# Audio

> Generate speech and audio using OpenAI, Minimax, or Gemini through the hosted Skills runtime with provider-cost pricing.

- **Type:** Skill
- **Install:** `agentstack add skill-hasna-skills-audio`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [hasna](https://agentstack.voostack.com/s/hasna)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [hasna](https://github.com/hasna)
- **Source:** https://github.com/hasna/skills/tree/main/skills/audio

## Install

```sh
agentstack add skill-hasna-skills-audio
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Audio Generation Skill

Generate speech or short audio from text using provider-backed audio models. This skill routes through the hosted Skills runtime so billing can reserve the selected provider/model cost before execution.

## Supported Providers

- `openai`: `tts-1`, `tts-1-hd`
- `minimax`: `speech-2.8-turbo`, `speech-2.8-hd`
- `gemini`: `gemini-2.5-flash-preview-tts`, `gemini-2.5-pro-preview-tts`

## Usage

```bash
audio generate --provider openai --text "Welcome to Skills.md" --voice alloy --output ./voice.mp3
audio generate --provider minimax --model speech-2.8-turbo --text "Fast narration" --output ./voice.mp3
audio generate --provider gemini --text "Studio announcement" --output ./voice.wav
```

## Options

- `--provider`: `openai`, `minimax`, or `gemini`
- `--model`: provider model override
- `--text`: text to synthesize
- `--voice`: provider-specific voice
- `--format`: output format such as `mp3`, `wav`, or `opus`
- `--output`: output file path

## Environment

- `SKILLS_API_KEY`: required for hosted runtime execution

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [hasna](https://github.com/hasna)
- **Source:** [hasna/skills](https://github.com/hasna/skills)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-hasna-skills-audio
- Seller: https://agentstack.voostack.com/s/hasna
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.