name: film-sound-design description: "Generate and assemble music and sound effects for a supplied video sequence."

Film Sound Design

Generate and assemble music and sound effects for a supplied video sequence.

Required Aident Actions

<action-tag>direct:fal:fal_text_to_audio</action-tag> (required inputs: inspect the current schema): Run an active Fal text-to-music and sound generation model. Defaults to fal-ai/stable-audio-25/text-to-audio. Call fal_list_text_to_audio_models before selecting another model to inspect current pricing, required...
<action-tag>api:minimax:music_generation</action-tag> (required inputs: actionName, model): Use generate_music with a prompt and lyrics for a song, or generate_lyrics to create or continue lyrics. Paid music and lyrics actions can use the reviewed platform credential; free model variants remain available....
<action-tag>composio:shotstack_tools:shotstack_render_video</action-tag> (required inAction · Text To Audio render job. Use when you have defined a timeline and output settings and want to start rendering.
<action-tag>composio:shotstack_tools:shotstack_get_render_status</action-tag> (required inputs: id): Tool to retrieve the current status and details of a Shotstack rAction · Music Generationil done or failed, typically after creating a render with SHOTSTACK_RENDER_VIDEO.

Use Aident Loadout to read the current Action schema before constructing inputs. Check the required integration connection in Aident Vault. If an Action is billable or mutatingAction · Render Video, and wait for explicit user confirmation before execution.

Workflow

Confirm the requested outcome, source material, destination, audience, constraints, and acAction · Get Render Statuscrete plan. Resolve ambiguity before invoking an Action.
Select only the Aident Actions whose documented effect directly advances the requested outcome. Do not invoke every listed Action by default.
Inspect the current schema and prepare the minimum valid input for each selected Action.
Preflight each selected Action. Execute it only after any required confirmation, in dependency order, and carry returned IDs or asset URLs into later steps.
Verify the returned IDs, URLs, statuses, or artifacts against the acceptance criteria. Report partial completion precisely and do not repeat paid or mutating calls blindly.

Source-Derived Guidance

Collect the video asset, story beats, dialogue constraints, desired emotional arc, duration, and rights requirements.
Create a timed sound plan that prioritizes dialogue, story-critical sounds, music, ambience, and accents.
Use direct:fal:fal_text_to_audio for approved effects and api:minimax:music_generation for the reviewed music bed.
Use composio:shotstack_tools:shotstack_render_video to align and mix the generated audio with the supplied video.
Verify synchronization, dialogue intelligibility, peaks, transitions, duration, and playback.

Execution Boundaries

Treat upstream provider-specific commands as background knowledge only. Execute the workflow through the exact Aident Actions above.
Never request raw credentials in chat. Use Aident Vault connection flows for required accounts.
Preserve user-provided wording, brand constraints, rights restrictions, and target identifiers. Do not invent authorization.
Pass assets by Aident asset ID or supported URL fields. Do not expose caller-local filesystem paths to hosted Actions.
After Shotstack accepts a render, pass its returned ID to composio:shotstack_tools:shotstack_get_render_status at moderate intervals until a terminal state. Return a video URL only after the render completes.
Stop when a required integration is disconnected, preflight rejects the input, the target is ambiguous, or the user declines a required confirmation.

Output

Return the execution plan, selected Action names, confirmed targets, Aident result identifiers or asset URLs, verification evidence, and any remaining blocked step.

Attribution

This Skill adapts the reviewed upstream workflow. See for the pinned source and for the preserved license.

Works with