Generate an instrumental music bed via ElevenLabs Music, routed through the GooseWorks proxy, so the call is charged to your GooseWorks credits. Trims any sparse intro, loudnorm, fades the tail. Prompt + length from the template recipe. Use for the music layer of any video-ad format.
Install gooseworks: https://gooseworks.ai/creative-agent/install.md # then, in Claude Code, Cursor, or Codex: /gooseworks use the create-music-elevenlabs skill
Superseded: the video kit now does this with the music-elevenlabs part, version 1.0.2, in the parts folder of this repository. It orders the bed through the private line and levels and fades it the same way. This atom stays, unchanged in behaviour, for skills outside the kit until they move; its scripts still run.
Generate an instrumental music bed via ElevenLabs Music, routed through the GooseWorks proxy, so the call is charged to your GooseWorks credits. Trims any sparse intro, loudnorm, fades the tail. Prompt + length from the template recipe. Use for the music layer of any video-ad format.
gen_music.py --prompt '...' --duration 10 --out music.m4a — charged to your GooseWorks credits; writes a duration-clamped, loudnorm'd bed.
media_proxy.py — never a provider SDK's default host.How ElevenLabs Music behaves, measured on shipped projects. Each note lives here once.
music_length_ms is a suggestion: a 32.9 second request came back 59 seconds, and a stated
ending was ignored. Measure the energy curve, find the natural ending and keep the window that
ends there, so the video closes on the music's own finish.fal-ai/elevenlabs/music with a composition_plan and
respect_sections_durations) the total length holds, but sections snap to bar lines and a
silent section plays at full level. Cut silences in the edit. force_instrumental with a
composition_plan returns 422.music_length_ms is a suggestion:* a 32.9 second request came back 59 seconds, and a statedfal-ai/elevenlabs/music with a composition_plan andResearch supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.
Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.
For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.