Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IRCAM_AMPLIFY_API_KEY | Yes | Your IRCAM Amplify API key from app.ircamamplify.io |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_music | Analyze an audio file to extract genre, mood, tempo, key, and detected instruments. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). Returns structured tags useful for music classification and discovery. |
| separate_stems | Separate an audio file into individual stems: vocals, drums, bass, and other instruments. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). For longer files, returns a job_id for async processing - use check_job_status to monitor progress. |
| detect_ai_music | Detect whether an audio file was generated by AI or created by humans. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). Returns a confidence score (0-100) and classification (ai_generated, human_made, or uncertain). |
| analyze_loudness | Analyze the loudness of an audio file following EBU R128 standard. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). Returns integrated loudness (LUFS), true peak (dB), and loudness range (LU). |
| check_job_status | Check the status of an async processing job. Use this to monitor jobs returned by separate_stems and other async operations. Returns job status (pending, processing, completed, failed), progress percentage, and results when completed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |