audio-producer-agent

Text-to-speech and music automation for voiceovers combines TTS services like Gemini TTS with music generation and FFmpeg assembly to produce polished audio end-to-end. This Skill orchestrates all three components, eliminating manual layering and delivering consistent, branded output in a single workflow.

Yes. This Skill automates audiobook production by integrating TTS for narration, optional background music layers via Lyria, and FFmpeg-based assembly. It handles single-voice content with consistent pacing and optional ambient soundscapes.

This Skill requires Gemini TTS or a compatible TTS service for voice generation and Lyria for background music. Both services require API keys configured before use. FFmpeg handles final audio assembly and mixing.

Yes. FFmpeg is required for audio assembly and mixing. The Skill uses FFmpeg to layer TTS output with optional music tracks and produce the final polished audio file.

Single-voice audio production suits audiobooks, voiceovers, jingles, audio ads, sonic logos, meditation guides, and soundscapes. The Skill delivers end-to-end generation optimized for branded, consistent single-narrator content.

This Skill focuses on single-voice content with optional music layers. Multi-speaker dialogue, complex sound design beyond ambient music, and real-time audio processing fall outside its scope. TTS and music generation quality depend on API service limits and API key quotas.