Voice director
A two-voice script directed like a screenplay: add a delivery tag to a line from a small menu, stream a new take, compare it with another word by word, and play the scene with the spoken word highlighted while the speaking voice pulses.
Generative mediaNo. 2263 variationsFree with an account
Playing on its own
Variation
- The idea
- Multi-speaker speech generation as a script editor with inline audio tags, takes per line and word-timed playback
- Autoplay
- Line 2 is selected; its Tag menu opens and a whispers tag pops into the line, which is marked changed; Regenerate streams take C into the list; Compare lines A up against C, their words linked across both waveforms; Play walks word by word through Ilan's whisper into Mara's next line while each avatar pulses with its voice.
- When you click
- Click or arrow to a line, Enter to edit its text, add tags from the Tag menu (T) at the caret, switch a line's speaker from its avatar (S), regenerate (R), pick a take, compare the take in the cut with another, play and pause with Space, scrub the ruler.
- Look
- two flat areas split by hairlines, 10px radius, streamed bars and word sweep, sans with mono times type
- Variations
- Studio night, Paper, Ice
- Files
- index.html, style.css, script.js and prompt.md. No framework, no CDN, works offline.
The prompt and the files
Paste the prompt into Claude, ChatGPT, Lovable or any coding agent to rebuild it in your own product, or take the three files as they are.
Loading the files