Upload Your Own Voices: Create your own podcast with custom voice samples.
Timestamps: Useful if you want to generate a video using Wan2.2 or other tools. The timestamps let you automatically separate each speaker (splitting the long podcast into smaller chunks), pass the audio clips to your video generation model, and then merge the generated video clips into a full podcast video (e.g., using FFmpeg + any video generation model such as image+audio → video).