Meldio automatically interprets dialogue when you generate audio. Performance directives let you take control of a particular line — whispered, shouted, hesitant, pleading — whenever you have a specific delivery in mind. Your directions always take priority over Meldio’s interpretation.
How the syntax works
A performance directive is written as a short phrase in asterisks directly before the line it applies to — for example, *whispering* before a line of dialogue. You can use familiar styles such as whispering, shouting, crying, nervous, laughing, angry, sad, excited, frightened, hesitant, pleading, sarcastic, tender, or calm, as well as a short descriptive phrase of your own. Meldio passes your direction to the performance engine rather than replacing it with an AI suggestion.
Directions written the traditional script way, in parentheses, work too — JULES: (sharp) Stop!, or (nervous) on its own line under the character's name. Parentheses that describe movement or who is being addressed, such as (crossing to the window) or (to DEREK), are simply left unspoken. The Review screen lists everything in parentheses that won't be read aloud, so you can choose to have any of it spoken instead.
Where directives matter most
- Emotional turning points. The line where a scene's tone shifts — from calm to angry, from steady to frightened — is exactly where a directive earns its place.
- Subtext-heavy lines. A line that means something different depending on delivery (sarcastic versus sincere) needs the directive to land correctly, since the words alone don't disambiguate it.
- Quiet or intimate moments. Whispered or hesitant delivery rarely happens by default, and often needs to be called out explicitly to read correctly.
Where to leave lines alone
You do not need to add directives to every line. Meldio interprets lines without directions automatically. Add your own cues where you want a particular performance choice.
Testing and iterating
Since directives affect voice delivery meaningfully, it's worth generating a scene once, listening for any line where the delivery feels off, and adjusting or adding a directive specifically to that line rather than guessing across the whole scene upfront. This iterative approach tends to get better results than trying to perfectly direct every line before hearing any of it.