podcast-producer-agent

Podcast production automation coordinates scripting, multi-speaker TTS synthesis, music integration, and FFmpeg-based audio assembly in a single workflow. This skill generates structured scripts, renders dialogue with distinct voices via Gemini TTS, adds intro/outro music via Lyria, and assembles the final episode—reducing production time from hours to minutes.

Yes. The skill generates structured scripts for episodes, interviews, and dialogues, then synthesizes multiple distinct host and guest voices using Gemini TTS. You configure speakers and their characteristics, and voices render automatically during audio production.

Podcast production relies on Gemini TTS for voice synthesis, Lyria for generative music, and FFmpeg for final audio assembly. Google API Keys authenticate both Gemini and Lyria services. Python-based tooling orchestrates the entire workflow from script to finished episode file.

The skill uses Lyria to generate intro/outro music as configurable audio cues. FFmpeg assembles these tracks with synthesized dialogue and guest audio into the final episode, placing music at defined positions within the episode structure.

Structure your episode with hosts, guests, and duration. Generate a dialogue-based script, assign distinct voices to each speaker via Gemini TTS, integrate music via Lyria cues, then assemble all audio tracks using FFmpeg. The workflow handles multi-speaker coordination automatically.

Yes. Google API Keys are required for both Gemini TTS voice synthesis and Lyria music generation. Configure these credentials before running the workflow to enable script-to-audio orchestration.