AIMusicVideoGen
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FFMPEG_PATH | No | Path to the ffmpeg binary. Set this if ffmpeg is not on your PATH. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_songA | Detect the BPM (tempo), musical key, Camelot code, bar length and duration of a local audio or video file, and find the most energetic 15 s and 30 s windows (usually the chorus or drop, good clips for TikTok, Reels and Shorts). Runs locally with ffmpeg. |
| plan_music_videoA | Build a shot list for a music video where every cut lands on a bar line, with a visual idea per section. Needs only the BPM and duration (get them from analyze_song). Optionally pass the song structure as sections in bars. |
| make_spotify_canvasA | Turn a local video clip or image into a Spotify Canvas: silent 1080x1920 9:16 MP4, 3-8 seconds. Videos are cut from |
| video_specsA | Aspect ratio, resolution, length and format rules for music videos and loops. Platforms: spotify-canvas, tiktok, instagram-reels, youtube-shorts, youtube. |
| create_ai_music_videoA | How to turn a song and one photo of the singer into a finished, lip-synced, beat-cut music video with AIMusicVideoGen (web app, paid credits). Returns the link and the steps; it does not upload anything. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool maps to a distinct stage: analysis (analyze_song), planning (plan_music_video), spec lookup (video_specs), and two creation paths (make_spotify_canvas, create_ai_music_video). The only mild friction is between the two creation tools, since one actually renders a file while the other only returns instructions and a link, but the descriptions make the distinction clear.
Four tools follow a clean verb_noun pattern (analyze_song, plan_music_video, make_spotify_canvas, create_ai_music_video). The lone outlier is video_specs, a bare noun, which is a minor deviation from an otherwise predictable convention.
Five tools is well-scoped for a focused music-video pipeline, with each tool earning its place across analysis, planning, specs, and generation. Nothing feels redundant or padded.
The surface covers a reasonable end-to-end flow: analyze a song, plan cuts, look up platform specs, and produce a Spotify Canvas or kick off full AI video generation. The main gap is that full video rendering is delegated to an external web app rather than produced locally, leaving a partial dead end.