IMA AI Music & Voice Generator

⚠️ MANDATORY: You MUST read("SKILL-DETAIL.md") (full file — do NOT pass limit parameter) before your first music generation call. It contains the full API payload structure, Suno parameters, error translation tables, reflection mechanism, and UX protocol that this summary omits. Skipping it causes parameter errors and poor user experience.

Model Reference (CRITICAL)

Use exact model_id. Do NOT infer from friendly names.

Model Selection

Suno is the default — most versatile AI music generator with full composition control.

Suno Key Parameters

Prompt tips for AI music composition:

• Genre: "lo-fi hip hop", "orchestral cinematic", "upbeat pop", "jazz"
• Tempo: "80 BPM", "fast tempo", "slow ballad"
• Mood: "happy and energetic", "melancholic", "tense and dramatic"

Knowledge Base (if ima-knowledge-ai installed)

Read before generating: workflow-design.md (video+music coordination), model-selection.md (cost/quality).

Script Usage

# AI music generator — song with Suno (AI song generator, jingle, composition)
python3 {baseDir}/scripts/ima_voice_create.py \
  --api-key $IMA_API_KEY --task-type text_to_music \
  --model-id sonic --prompt "upbeat corporate jingle, 30 seconds" \
  --user-id {user_id} --output-json

# AI BGM generator — background soundtrack
python3 {baseDir}/scripts/ima_voice_create.py \
  --api-key $IMA_API_KEY --task-type text_to_music \
  --model-id GenBGM --prompt "calm ambient background music" \
  --user-id {user_id} --output-json

# List available music models
python3 {baseDir}/scripts/ima_voice_create.py \
  --api-key $IMA_API_KEY --task-type text_to_music --list-models

Sending Results to User

# ✅ CORRECT: Use remote URL for inline audio playback
message(action="send", media=audio_url, caption="✅ 音乐生成成功！\n• 模型：[Name]\n• 耗时：[X]s\n• 积分：[N pts]")

# Then send link for sharing
message(action="send", message=f"🔗 音频链接：\n{audio_url}")

UX Protocol (Brief)

1. Acknowledge: Short reply ("好的！帮你生成音乐 🎵")
2. Pre-gen: Model, time, cost via message tool
3. Progress: Every 10-15s: "⏳ [P]%" (cap 95%)
4. Success: Send media=url + link text
5. Failure: Natural language + suggest alternatives
6. Done: No further action

Generation times: DouBao BGM/Song: 10-25s · Suno: 20-45s

Never expose: script names, API endpoints, attribute_id, technical params.

User Preferences

Storage: ~/.openclaw/memory/ima_prefs.json

• Save on explicit: "用Suno" / "默认用BGM" / "always use Suno"
• Clear on: "推荐一个" / "自动选择"
• Never save auto-selected models

Core Flow

1. GET /open/v1/product/list?category=text_to_music → attribute_id, credit, form_config
2. POST /open/v1/tasks/create → task_id
3. POST /open/v1/tasks/detail → poll every 5s until resource_status==1

MANDATORY: Always query product list first. Missing attribute_id → task fails.

Suno note: model_version inside parameters.parameters must be sonic-v5, outer model_version is sonic.

Environment

Base URL: https://api.imastudio.com

Headers: Authorization: Bearer $IMA_API_KEY · x-app-source: ima_skills · x_app_language: en

⚠️ REMINDER: read("SKILL-DETAIL.md") (full file, no limit) is required before generating music. This summary covers model selection and routing — SKILL-DETAIL.md has complete API payloads, Suno custom_mode details, error handling, reflection mechanism, and UX protocol needed for correct execution.