videoagent-audio-studio

Turn speech, music, and sound ideas into ready audio.

audio generation

What it does

Generates speech, music, sound effects, and cloned voices through routed audio models.

When to use it

Use when the user requests speech, narration, a voice-over, music, or a sound effect.

Give it an audio-generation request; it routes the request to a model and returns a ready-to-use audio URL.

This skill

/tmp/audiomind_usage_count.txt

Write

Updates the free-trial counter (irreversible)

ElevenLabs

Write

Sends audio requests to ElevenLabs

fal.ai

Write

Sends music prompts to fal.ai

@elevenlabs/mcp

Execute

Installs the ElevenLabs MCP server

Requires the ElevenLabs MCP package that supplies the server used for audio generation.

Reads the required ElevenLabs API key from the skill environment configured in ~/.openclaw/openclaw.json.

Reads an optional fal.ai key to enable fal.ai music and sound-effects models.

Reads an optional Pro API key from the environment; Pro mode also requires ELEVENLABS_API_KEY.