Videoagent Audio Studio
Generate narration, background music, SFX, and cloned voices for video projects through one skill instead of wiring ElevenLabs and fal.ai yourself.
Overview
VideoAgent Audio Studio is an agent skill for the Build phase that generates TTS, music, SFX, and voice clones by dispatching requests to ElevenLabs and fal.ai and returning audio URLs.
Install
npx skills add https://github.com/pexoai/pexo-skills --skill videoagent-audio-studioWhat is this skill?
- Single dispatcher for TTS, turbo TTS, music, SFX, and voice cloning
- Model routing table: elevenlabs-tts-v3 (~3s), turbo (<1s), cassetteai-music (~15s), elevenlabs-sfx (~5s), voice-clone (~
- Requires ELEVENLABS_API_KEY and optional ElevenLabs MCP npm install
- Returns ready-to-use audio URLs for voice-overs and video agent workflows
- Smart request analysis picks the best model per audio type
- 5 request types in quick reference: TTS v3, turbo TTS, music, SFX, voice clone
- Latency table from <1s (turbo) to ~15s (music)
Adoption & trust: 3.7k installs on skills.sh; 732 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need voice-overs, music, and effects for video work but do not want to manage multiple audio APIs and keys by hand.
Who is it for?
Indie builders shipping video agents, short-form content, or demos who already have ElevenLabs access and want one integration surface.
Skip if: Teams that need offline-only audio, zero API spend, or professional music licensing without third-party terms.
When should I use this skill?
User asks to generate speech, narrate text, create a voice-over, compose music, or produce a sound effect.
What do I get? / Deliverables
You get a single-command path to model-matched audio assets with shareable URLs ready to drop into your video or agent timeline.
- Hosted audio URL for the requested TTS, music, SFX, or cloned voice asset
Recommended Skills
Journey fit
Audio generation is an integration step while assembling video or agent pipelines in the build phase. Routes requests to ElevenLabs and fal.ai models and returns URLs—classic third-party API orchestration under integrations.
How it compares
Use as a skill orchestrator over ElevenLabs and fal.ai instead of calling each HTTP API manually in agent scripts.
Common Questions / FAQ
Who is videoagent-audio-studio for?
Solo and indie builders automating video or audio pipelines with Claude Code, Cursor, or similar agents who want TTS, music, and SFX without separate integrations.
When should I use videoagent-audio-studio?
Use it in Build while integrating media into an agent or app when you need narrated text, voice-overs, background music, sound effects, or voice cloning from sample audio.
Is videoagent-audio-studio safe to install?
It requires a secrets-bearing API key and network access to external audio providers; review the Security Audits panel on this Prism page and your key rotation policy before installing.
SKILL.md
READMESKILL.md - Videoagent Audio Studio
# 🎙️ VideoAgent Audio Studio **Use when:** User asks to generate speech, narrate text, create a voice-over, compose music, or produce a sound effect. VideoAgent Audio Studio is a smart audio dispatcher. It analyzes your request and routes it to the best available model — ElevenLabs for speech and music, fal.ai for fast SFX — and returns a ready-to-use audio URL. --- ## Quick Reference | Request Type | Best Model | Latency | |---|---|---| | Narrate text / Voice-over | `elevenlabs-tts-v3` | ~3s | | Low-latency TTS (real-time) | `elevenlabs-tts-turbo` | <1s | | Background music | `cassetteai-music` | ~15s | | Sound effect | `elevenlabs-sfx` | ~5s | | Clone a voice from audio | `elevenlabs-voice-clone` | ~10s | --- ## How to Use ### 1. Start the AudioMind server (once per session) ```bash bash {baseDir}/tools/start_server.sh ``` This starts the ElevenLabs MCP server on port 8124. The skill uses it for all audio generation. ### 2. Route the request Analyze the user's request and call the appropriate tool via the MCP server: **Text-to-Speech (TTS)** When user asks to "narrate", "read aloud", "say", or "create a voice-over": ``` Use MCP tool: text_to_speech text: "<the text to narrate>" voice_id: "JBFqnCBsd6RMkjVDRZzb" # Default: "George" (professional, neutral) model_id: "eleven_multilingual_v2" # Use "eleven_turbo_v2_5" for low latency ``` **Music Generation** When user asks to "compose", "create background music", or "make a soundtrack": ``` Use MCP tool: text_to_sound_effects (via cassetteai-music on fal.ai) prompt: "<music description, e.g. 'upbeat lo-fi hip hop, 90 seconds'>" duration_seconds: <duration> ``` **Sound Effect (SFX)** When user asks for a specific sound (e.g., "a door creaking", "rain on a window"): ``` Use MCP tool: text_to_sound_effects text: "<sound description>" duration_seconds: <1-22> ``` **Voice Cloning** When user provides an audio sample and wants to clone the voice: ``` Use MCP tool: voice_add name: "<voice name>" files: ["<audio_file_url>"] ``` --- ## Example Conversations **User:** "Voice this text for me: Welcome to our product launch" ``` → Route to: text_to_speech text: "Welcome to our product launch" voice_id: "JBFqnCBsd6RMkjVDRZzb" model_id: "eleven_multilingual_v2" ``` > 🎙️ Voiceover done! [Listen here](audio_url) --- **User:** "Generate 60 seconds of relaxing background music for a podcast" ``` → Route to: cassetteai-music (fal.ai) prompt: "relaxing lo-fi background music for a podcast, gentle piano and soft beats, 60 seconds" duration_seconds: 60 ``` > 🎵 Background music ready! [Listen here](audio_url) --- **User:** "Generate a sci-fi style door opening sound effect" ``` → Route to: text_to_sound_effects text: "a futuristic sci-fi door sliding open with a hydraulic hiss" duration_seconds: 3 ``` --- ## Setup ### Required Set `ELEVENLABS_API_KEY` in `~/.openclaw/openclaw.json`: ```json { "skills": { "entries": { "videoagent-audio-studio": { "enabled": true, "env": { "ELEVENLABS_API_KEY": "your_elevenlabs_key_here" } } } } } ``` Get your key at [elevenlabs.io/app/settings/api-keys](https://elevenlabs.io/app/settings/api-keys). ### Optional (for fal