
Videoagent Audio Studio
This is essentially an audio API router that saves you from juggling multiple services. Point it at text and it'll generate speech via ElevenLabs, ask for background music and it hits fal.ai's models, request sound effects and it picks the fastest available option. The routing logic is solid and it handles the async complexity of music generation, but you're still dependent on external API reliability and costs. Most useful when you're building something that needs multiple types of audio generation without wanting to implement each service's quirks yourself. Setup requires at minimum an ElevenLabs key, though fal.ai access unlocks the music features.
- skills.sh installs
- 4K
- GitHub stars
- 823
- last updated
- Aug 21, 2026
Install
$ npx -y skills add pexoai/pexo-skills --skill videoagent-audio-studio --agent claude-codeInstalls into .claude/skills of the current project.
Files
🎙️ 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 {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":
Sponsors
Details
- Repository
- github.com/pexoai/pexo-skills
- Categories
- Backend & APIs, Generative Media