How do I install the Sjinn Audio Generation skill?

Run npx skillmds@latest add sjinn-ai/sjinn-audio-generation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Sjinn Audio Generation skill do?

Generate audio with SJinn using the official sjinn audio generate CLI command. It is listed under Coding & Dev Tools on SkillMD.

Is Sjinn Audio Generation safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Sjinn Audio Generation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Sjinn Audio Generation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Sjinn Audio Generation?

sjinn-ai (@sjinn-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Sjinn Audio Generation by sjinn-ai — Agent Skill

Name: Sjinn Audio Generation
Author: sjinn-ai

File contents

SJinn Audio Generation

Use this skill when the user wants to create audio from text, optionally guided by reference audios or a reference image, through SJinn.

Prerequisites

Before generating, quickly verify the CLI and login:

sjinn --version
sjinn auth whoami

If either command fails, use sjinn-setup first.

Model and Parameters

Only one audio model is currently available:

seed-audio-1-0 (Seed Audio 1.0 by ByteDance) - generates an .mp3.

Parameter	Required	Support in seed-audio-1-0
`--prompt`	Yes	Text description of the audio. Cite reference audios as `@Audio1` / `@Audio2` / `@Audio3` in the order passed to `--audio-urls`.
`--audio-urls`	No	Up to 3 reference audio files or URLs (mp3, m4a, wav), comma-separated. Mutually exclusive with `--image-urls`.
`--image-urls`	No	A single reference image (jpg, jpeg, png, webp). Mutually exclusive with `--audio-urls`.

Reference audios and a reference image cannot be used together.

Workflow

Prefer JSON output so results are easy to parse.
Use --async for long-running jobs unless the user explicitly wants to wait.
Use --download [path] only when the user asks to save the result locally.

Commands

Text to audio:

sjinn audio generate --prompt "a calm female voice reading a bedtime story" --model seed-audio-1-0 --async --json

With reference audios (cited in the prompt):

sjinn audio generate --prompt "narrate in the style of @Audio1 with the energy of @Audio2" --audio-urls "./ref-a.mp3,./ref-b.wav" --model seed-audio-1-0 --json

With a reference image:

sjinn audio generate --prompt "background music matching the mood of this scene" --image-urls "./scene.png" --model seed-audio-1-0 --async --json

Download the result locally:

sjinn audio generate --prompt "short upbeat jingle" --model seed-audio-1-0 --download ./jingle.mp3 --json

Output Handling

On success, return the task ID, primary URL, any additional URLs, model, and elapsed time. If status is created, tell the user to query the task with sjinn-task-status.

On error, summarize the CLI error plainly and suggest sjinn-setup only when the error indicates the CLI is missing or unauthenticated.

---name: sjinn-audio-generationdescription: Generate audio with SJinn using the official sjinn audio generate CLI command.---# SJinn Audio GenerationUse this skill when the user wants to create audio from text, optionally guided by reference audios or a reference image, through SJinn.## PrerequisitesBefore generating, quickly verify the CLI and login:```bashsjinn --versionsjinn auth whoami```If either command fails, use `sjinn-setup` first.## Model and ParametersOnly one audio model is currently available:**seed-audio-1-0** (Seed Audio 1.0 by ByteDance) - generates an `.mp3`.| Parameter | Required | Support in seed-audio-1-0 || --- | --- | --- || `--prompt` | Yes | Text description of the audio. Cite reference audios as `@Audio1` / `@Audio2` / `@Audio3` in the order passed to `--audio-urls`. || `--audio-urls` | No | Up to **3** reference audio files or URLs (mp3, m4a, wav), comma-separated. Mutually exclusive with `--image-urls`. || `--image-urls` | No | A single reference image (jpg, jpeg, png, webp). Mutually exclusive with `--audio-urls`. |Reference audios and a reference image cannot be used together.## Workflow1. Prefer JSON output so results are easy to parse.2. Use `--async` for long-running jobs unless the user explicitly wants to wait.3. Use `--download [path]` only when the user asks to save the result locally.## CommandsText to audio:```bashsjinn audio generate --prompt "a calm female voice reading a bedtime story" --model seed-audio-1-0 --async --json```With reference audios (cited in the prompt):```bashsjinn audio generate --prompt "narrate in the style of @Audio1 with the energy of @Audio2" --audio-urls "./ref-a.mp3,./ref-b.wav" --model seed-audio-1-0 --json```With a reference image:```bashsjinn audio generate --prompt "background music matching the mood of this scene" --image-urls "./scene.png" --model seed-audio-1-0 --async --json```Download the result locally:```bashsjinn audio generate --prompt "short upbeat jingle" --model seed-audio-1-0 --download ./jingle.mp3 --json```## Output HandlingOn success, return the task ID, primary URL, any additional URLs, model, and elapsed time. If `status` is `created`, tell the user to query the task with `sjinn-task-status`.On error, summarize the CLI error plainly and suggest `sjinn-setup` only when the error indicates the CLI is missing or unauthenticated.

Frequently asked questions

Sjinn Audio Generation