IMA Studio Music — Suno, DouBao — 技能

技能详情（站内镜像，无评论）

Generate music from text with IMA Open API. Supports Suno (sonic), DouBao BGM (GenBGM), and DouBao Song (GenSong). Uses only api.imastudio.com.

开发与 DevOps

许可证：MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本：v1.0.11

统计：⭐ 0 · 398 · 1 current installs · 1 all-time installs

⭐ 0

安装量（当前） 1

🛡 VirusTotal ：良性 · OpenClaw ：良性

Package：allenfancy-gan/ima-voice-ai

安全扫描（ClawHub）

VirusTotal ：良性
OpenClaw ：良性

OpenClaw 评估

The skill's requirements and runtime instructions match its stated purpose (text-to-music via api.imastudio.com) and it only requests a single API key; nothing in the manifest or visible code contradicts that.

目的

Name/description, required env var (IMA_API_KEY), SKILL.md, clawhub.json, and the included Python script all consistently describe calling api.imastudio.com to create and poll text_to_music tasks. The single requested secret (IMA_API_KEY) is appropriate for authenticating to that API.

说明范围

SKILL.md specifies calling product list → create task → poll detail on api.imastudio.com, describes expected outputs, and instructs use of the IMA_API_KEY environment variable. It does not instruct reading other skills' files or unrelated system files in the visible content.

安装机制

No install spec is provided (instruction-only), which is low risk. The package includes a Python script and requirements.txt (requests). The lack of an automated install means the host must already have Python and requests installed; this is reasonable but the presence of an executable script is worth noting — it will run locally and make network calls when invoked.

证书

Only a single environment variable (IMA_API_KEY) is required and is justified by the skill's API calls. No other credentials or unrelated env vars are requested.

持久

always is false, the skill does not request any persistent read/write paths, and SKILL.md/manifest state no local logging or preferences by default. Autonomous invocation is allowed (platform default) but not elevated (no always:true).

综合结论

This skill appears internally consistent: it ships a Python script that calls only api.imastudio.com and requires a single IMA_API_KEY. Before installing, ensure the API key you provide is intended for use with IMA Studio and is not reused for other services. Because the skill runs a local script that makes network requests, run it in an environment where network activity is permitted and expected. Check that you have the Python 'requests' pac…

安装（复制给龙虾 AI）

将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「IMA Studio Music — Suno, DouBao」。简介：Generate music from text with IMA Open API. Supports Suno (sonic), DouBao BGM (…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/allenfancy-gan/ima-voice-ai/SKILL.md
（来源：yingzhi8.cn 技能库）

SKILL.md

打开原始 SKILL.md（GitHub raw）

---
name: IMA Studio Music Generation
version: 1.2.2
category: file-generation
author: IMA Studio (imastudio.com)
keywords: imastudio, ai music, text_to_music, Suno, DouBao, GenBGM, GenSong
description: >
  Generate music from text with IMA Open API. Supports Suno (sonic), DouBao BGM (GenBGM),
  and DouBao Song (GenSong). Uses only api.imastudio.com.
requires:
  env:
    - IMA_API_KEY
  primaryCredential: IMA_API_KEY
  credentialNote: IMA_API_KEY is sent only to api.imastudio.com for authentication.
persistence:
  readWrite: []
  retention: No local preferences or logs are written by this skill script.
---

# IMA Voice AI Creation

## Capability

This skill generates music/audio from text prompts (`text_to_music`) through IMA Open API.

Supported model IDs:
- `sonic` (Suno)
- `GenBGM` (DouBao BGM)
- `GenSong` (DouBao Song)

## Network and Credential Transparency

- API domain used: `https://api.imastudio.com`
- Required key: `IMA_API_KEY` (environment variable)
- The script does not call secondary upload domains.
- The script does not read other skills' files.

## Runtime Rules

1. Always query `/open/v1/product/list` first.
2. Resolve `attribute_id`, `credit`, and latest `model_version` from product list.
3. Create task via `/open/v1/tasks/create`.
4. Poll `/open/v1/tasks/detail` until completed or timeout.

## Defaults and Timeouts

- Task type is fixed to `text_to_music`.
- Poll interval: 5 seconds.
- Max poll wait: 8 minutes.
- If `--model-id` is omitted, default model is `sonic`.

## User Input Mapping

- BGM / instrumental / 背景音乐 / 纯音乐 -> `GenBGM`
- Song / lyrics / 人声 / 歌曲 -> `sonic` or `GenSong`
- If unspecified -> default `sonic`

## Script Invocation

Set key first:

```bash
export IMA_API_KEY="ima_your_key_here"
```

```bash
python3 {baseDir}/scripts/ima_voice_create.py 
  --model-id sonic 
  --prompt "upbeat lo-fi hip hop, 90 BPM, no vocals" 
  --output-json
```

List models:

```bash
python3 {baseDir}/scripts/ima_voice_create.py 
  --list-models
```

## Error Handling Policy

- Return user-friendly error summaries in plain language.
- Include practical next step suggestions (retry, switch model, check API key/credits).
- Do not expose raw internal payloads unless debugging is explicitly requested.

## Expected Output

On success, return:
- task id
- result URL
- model id/model name
- credit used

If `--output-json` is enabled, parse JSON from script output.