VoiceCast
Ava Narrator
The lighthouse was still there. Waiting.
A STUDIO FOR STORIES & VIDEO
One script. A whole cast.
Assign a distinct voice to each character, shape the delivery line by line, and export your story as audio and SRT subtitles.
Multi-character scripts · Line-by-line direction · Audio & SRT export
Elliot Character A
I thought you would never come back.
Gabriel Character B
Some promises are worth keeping.
Click play to preview each line · Free to listen
30 voice presetsMulti-character creationMP3 / WAV / FLACSRT / MP4
ONE WORKFLOW. DIFFERENT STORIES.
Create something worth listening to.
01
Stories, with a full cast
Distinct voices. A shared story. Edit each line without losing the scene.
Explore workflow ↗02A new voice for your video
Work from SRT subtitles, refine timing and dialogue, then export a dubbed video.
Explore workflow ↗03Bring the page to life
Separate narration from dialogue and review the cast before you generate.
Explore workflow ↗MORE THAN A GENERATE BUTTON
Direct the details.
Keep the whole story.
Move between the script, character voices and individual lines in one workspace. Save your project and return to the scene when inspiration strikes.
See how it works →Cast
Choose a voice for each role.
Emotion
Shape the tone of individual lines.
Pacing
Adjust speed and pauses.
Export
Take audio and subtitles with you.
Current controls and writing examples
Theater: generate, play and follow the script
Expand a dialogue line to choose its voice, emotion and speed. Its action changes from Generate to Play and Stop. While audio plays, the source script highlights the corresponding sentence and scrolls to it; long list summaries wrap instead of truncating the text.
Use More actions to rename a role, duplicate, move, delete or regenerate a line. Changing dialogue or delivery requires a new generation; cached replay does not apply the new settings automatically. Review the displayed credit estimate before confirming.
Writing prompts for AI narration, dialogue and game voices
Treat these prompts as writing briefs for preparing your script, not commands to paste into spoken dialogue. Use the existing emotion, speed and pause controls for delivery. A role label such as Narrator: or Merchant: identifies the speaker and is not spoken as part of the line.
Narration brief: write a calm 20-second scene in two short sentences, with no stage directions. Dialogue brief: write six alternating lines for two characters with consistent role labels. Game brief: write one greeting, one warning and one farewell for a fantasy merchant; choose an available character preset, then preview each line.
For SRT video dubbing, ask for short, speakable lines that preserve the meaning and names within your existing timestamps. Count timing by listening: shortening the wording is often better than extreme speed. Review recognition errors and overlapping timestamps before generating the full video.
BEFORE YOU CREATE
A few useful answers.
Clear features. Clear limits.
Can I use different voices in one script?
Yes. Assign a voice to each role, then adjust individual lines in the director workspace.
Which files can I export?
The script studio supports MP3, WAV and FLAC audio, plus SRT subtitles. The video studio exports MP4, MOV, MKV or WebM video and WAV, MP3 or FLAC dubbing audio.
Does dubbing automatically translate a video?
No. This workflow voices the subtitles you provide or edit. Translate and review the dialogue yourself before generating another language.
Are voice previews free?
Generating a preview uses credits. A cached preview can be replayed without generating it again. Review the credit estimate before generation.
How are credits charged?
Generating speech, recognizing subtitles, creating dubbed videos and downloading media use credits. Check the estimate before confirming. Replaying valid cached audio does not repeat the speech generation charge.
Can I continue editing a saved project?
Yes. Open a saved project from your project list. Keep a backup of important media: project text and settings do not replace the original audio or video files.
How long are generated files kept?
Generated audio caches are kept for 3 days and video media for 7 days. Download important results before expiry. Regenerating expired audio may use credits.
What recording do I need for voice cloning?
Use a clear 6–60 second recording of one speaker, up to 10 MB. Avoid background music and overlapping voices. Use only your own voice or a voice you are authorized to use.
What if a generation task fails?
Check the task history before retrying. Completed lines may be reused while their cache is valid. Unsettled reserved credits are refunded on failure; completed lines may still be charged.
Is voice cloning available?
Yes. Create a cloned voice from an authorized recording, then use it for character dialogue and video dubbing. Speech generation uses credits.
YOUR NEXT SCENE