Existing TTS tools usually support only single voices, but I needed natural multi-character conversations for audiobooks and podcasts—so I built Voxica.
Live demo: https://voxica.io (try the "Maya & Noah" conversation)
Voxica generates:
Multi-character dialogue from simple text input
Automatic voice switching
Realistic background sounds (café, rain, office, etc.)
Export-ready audio files
Perfect for:
Podcast/audiobook creators
Developers building voice apps
Educators making interactive lessons
Anyone who needs conversation audio quickly
I built this after spending weeks manually editing podcast voice clips—now it takes 30 seconds instead of 3 hours.
API docs: https://voxica.io/docs Free to try, usage-based pricing after that.
Curious what other use cases or conversation scenarios people here would find useful!
0 comments