Podcast Generator 🎙️
This skill streamlines the creation of audio briefings and podcasts, ensuring clean narration and professional background music mixing.
Workflow
Draft Script:
- Write the script based on the requested topic.
- Rule: No meta-instructions or bracketed notes (e.g., "[Intro]") in the final script.
- Persona: Friday (🦞). Sharp, calm, concise.
- Format: Natural monologue.
Generate TTS:
- Use the
ttstool. Always generate as MP3. - Save raw voice to:
~/.openclaw/media/temp_voice.mp3.
- Use the
Mix Background Music:
- Select a track from
assets/music/or find/download CC-licensed ambient techno if a specific vibe is requested. - Run the mixer script using paths relative to the skill or user home:
python3 ./scripts/mix_audio.py \ ~/.openclaw/media/temp_voice.mp3 \ ./assets/music/vladislav_zavorin-ambient-techno-405559.mp3 \ ~/.openclaw/media/output_briefing.mp3 \ --volume 0.08 \ --outro-seconds 5 - The background track loops if needed. Once the narration ends, keep the music for five seconds and fade it smoothly to silence. Do not cut it abruptly.
- Select a track from
Deliver:
- If an openclaw helper, delivery the final result to the default or specified channel. Otherwise save to the workspace and return the file path.
- Standard delivery path:
~/.openclaw/media/.
Open Source Music Sources
If specific background tracks are needed, search for and download Creative Commons (CC-BY / CC0) licensed music from:
- Free Music Archive (FMA)
- Pixabay Music (Filtered for "Ambient Techno")
- Wikimedia Commons
- Incompetech (Kevin MacLeod)
Constraints
- Relative Paths: Use relative paths where possible or
~expansion to avoid hardcoded environment strings. - Volume: Keep background music at
0.08for voice clarity. - Outro: For narration with music, default to a five-second music-only fade-out after the voice ends. Use
--outro-secondsto override it when the user requests a different ending. - Cleanup: Temp files should be overwritten or cleaned up to save space.