podcast-generation

To convert text into a podcast, this tool processes your written content into a structured JSON script with two hosts and synthesizes speech using Volcengine TTS, outputting an MP3 audio file. You simply provide the text file path for processing.

Yes, you can generate a two-host dialogue from a text file. The skill creates a conversational audio format featuring distinct male and female voices by structuring your text into a JSON script before speech synthesis.

Text-to-speech podcast generation supports both Chinese and English content. It processes multilingual text inputs to produce natural-sounding MP3 audio files and markdown transcripts in either language.

You need specific environment variables configured for Volcengine TTS API access to generate podcasts. These credentials are required for the underlying text-to-speech engine to synthesize the audio output successfully.

When creating audio from text, the skill outputs MP3 audio files and markdown transcripts. The MP3 contains the synthesized two-host dialogue, while the markdown provides a readable text version of the generated script.