PHASE 3 OF 8
A full audio suite, not just text-to-speech
Voice design, dialogue, sound effects, and music generation for every scene — plus a dedicated pipeline for audio-only productions like audiobooks and podcasts.
From script notes to finished sound
How the Audio phase works
01
Design the voices
Use each character’s voice description to audition previews, save a voice profile, and keep the performance consistent across the project.
02
Build the sound
Generate dialogue, effects, ambience, and scene music from the notes and descriptions already developed in the Script phase.
03
Review and hand off
Keep every take organized, choose the active version, and send the approved audio to Storyboard, Video, and the Timeline Editor.
What's covered
Everything needed to move the story forward
- Voice design from a text description, with preview before saving
- Character voice profiles with saved voice IDs
- Per-shot or per-passage dialogue TTS with take management
- Multi-speaker dialogue generation for full scenes
- AI emotion tags with manual editing and review before generation
- Sound effects from shot audio notes plus location ambience
- Prop interaction sounds and scene-level background music
- Full Score generation for one continuous project-wide music track
- Active takes flow into Storyboard preview, Video conditioning, and Timeline
- Audiobook, podcast, audio-drama, and narrated-course project types