job-id JOB_ID --out ./audio/score.mp3 # waits, then downloads
If --timeout (default 1800 seconds) runs out, the job keeps running. The script exits with code 3 and prints the --job-id command that resumes it.
Options
| Option | Meaning |
|---|---|
--model ID | Use a specific model. |
--lyrics TEXT / --lyrics-file FILE | Lyrics to sing, on models that take them. |
--duration N | Length in seconds. Supported values depend on the model. |
--param key=value | Any other model parameter, for example --param seed=7. |
--out PATH | File or directory to save to (default: current directory). |
--no-wait | Submit the job, print its id, and exit. |
--job-id ID | Wait for an earlier job and download its result. |
--no-download | Print the hosted URL without saving the file. |
--overwrite | Replace an existing file. By default a numeric suffix is added instead. |
Choose a model and check prices
Audio is billed per generated second or per request, depending on the model. Check before long runs, and confirm costly runs with the user:
python3 scripts/music.py --list-models
* marks the model used when --model is omitted. For a model's durations, formats, and other parameters, use the empiriolabs-models skill (models.py --show MODEL_ID).
Exit codes and errors
0success,1the request failed (the message says why),2invalid arguments,3still running when--timeoutran out.HTTP 401: the key is missing or invalid.HTTP 402: add credits at https://platform.empiriolabs.ai/dashboard/billing.
Other ways to connect
The same models are available through the EmpirioLabs AI remote MCP server at https://mcp.empiriolabs.ai/mcp (OAuth sign-in, or the API key as a bearer token). Setup: https://docs.empiriolabs.ai/mcp. API reference: https://docs.empiriolabs.ai.
Related skills
- Downloads
- Security audit
- Review
- Last updated
- 2d ago
- Current version
- v1.0.0
- License
- MIT-0
