← 返回 Skills 市场

IMA AI Music Generator — Suno, DouBao

Name: IMA AI Music Generator — Suno, DouBao
Author: allenfancy-gan

作者 allenfancy-gan · GitHub ↗ · v1.0.14 · MIT-0

cross-platform ✓ 安全检测通过

657

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ima-voice-ai

功能描述

Generate voiceovers, narration, and spoken audio for videos, explainers, ads, and social content.

使用说明 (SKILL.md)

IMA Voice AI — Music Generator

For complete API documentation, security details, all parameters, and Python examples, read SKILL-DETAIL.md.

Model ID Reference (CRITICAL)

Use exact model_id from this table. Do NOT infer from friendly names.

Friendly Name	model_id	Notes
Suno	`sonic`	✅ Default, full songs with vocals
DouBao BGM	`GenBGM`	⚠️ Instrumental only, background music
DouBao Song	`GenSong`	⚠️ Songs with vocals

User input aliases: BGM/背景音乐/纯音乐 → GenBGM · 歌曲/人声/Song → sonic or GenSong · 默认 → sonic

Music Generation Mode

User intent	model_id	When to use
Background music, instrumental	`GenBGM`	"做一段BGM" / "纯音乐" / "背景音乐"
Song with vocals	`sonic`	"写首歌" / "带人声" / "歌曲"
Song (alternative)	`GenSong`	"豆包歌曲" / "GenSong"

Model Selection Priority

User preference (if explicitly stated) → highest priority
Fallback default: sonic (Suno)

Task	Default Model	model_id	Notes
General music	Suno	`sonic`	Full songs, vocals
Instrumental/BGM	DouBao BGM	`GenBGM`	No vocals
Chinese songs	DouBao Song	`GenSong`	Alternative to Suno

Script Usage

# Generate music (default: sonic/Suno)
python3 {baseDir}/scripts/ima_voice_create.py \
  --model-id sonic \
  --prompt "upbeat lo-fi hip hop, 90 BPM, no vocals" \
  --output-json

# List available models
python3 {baseDir}/scripts/ima_voice_create.py --list-models

# Generate BGM
python3 {baseDir}/scripts/ima_voice_create.py \
  --model-id GenBGM \
  --prompt "calm piano background music for meditation" \
  --output-json

Sending Results to User

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

# ❌ WRONG: Never download to local file

UX Protocol (Brief)

Pre-generation: "🎵 开始生成音乐… 模型：[Name]，预计[X~Y]秒，消耗[N]积分"
Progress: Every 30-60s: "⏳ 正在生成中… [P]%" (cap at 95%)
Success: Send audio via media=audio_url + include link in caption
Failure: Natural language error + suggest alternative models. See SKILL-DETAIL.md for error translation.

Never say to users: script names, API endpoints, attribute_id, technical parameter names. Only: model name · time · credits · result · status.

Environment

Base URL: https://api.imastudio.com Headers: Authorization: Bearer $IMA_API_KEY · x-app-source: ima_skills · x_app_language: en

Core Flow

GET /open/v1/product/list?app=ima&platform=web&category=text_to_music → get attribute_id, credit, model_version
POST /open/v1/tasks/create → get task_id
POST /open/v1/tasks/detail → poll every 5s until resource_status==1

MANDATORY: Always query product list first. attribute_id is required.

Defaults and Timeouts

Task type: text_to_music (fixed)
Poll interval: 5 seconds
Max poll wait: 8 minutes
Default model: sonic (if --model-id omitted)

Estimated Generation Time

Model	Estimated Time	Poll Every
Suno (sonic)	60~180s	5s
DouBao BGM (GenBGM)	30~90s	5s
DouBao Song (GenSong)	60~120s	5s

安全使用建议

This skill appears to be what it says: a Python client for IMA's text-to-music API that requires one API key. Before installing, verify the publisher/site (imaclaw.ai vs imastudio.com branding mismatch) and confirm you trust that provider. Limit risk by using a scoped/test API key (not a key granting broad account rights), review the provider's data/credit usage and privacy policies, and test with minimal inputs. If you need true TTS voiceovers (speech synthesis) rather than song vocals, confirm the API supports that use case — the script is fixed to a text_to_music task and may not perform general TTS.

功能分析

Type: OpenClaw Skill Name: ima-voice-ai Version: 1.0.14 The IMA Music Generator skill bundle is a legitimate tool for generating AI music via the IMA Studio API. The core logic in `scripts/ima_voice_create.py` implements a robust task creation and polling flow, including a 'reflection' mechanism to retry requests with adjusted parameters upon failure. The instructions in `SKILL.md` and `SKILL-DETAIL.md` are focused on providing a clean user experience and correctly handling media URLs without local file storage. No evidence of data exfiltration, unauthorized execution, or malicious prompt injection was found; all network activity is restricted to the declared `api.imastudio.com` endpoint.

能力评估

ℹ Purpose & Capability

Overall coherent: the skill claims to generate music/voice and the code and SKILL.md implement a text_to_music flow (product list → create task → poll). Minor mismatch: some metadata/homepage references use imaclaw.ai while the API host is api.imastudio.com (inconsistent branding), and the description mentions 'voiceovers/narration' while the code fixes TASK_TYPE to text_to_music (models support vocals for songs but this is not a general TTS endpoint). These are plausible explanations (branding/terminology slop) but worth verifying with the publisher.

✓ Instruction Scope

SKILL.md instructs only calls to api.imastudio.com and UX behavior (progress updates, not exposing internal params). The included script builds requests to the declared API, uses the IMA_API_KEY only for Authorization headers, polls task detail, and returns remote audio URLs. It does not instruct reading unrelated files or other environment secrets.

✓ Install Mechanism

No install spec; the skill is instruction+script only and requires python3 and the 'requests' package. No downloads from arbitrary URLs or extraction operations are present.

✓ Credentials

Only a single credential (IMA_API_KEY) is required and used as the Authorization bearer token to api.imastudio.com. The key is the declared primary credential and no other secrets or host credentials are requested. This is proportionate for an API client.

✓ Persistence & Privilege

The skill does not request persistent or system-level privileges (always:false). The manifest and script indicate no local read/write of preferences or logs by default.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install ima-voice-ai
安装完成后，直接呼叫该 Skill 的名称或使用 /ima-voice-ai 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.14

- Added credentialNote to indicate IMA_API_KEY is sent only to api.imastudio.com. - Updated homepage link to https://www.imaclaw.ai in metadata. - No changes to features or usage.

v1.0.13

- No code or documentation changes detected in this release. - Functionality and usage remain unchanged from the previous version.

v1.0.12

- Added comprehensive usage and protocol details in SKILL-DETAIL.md. - Included !keywords.txt to expand keyword and alias coverage. - Enhanced documentation for model selection, user UX, result delivery, and environment settings. - No changes to core script or network/API logic; update is documentation and metadata focused.

v1.0.11

- Removed the ima_logger.py script. - Updated SKILL.md to reflect use of IMA_API_KEY as an environment variable during script invocation. - Clarified script usage and setup instructions in SKILL.md. - Incremented SKILL.md version to 1.2.2.

v1.0.10

**IMA Voice AI (v1.0.10) Changelog** - Documentation and metadata updates only; no code changes. - Clarified supported models (Suno/sonic, DouBao BGM/GenBGM, DouBao Song/GenSong). - Stated API usage is limited to api.imastudio.com. - Updated default behavior and user input mappings. - Enhanced error handling and runtime documentation. - Confirmed: No longer reads, writes, or persists local logs or preferences.

v1.0.9

- Revised documentation to clarify that the skill can be used standalone, with ima-knowledge-ai integration now optional. - Added explicit environment variable and persistence requirements for improved clarity and transparency. - Updated section headings and guidance for knowledge base usage to be non-mandatory, focusing on recommendations instead. - Streamlined the skill’s description and removed mandatory pre-check language. - No changes to code or functionality.

v1.0.8

IMA Voice AI 1.0.8 Changelog - Added .gitignore for repository hygiene. - Added SECURITY.md to document security policies and reporting guidelines.

v1.0.7

- No code or documentation changes detected in this version. - Functionality, workflow, and user experience remain unchanged from the previous release. - If this was unintended, please check deployment process or version tagging.

v1.0.6

- Added registry metadata file clawhub.json for platform integration. - No functional or API changes to the skill itself. - Existing features and user logic remain unchanged. - Update primarily improves registry/discovery; no impact on usage or workflows.

v1.0.5

IMA Voice AI v1.0.5 - Expanded keywords for broader language and usage coverage (e.g., 音乐生成, AI音乐, 作曲, BGM, Suno, DouBao). - Improved documentation clarity and formatting in SKILL.md. - No breaking changes to music generation logic or user API.

v1.0.4

**Major update: Adds intelligent error recovery and user intent mapping for AI music generation.** - Introduced a 3-layer "reflection" mechanism: the skill now automatically retries failed music generation attempts with smart parameter adjustments for maximum compatibility. - Enhanced user input parsing: includes detailed mapping from user language/intent to correct model selection and parameters, improving support for BGM, vocals, gender, and custom lyrics. - Updated documentation for clarity, now explicitly explaining parameter mapping, error handling, and interaction with the ima-knowledge-ai companion skill. - Removed legacy files (docs, security/readme, project JSON) for a cleaner codebase. - No changes to external API endpoint usage or privacy policy; all network activity remains transparent.

v1.0.3

IMA Voice AI 1.0.3 Changelog - Added detailed security and review documentation: CLAWHUB_SECURITY_IMPROVEMENTS.md and OPENCLAW_REVIEW_RESPONSE.md. - No changes to core code or user-facing logic in this release.

v1.0.2

ima-voice-ai v1.0.2 - Removed the internal review response file: OPENCLAW_REVIEW_RESPONSE.md. - No user-facing changes; functionality remains the same. - File system and privacy behaviors are unchanged.

v1.0.1

ima-voice-ai 1.0.1 - Added INSTALL.md with setup instructions, SECURITY.md for detailed privacy policy, and requirements.txt for dependencies. - Updated SKILL.md security section: clarified user permissions, now explicitly allows viewing/deleting local data (e.g., preference and log files); added transparency about file storage and privacy. - Added reference to SECURITY.md in user guidance and agent response template. - Minor updates in README.md and metadata for clarity and consistency.

v1.0.0

ima-voice-ai 1.0.0 — initial release for AI music generation via IMA Open API - Supports text-to-music with 3 models (Suno sonic-v5, DouBao BGM, DouBao Song); defaults to the newest and most popular model (Suno). - Output formats: MP3/WAV; requires an ima_* API key. - Implements strict read-only security policy—users may only set API key and select models. - Remembers user model preferences; applies them for future generations. - Provides clear, stepwise user notifications throughout the music generation process.

元数据

Slug ima-voice-ai

版本 1.0.14

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 15

常见问题