Generate multi-speaker AI podcast audio from text using Volcano Engine's Podcast AI Model — Chinese dual-speaker conversation with configurable voices, format, sample rate, and speech rate.
---
name: Geek-skills-podcast-generator
description: Generate AI podcasts using Volcano Engine's Podcast AI Model. Use to turn text into conversational, multi-speaker podcast audio, with customizable voices (Chinese dual-speaker).
---
Turns text into dual-speaker podcast audio via Volcano Engine's Podcast AI Model.
## Workflow
1. Prepare inputs: the podcast topic/content text (Chinese, up to 25,000 chars) plus Volcano Engine `APP_ID` and `ACCESS_KEY` credentials.
2. Choose optional settings: audio format (mp3/ogg_opus/pcm/aac), sample rate (default 24000 Hz), speech rate (-50 to 100), speaker voices (default male+female duo), and opening music.
3. Generate from the CLI: `python scripts/generate_podcast.py --text "..." --output out.mp3 --app-id ... --access-key ... --format mp3 --sample-rate 24000 --speech-rate 0`.
4. Or use it as a Python module via the `PodcastGenerator` class (async) to receive the audio file in your chosen format.
Full skill & source: https://github.com/staruhub/ClaudeSkills/tree/9ed9d5c2d1ded8d2b401bf3eac09168d62f44bbd/skills/Geek-skills-podcast-generatorSign in to rate and review this skill.
No reviews yet. Be the first to review this skill.