Tell it how to feel.
Describe emotion and delivery in natural language. Let a whisper, a laugh, or a hesitation land exactly where it belongs.
Meet Drama 3. Direct expressive voice performances with the words you already know—emotion, timing, texture, and all.
01 / THE EXPERIENCE
Change the direction and the meaning changes with it. Explore how simple performance notes can reshape the very same words.
CHOOSE A DIRECTION
Select a direction to see how you could prompt a performance.
[softly, with quiet resolve]
“I knew you'd come back.”
A small line becomes a turning point when its intention is clear.
02 / CREATIVE CONTROL
Drama 3 turns plain language into performance direction, giving each moment more room to breathe.
Describe emotion and delivery in natural language. Let a whisper, a laugh, or a hesitation land exactly where it belongs.
Use paired tags to shape selected words without changing the feeling of the entire line.
Write multi-speaker dialogue and direct an entire exchange together in the Text to Speech editor.
03 / THE PROCESS
Start with the words you want to hear. A sentence, a story, or a conversation.
Add notes like [barely holding back tears] or place a tag around a phrase.
Choose your voices in Fish Audio, generate a take, and refine your direction.
04 / GOOD TO KNOW
Drama 3 is Fish Audio's expressive text-to-speech model. It lets you direct how a line is performed with written instructions for emotion, pacing, sounds, and more.
Place a natural-language direction in square brackets where you want it, such as [sigh] or [speaking softly]. You can also use paired tags to affect selected words.
Yes. Fish Audio's Text to Speech editor supports adding speakers, assigning a voice to each, and generating the dialogue together.
Open the Fish Audio Text to Speech studio ↗ and select Drama 3.