Paste the script. It is already directed.
Auto-Director assigns emotion and intensity to every line. Change what you want, preview the performance, then render one finished voiceover for stories, podcasts, audiobooks, training, and video.
Choose one stock or cloned voice for the whole production.
The city had forgotten what silence sounded like.
Until one small lantern appeared in the window.
And then the whole skyline answered.
The emotional direction happens before you press render.
Without Auto-Director, someone has to direct every line by hand. Studio gives you a complete first pass, then leaves every decision editable.
Paste
Drop in a scene, episode, lesson, or full narration script.
Auto-Direct
Get an emotion and intensity plan for every spoken line.
Preview and change
Hear one line quickly, then adjust the delivery where it matters.
Render
Track the long-form job, play the WAV, and download the finished audio.
The same voice can carry the whole piece without reading every line the same way.
Cast is for scripts with an arc. The voice stays consistent while the delivery moves with the writing.
“You made it. I was beginning to think the storm had won.”
One neutral delivery has to carry relief, fear, and warmth by itself.
“You made it.” warm, bold
“I was beginning to think the storm had won.” empathy, subtle
Two lines, one voice, two clear performance decisions.
[
{
"text": "You made it.",
"emotion": "warm",
"intensity": "bold"
},
{
"text": "I was beginning to think the storm had won.",
"emotion": "empathy",
"intensity": "subtle"
}
]Direct the moments people remember.
Studio works best when a script needs more than a clean read. These are the lines where delivery changes the meaning.
Storytelling
Give narration an emotional arc without directing every sentence by hand.
“The forest held its breath.”
“Then the first bird called.”
Podcasts
Move from a strong cold open to a thoughtful explanation without one flat read.
“This is the part nobody tells you.”
“The real answer is quieter.”
Audiobooks
Direct scene changes and dialogue beats across chapters while keeping one narrator.
“Do not open that door, she whispered.”
“He opened it anyway.”
Product videos
Keep feature explanations clear, then lift the delivery when the payoff arrives.
“Your workflow stays exactly where it is.”
“The finished cut is ready to share.”
Training and learning
Make instructions easy to follow and sensitive moments sound considered.
“Pause here and check the pressure gauge.”
“If you are unsure, ask for help.”
Brand audio
Keep campaign reads recognizable while changing the energy line by line.
“Made for the long way home.”
“Available Friday.”
Cast for directed scripts. Speak for immediate synthesis.
If every line can use the same delivery, Speak is the simpler tool. When the performance needs to move with the script, open Studio and direct it.
FAQ
What does Auto-Director do?
Auto-Director reads a multi-line script and assigns an emotion and intensity to each spoken line. You can keep the plan, change any direction, or preview one line before rendering the full piece.
Can I use my own voice?
Yes. Studio uses the same PyAI voice catalog as Speak and Clone. Choose a stock voice or a voice you have cloned, then use it across the whole production.
How does long-form rendering work?
A render runs as an asynchronous job. Studio shows progress, saves the job to your project, and gives you a WAV player and download when the audio is ready. You can close the tab and return later without losing the render.
How much does Cast cost?
Cast is $0.02/min of finished audio. Usage is measured per second, so a short production is billed for its actual duration rather than rounded up to a full minute.
When should I use Cast instead of Speak?
Use Cast when delivery changes across a script and you need to direct emotion line by line. Use Speak when you need low-latency synthesis for a single prompt or a conversational response.
Can developers use the Cast API directly?
Yes. The same workflow is available through the Cast API: direct the script, preview a line, submit an asynchronous render job, poll its progress, then fetch the finished audio.
Your first direction pass is waiting.
Paste the script, review the performance plan, and render the voiceover from the same PyAI account you already use.