audio-music-generate

Audio Music Generate

Overview

Instrumental music / BGM generation (no vocals, no lyrics), supporting multiple styles (jazz/classical/electronic/piano/ambient, etc.) and precise duration control (30–120 seconds). It leans toward ambient/铺垫/background instrumental music, and is not responsible for strong rhythm, strong variation, or complete song structure.

Before execution, the user should be clearly informed that: this Skill will use Meitu OpenAPI credentials, call the local meitu CLI, send the generation request to the Meitu OpenAPI, and write the generated audio file to ./output/ or $VISUAL/output/audio-music-generate/。

API Mapping

• Instrumental music / BGM generation:audio_peanut_generate

Dependencies

• meitu-cli: >=2.0.6
• Credentials：CONFIG AKSK → meitu tools update; EXEC AKSK → actual execution (see root CONFIG.md）
• Environment variables：MEITU_OPENAPI_TOOL_TASK_MODE=command

Path alias:$VISUAL = {OPENCLAW_HOME}/workspace/visual/

Core Workflow

Preflight → Execute → Deliver

Preflight

1. meitu --version ≥ 2.0.6
2. Already ran with CONFIG AKSK meitu tools update
3. Current AKSK = EXEC,MEITU_OPENAPI_TOOL_TASK_MODE=command
4. output_dir：openclaw.yaml → ./output/ ｜else → $VISUAL/output/audio-music-generate/；mkdir -p

Execute

Trigger signals / routing rules

Core dimensions:Instrumental music scenario hit + complete parameters。

Scenario	Judgment keywords	Routing
Instrumental music / BGM / background music	Explicitly request generation of BGM, instrumental music, or background music without vocals	audio_peanut_generate

Single API tool: call when parameters are complete; after a failure, retry once and then return an error; no cross-tool fallback.

Parameter definitions

Parameter	Type	Required	Range	Default	Description
prompt	STRING	Yes	--	--	Instrumental music description (theme/style/scenario/emotion). If missing → prompt "Please describe the music style or scenario you want"
duration	NUMBER	Yes	30–120	30	Generation duration (seconds). If out of range, automatically clamp to 30–120 and inform the user

prompt Organized by the Agent into a structured style/scenario/emotion description.

Tool invocation

meitu audio-music-generate --prompt "<style/scene/mood>" [--duration 30] --json --download-dir {output_dir} --skill_name skill_audio-music-generate

Error degradation

Scenario	Handling method
prompt Missing	Prompt "Please describe the music style or scenario you want", do not call the API
duration Out of 30–120	Automatically clamp, inform the user
User requests >120s	Inform that the maximum is 120s, clamp
audio_peanut_generate Call failed	Retry once; if it still fails, return an error
Style description is vague	Prompt to supplement style/scenario/emotion preferences
Content compliance interception	Directly return a compliance prompt, do not retry

Deliver

• Use the output_dir parsed by Preflight
• From downloaded_files[0].saved_path read the downloaded audio file path
• mv {downloaded_files[0].saved_path} {output_dir}/{YYYY-MM-DD}_{descriptive}_audio-music-generate.mp3

Output

• Format：MP3
• Location: project → ./output/, one-time → $VISUAL/output/audio-music-generate/

Baseline Task ID

See references/task-id-baseline.md for the corresponding row.