I thought multi-speaker TTS would be simple.

Give each character a voice.
Paste the dialogue.
Generate the audio.

But while building TTS Dialog, I realized the annoying part isn t generating speech.

It s everything around it.

I m building TTS Dialog for writers and creators who need more than a single narrator.

The workflow is simple: cast a voice for each character, write dialogue with speaker labels, then generate the full conversation as audio.

I d love to learn from you:

What are you creating: fiction, lessons, podcasts, videos, or something else?